JP2019164591A - Information processing device, information processing method, and information processing program - Google Patents

Abstract

To provide a user with appropriate information.SOLUTION: An information processing device comprises an acquisition unit, a determination unit, and a provision unit. The acquisition unit acquires fake news-related information related to content. The determination unit determines whether the content meets conditions on the fake news-related information on the basis of the content-related information acquired by the acquisition unit. The provision unit provides fake opinion information serving as decision-making information for determining whether the content corresponds to the fake news on the basis of the determination made by the determination unit and displayed together with the content in the terminal device used by a user to the terminal device.SELECTED DRAWING: Figure 3

Description

  The present invention relates to an information processing apparatus, an information processing method, and an information processing program.

  2. Description of the Related Art Conventionally, techniques for providing various information such as contents to users are known. There is also known a technique for providing information as a judgment material to a user. For example, there is provided a data determination support system technology that enables an investor or the like to easily make an investment determination. For example, in such a technique, the time-series data of the first value indicating a certain event, the time-series data of the second value indicating an event different from the event, and the data arranged in time series are displayed. By doing so, the user's judgment in investment is supported.

JP 2014-167688 A

  However, with the above-described conventional technology, it may be difficult to provide appropriate information to the user. For example, in the case where the comparison is not effective in time series, it is difficult to provide appropriate information to the user. For example, in comparison in time series, it may be difficult to determine whether the content is true or false.

  The present application has been made in view of the above, and an object thereof is to provide an information processing apparatus, an information processing method, and an information processing program that provide appropriate information to a user.

  The information processing apparatus according to the present application determines whether the content satisfies a fake nice condition based on the acquisition unit that acquires content-related information related to the content and the content-related information acquired by the acquisition unit And a terminal device used by a user, which is fake opinion information that is used as a material for determining whether the content corresponds to the fake nice when the content is determined to satisfy the condition by the determination unit. And a providing unit that provides the terminal device with fake opinion information displayed together with the content.

  According to one aspect of the embodiment, there is an effect that appropriate information can be provided to the user.

FIG. 1 is a diagram illustrating an example of information processing according to the embodiment. FIG. 2 is a diagram illustrating a configuration example of the information processing system according to the embodiment. FIG. 3 is a diagram illustrating a configuration example of the information processing apparatus according to the embodiment. FIG. 4 is a diagram illustrating an example of the provider information storage unit according to the embodiment. FIG. 5 is a diagram illustrating an example of a content information storage unit according to the embodiment. FIG. 6 is a diagram illustrating an example of the individual score information storage unit according to the embodiment. FIG. 7 is a diagram illustrating an example of the determination information storage unit according to the embodiment. FIG. 8 is a diagram illustrating an example of the authenticity result information storage unit according to the embodiment. FIG. 9 is a flowchart illustrating an example of information processing according to the embodiment. FIG. 10 is a flowchart illustrating an example of information processing according to the embodiment. FIG. 11 is a diagram illustrating an example of display of fake opinion information according to the embodiment. FIG. 12 is a hardware configuration diagram illustrating an example of a computer that implements the functions of the information processing apparatus.

  Hereinafter, an information processing apparatus, an information processing method, and an information processing program according to the present application (hereinafter referred to as “embodiment”) will be described in detail with reference to the drawings. Note that the information processing apparatus, the information processing method, and the information processing program according to the present application are not limited by this embodiment. In the following embodiments, the same portions are denoted by the same reference numerals, and redundant description is omitted.

(Embodiment)
[1. Information processing)
First, an example of information processing according to the embodiment will be described with reference to FIG. FIG. 1 is a diagram illustrating an example of information processing according to the embodiment. The example of FIG. 1 illustrates a case where the information processing apparatus 100 determines whether or not each content satisfies a fake nice condition based on content-related information related to the content. Note that the fake news referred to here may be news (content) including incorrect information, false information that does not exist, information that is not fact, inaccurate information, and the like. In addition, the fake news is not limited to the above, and may be various contents including information that makes the user who browsed the site misunderstood. The content may include information that is intended to cause an error. The example in FIG. 1 shows a case where the content is a news article, but the content may be any content as long as the authenticity of the content is important. Each content is provided by a content provider (hereinafter, simply referred to as “provider”) that provides the content. In the example of FIG. 1, the information processing device 100 provides a user with fake opinion information that is used as a material for determining whether content corresponds to fake nice based on the determination result.

[Configuration of information processing system]
Prior to the description of the processing shown in FIG. 1, the information processing system 1 shown in FIGS. 1 and 2 will be described. As illustrated in FIG. 2, the information processing system 1 includes a terminal device 10, a providing source device 20, and an information processing device 100. The terminal device 10, the providing source device 20, and the information processing device 100 are connected via a predetermined network N so as to be communicable by wire or wirelessly. FIG. 2 is a diagram illustrating a configuration example of the information processing system according to the embodiment. Note that the information processing system 1 illustrated in FIG. 2 may include a plurality of terminal devices 10, a plurality of providing source devices 20, and a plurality of information processing devices 100.

  The terminal device 10 is an information processing device used by a user. The terminal device 10 is realized by, for example, a smartphone, a tablet terminal, a notebook PC (Personal Computer), a desktop PC, a mobile phone, a PDA (Personal Digital Assistant), or the like. In the example shown in FIG. 1, the case where the terminal device 10 is a smartphone used by the user is shown. Hereinafter, the terminal device 10 may be referred to as a user. That is, hereinafter, the user can be read as the terminal device 10. Specifically, FIG. 1 illustrates a case where the terminal device 10 is a smartphone used by a user identified by the user ID “U1” (hereinafter, may be referred to as “user U1”).

  The provider device 20 is an information processing device used by a content provider. The provider device 20 may be used by any entity as long as it is a content provider, and is used by various providers such as companies and individuals. The provider apparatus 20 is realized by, for example, a smartphone, a tablet terminal, a notebook PC, a desktop PC, a mobile phone, a PDA, or the like. FIG. 1 shows a case where the providing apparatus 20 is a notebook PC.

  In the example illustrated in FIG. 1, the providing source device 20 is described as providing source devices 20-1 to 20-4 according to the providing source that uses the providing source device 20. For example, the provider device 20-1 is the provider device 20 used by the provider (provider CP11) identified by the provider ID “CP1”. The provider device 20-1 is an information processing device that is used by an administrator of the A medium that is the provider CP11. Thus, when “provider CP * (* is an arbitrary numerical value)” is described, it indicates that the provider is a provider identified by the provider ID “CP *”. For example, when “provider CP11” is described, the provider is a provider identified by the provider ID “provider CP11”. Hereinafter, the providing source devices 20-1 to 20-4 are referred to as providing source devices 20 when they are described without particular distinction.

  The information processing apparatus 100 is an information processing apparatus that determines whether a content satisfies a condition regarding fake nice based on content-related information related to the content. For example, the information processing apparatus 100 is an information processing apparatus that provides the terminal apparatus 10 with fake opinion information that is used to determine whether content corresponds to fake nice based on the determination.

  From here, a specific process is demonstrated using FIG. In the example of FIG. 1, the information processing apparatus 100 acquires the content CT11 of the providing source CP11 from the providing source apparatus 20-1 (Step S11-1). For example, the provider CP11 transmits the content CT11 to the information processing apparatus 100 using the provider apparatus 20-1. When “content CT * (* is an arbitrary numerical value)” is described in this way, it indicates that the content is content identified by the content ID “CT *”. For example, when described as content CT11, it indicates various information such as content information such as character information and image information included in the content identified by the content ID “CT11”, information indicating the provider, and category information. To do.

  Further, the information processing apparatus 100 acquires the content CT12 of the provider CP12 from the provider apparatus 20-2 (Step S11-2). Further, the information processing apparatus 100 acquires the content CT13 of the providing source CP13 from the providing source apparatus 20-3 (Step S11-3). Further, the information processing apparatus 100 acquires the content CT14 of the providing source CP14 from the providing source apparatus 20-4 (Step S11-4). For example, the provider CP12 to CP14 transmit the contents CT12 to CT14 to the information processing apparatus 100 using the provider devices 20-2 to 20-4, respectively.

  Note that steps S11-1 to S11-4 are for explaining the processing, and any of steps S11-1 to S11-4 may be performed first, and each of steps S11-1 to S11-4 may be performed. May be performed multiple times. For example, the information processing apparatus 100 may acquire the content of each provider by performing each step S11 a plurality of times at a predetermined timing. Hereinafter, when it demonstrates without distinguishing step S11-1-S11-4, it is named step S11 generically.

  Then, the information processing apparatus 100 registers the contents CT11 to CT14 acquired in step S11 (step S12). The information processing apparatus 100 stores the contents CT11 to CT14 in the storage unit 120 (see FIG. 3). In the example of FIG. 1, the information processing apparatus 100 stores information extracted from the contents CT11 to CT14 and the contents CT11 to CT14 in the content information storage unit 122.

  The content information storage unit 122 illustrated in FIG. 1 includes items such as “content ID”, “content information”, “provider ID”, “category”, “cited content”, and “content”. In addition, although illustration is abbreviate | omitted in FIG. 1, the content information storage part 122 memorize | stores the information regarding the date when each content was produced.

  “Content ID” indicates identification information for identifying the content. “Content information” indicates the content identified by the corresponding content ID. In the example of FIG. 1, the content information is indicated by an abstract code such as “CDT11”, but each content information may include specific information of the content such as character information and image information included in the article. For example, the content information stores information corresponding to the content indicated in parentheses such as “article A” and “article B”.

  The “provider ID” indicates identification information for identifying the provider of the corresponding content. “Category” indicates classification information based on the content. “Quoted content” indicates the content on which the corresponding content is generated. The cited content mentioned here may include other content that is cited in the content or other content that serves as an information source for the content. “Content” indicates the specific content of the corresponding content. For example, the information processing apparatus 100 extracts an important keyword (topic) from character information included in the content. Note that the information processing apparatus 100 may extract a topic from character information by appropriately using various conventional methods such as topic analysis (analysis). For example, the information processing apparatus 100 may extract a topic from character information by appropriately analyzing the character information using a natural language processing technique such as morphological analysis. Further, for example, the information processing apparatus 100 may determine whether the content is positive or negative about the topic based on the syntactic relationship between the extracted topic and a keyword indicating topic affirmation or denial. . Then, the information processing apparatus 100 stores information indicating whether the content is positive or negative about the topic in “content”.

  In the example of FIG. 1, the content CT11 indicates that the article A is provided by the providing source CP11. The content CT11 indicates that it is classified into the category “politics”. The content CT11 indicates that there is no cited content. In addition, the content CT11 indicates that the tax increase after the election is positive. That is, the content CT11 indicates that it is a news article about a tax increase after the election.

  Then, the information processing apparatus 100 calculates a score of each content (hereinafter also referred to as “fake score”) (step S13). For example, the information processing apparatus 100 calculates the fake scores of the contents CT11 to CT14. In the example of FIG. 1, the information processing apparatus 100 calculates the fake scores of the contents CT11 to CT14 based on the information stored in the individual score information 123.

  The “determination element ID” in the individual score information storage unit 123 illustrated in FIG. 1 indicates identification information for identifying each determination element. The “determination element” in the individual score information storage unit 123 illustrated in FIG. 6 indicates the content of the determination element identified by the corresponding determination element ID. “Individual score” in the individual score information storage unit 123 shown in FIG. 1 indicates an individual score of each determination element.

  In the example of FIG. 1, the determination element (determination element JE11) identified by the determination element ID “JE11” indicates that there is a content creation date. Judgment element JE11 indicates that an individual score “0.2” is assigned to content that has no creation date, which may be fake news.

  In the example of FIG. 1, the determination element (determination element JE12) identified by the determination element ID “JE12” indicates the presence or absence of evidence citation. Judgment element JE12 indicates that an individual score “0.5” is assigned to content with no evidence citation, which may be fake news. Further, the determination element (determination element JE13) identified by the determination element ID “JE13” indicates that there is a difference in content from the content of the other provider. The determination element JE13 indicates that the content having a difference in content from the content of the other provider is assigned with the individual score “7” because there is a possibility that the content is fake news. Note that the information processing apparatus 100 may calculate an individual score, or may acquire an individual score from another information processing apparatus. The calculation of the individual score will be described later.

  For example, the information processing apparatus 100 calculates a score (fake score) using the following formula (1).

y = ω ₁ · x ₁ + ω ₂ · x ₂ + ω ₃ · x ₃ ... + ω _N · x _N (1)

“Ω _N ” and “ _N ” in “x _N ” in the right side of the formula (1) indicate an arbitrary number. For example, “N” indicates the number of determination elements. Further, “y” in the left side of the above formula (1) corresponds to the score output by the model. For example, “y” indicates a score (fake score) used to determine whether the news is fake news.

In the above formula (1), “x” corresponds to a determination element (feature). For example, “x ₁ ” in the above formula (1) corresponds to the determination element “no creation date”. In this case, if there is no creation date in the input content, “x ₁ ” becomes “1”. If the input content has a creation date, “x ₁ ” becomes “0”.

For example, for example, “x ₂ ” in the above formula (1) corresponds to the determination element “no evidence citation”. In this case, “x ₂ ” is “1” when there is no citation of evidence in the input content. In addition, if there is evidence citation in the input content, “x ₂ ” is “0”. For example, for example, “x ₃ ” in the above formula (1) corresponds to the determination element “difference from other providers”. In this case, if the input content is different from the content of another provider, “x ₂ ” is “1”. If the input content is not different from the content of other providers, “x ₂ ” is “0”.

In the above formula (1), “ω” is the weight of “x” and indicates the individual score of the corresponding determination element. For example, “ω ₁ ” in the above formula (1) is a weight (individual score) of “x ₁ ”, “ω ₂ ” is a weight (individual score) of “x ₂ ”, and “ω ₃ ” Is a weight (individual score) of “x ₃ ”. The information processing apparatus 100 calculates (generates) the individual score information by any method as long as the information processing apparatus 100 can calculate the information about the individual score based on the content related information related to the content. Also good.

  In the example of FIG. 1, the information processing apparatus 100 may use information indicating the reliability of the provider of each content stored in the provider information storage unit 121. The “credit (fake rate)” shown in the provider information storage unit 121 in FIG. 1 indicates the credit of the provider identified by the corresponding provider ID. For example, “credibility (fake rate)” indicates the proportion of content corresponding to fake news among the content provided by the provider. For example, when the credit rating (fake rate) is “5”, the probability that the content provided by the provider is fake news is 5%. In this case, the creditworthiness (fake rate) of the provider indicates that the provider can be trusted as the value decreases. In the example of FIG. 1, the credit quality of the provider CP11 is “2”, and the creditworthiness of the provider CP12 is “0”, indicating that the provider CP12 can be trusted more than the provider CP11. Note that the information processing apparatus 100 is not limited to the fake rate described above, and various information may be used as information indicating the trustworthiness of the provider.

  For example, in the example illustrated in FIG. 4, the provider (provider CP1) identified by the provider ID “CP1” indicates that the name is “A medium” and the type is “newspaper”. Further, the provider CP1 indicates that the reliability (fake rate) is “2” and the probability that the content provided by the provider CP1 is fake news is 2%.

  For example, the determination element JE13 which is the determination element “difference from other providers” has a difference in content from the contents of other providers whose reliability (fake rate) is less than a predetermined threshold, and the contents are the other providers It is determined that there is a difference between the content and the content.

In the example of FIG. 1, the information processing apparatus 100 determines that the content of the determination element JE13 is different from the content of the other provider whose reliability (fake rate) is less than “0.5”. It is determined that there is a difference between the content and the content. Here, among the contents CT11 to CT14, a certain content CT11 is the content of the other providers CP12 to CP14 whose only content is “tax increase after election = affirmation” and whose credit rating (fake rate) is less than “0.5”. The contents of CT11 to CT14 are “tax increase after election = denial”. Therefore, the information processing apparatus 100 determines that the content CT11 corresponds to the determination element JE13. Therefore, the information processing apparatus 100 sets “x ₃ ” corresponding to the determination element JE13 to “1” for the content CT11 in the above formula (1).

  Through the processing as described above, the information processing apparatus 100 calculates the fake score of each content as shown in the determination information storage unit 124 in FIG. In the example of FIG. 1, the information processing apparatus 100 calculates a fake score for each content based on the above formula (1) and the content information of each content.

  The “content ID” in the determination information storage unit 124 illustrated in FIG. 1 indicates identification information for identifying the content. The “fake score” in the determination information storage unit 124 illustrated in FIG. 1 indicates the fake score of the content identified by the corresponding content ID. For example, the score stored in the “fake score” indicates the degree of possibility that the corresponding content is fake news.

  In the example of FIG. 1, the information processing apparatus 100 calculates the fake score of the content CT11 as “15”. In addition, the information processing apparatus 100 calculates the fake score of the content CT12 as “0.02”. The information processing apparatus 100 calculates the fake score of the content CT13 as “0.5”. In addition, the information processing apparatus 100 calculates the fake score of the content CT14 as “1”.

  Then, the information processing apparatus 100 determines whether or not a condition regarding fake nice is satisfied (step S14). For example, when one content satisfies a condition related to fake nice, there is a possibility that the one content is fake news (hereinafter, described as “possible fake possibility”). judge. For example, when one content does not satisfy the condition regarding fake nice, there is no possibility that the one content is fake news (hereinafter, described as “no fake possibility”). Is determined.

  For example, if the fake score of the content is equal to or greater than a predetermined threshold (hereinafter also referred to as “determination threshold”), the information processing apparatus 100 determines that the content has the possibility of fake. In the example of FIG. 1, the information processing apparatus 100 determines that the content has the possibility of fake when the fake score of the content is equal to or greater than the determination threshold “10”.

  For example, since the fake score “15” of the content CT11 is equal to or greater than the determination threshold “10”, the information processing apparatus 100 determines that the content CT11 has the possibility of fake. Further, the information processing apparatus 100 determines that the content CT12 is not likely to be fake because the fake score “0.02” of the content CT12 is less than the determination threshold “10”. Since the fake score “0.5” of the content CT13 is less than the determination threshold “10”, the information processing apparatus 100 determines that the content CT13 has no possibility of fake. Further, the information processing apparatus 100 determines that the content CT14 has no possibility of fake because the fake score “1” of the content CT14 is less than the determination threshold “10”. As described above, the information processing apparatus 100 determines that the content CT11 has the possibility of fake and determines that the contents CT12 to CT14 have no possibility of fake. And the information processing apparatus 100 provides the fake opinion information which shows the fake possibility of each content CT11-CT14 based on determination with a content.

  The information processing apparatus 100 acquires a content request from the terminal device 10 used by the user U1 (step S13). In FIG. 1, the terminal device 10 requests content from the information processing device 100 in accordance with the operation of the user U1.

  Then, the information processing apparatus 100 determines content to be provided to the user U1 in response to a content request from the terminal device 10 (step S16). Note that the information processing apparatus 100 determines content to be provided to the user U1 using various information as appropriate, but in FIG. 1, the information processing apparatus 100 transmits the content CT11 to the user U1 in order to simplify the description. The content to be provided is determined. For example, the information processing apparatus 100 may determine content to be provided to the user U1 based on the attribute information of the user U1. For example, when the user U1 is a user interested in politics, the information processing apparatus 100 may determine content belonging to the category “politics” as content to be provided to the user U1. Further, the information processing apparatus 100 may determine not to provide the content determined to have fake possibility. In this case, the information processing apparatus 100 may determine content other than the content CT11 determined to have fake possibility as content to be provided to the user U1.

  In the example of FIG. 1, the information processing apparatus 100 adds information to the content CT11 determined as the content to be provided to the user U1 (step S17). The information processing apparatus 100 adds information that is used as a material for determining whether the content CT11 is fake news to the content CT11. For example, the information processing apparatus 100 adds the fake score “15” and the opinion information INF11 including information indicating the possibility of fake to the information provided to the user U1. As shown in the providing content DC11, the information processing apparatus 100 adds the opinion information INF11 as information to be provided to the user U1 together with the content information CDT11 (article A) of the content CT11.

  Thereafter, the information processing apparatus 100 provides the terminal apparatus 10 with the content CT11 and fake score “15” and opinion information INF11 indicating that the fake possibility exists (step S18). The information processing apparatus 100 transmits the content CT11, the fake score “15”, and the fake opinion information INF11 indicating the possibility of fake to the terminal apparatus 10. Then, the terminal device 10 that has received the content CT11 and the fake opinion information INF11 displays the received information (step S19). The terminal device 10 displays the content CT11 and the fake opinion information INF11. In the example of FIG. 1, the terminal device 10 displays the fake opinion information INF51 in the area AR11 located in the vicinity of the content CT11. Specifically, the terminal device 10 displays the content CT11 which is the content of allowing the tax increase after the election of the XX newspaper company, and the fake opinion information INF51 indicating that the content may be fake (suspect) To do.

  As described above, the information processing apparatus 100 provides the terminal apparatus 10 with the content to be provided and fake opinion information indicating whether the content is a fake. Thereby, the user who has received the information can browse the content together with the fake opinion information that is a material for determining whether the content is fake news. Therefore, the user can browse the content in consideration of information about the authenticity of the content. Therefore, the information processing apparatus 100 can provide appropriate information to the user.

[1-1. Judgment)
In the example of FIG. 1, the information processing apparatus 100 determines whether a content has a possibility of fake based on a comparison between a fake score that is a sum of individual scores of each determination element and a determination threshold. Determine if there is a possibility. However, the information processing apparatus 100 is not limited to the above, and may determine whether the content has the possibility of fake or not by various methods.

[1-1-1. (Applicable to specific judgment factors)
When a certain content corresponds to a specific determination element, the information processing apparatus 100 may determine that the content has a possibility of fake. For example, the information processing apparatus 100 may determine that the content of a certain provider has a fake possibility if the content is different from the content of another provider. For example, when the content of one provider is different from the content of another provider that can be trusted more than the one provider, the information processing apparatus 100 may determine that the content has the possibility of fake.

  For example, the information processing apparatus 100 may determine that the content of one provider is different from the content of another provider having higher reliability than the one provider, and that the content may be fake. . That is, the information processing apparatus 100 may determine that the content of one provider has a possibility of fake when the content of the provider is different from the content of the other provider that is less reliable than the provider. . For example, the information processing apparatus 100 may determine that the content of one provider is different from the content of another provider having a fake rate lower than that of the one provider as having the possibility of fake. Good. For example, the information processing apparatus 100 may determine that the content has a possibility of fake when the content of one provider is different from the content of a plurality of other providers (for example, 5).

  For example, when a certain content corresponds to “difference in content from other provider's content” that is the determination element JE13, the information processing device 100 may determine that the content is likely to be fake. For example, when a certain content corresponds to the “difference between content and content of another provider” that is the determination element JE13, the information processing apparatus 100 determines that the content is likely to be fake regardless of the fake score of the content. May be.

[1-1-2. (Citation content information)
Further, the information processing apparatus 100 may determine whether the content has the possibility of fake or not with the possibility of using the content of the cited content that is other content cited by the content. For example, when it is determined that the cited content of one content is fake news, the information processing device 100 may determine that the one content has a possibility of fake. For example, if the cited content of one content is the content CT1 (see FIG. 8) that is determined to be fake news, the information processing apparatus 100 determines that the one content has a possibility of fake. Also good.

  Further, for example, when the cited content of one content has a possibility of fake news, the information processing apparatus 100 may determine that the one content has a possibility of fake. In the example of FIG. 1, the information processing apparatus 100 may determine that the content CT21 has the possibility of fake because the content CT11 that is the cited content of the content CT21 has the possibility of fake news.

  For example, the information processing apparatus 100 may calculate the fake score of the content using a determination element related to the cited content of the content. For example, the information processing apparatus 100 may calculate the fake score of the content using the individual score of the determination element regarding the cited content of the content.

  For example, the information processing apparatus 100 may calculate the fake score of the content using a determination element (hereinafter referred to as “determination element JEX”) regarding whether or not the cited content of the content may be fake news. For example, the information processing apparatus 100 may calculate the fake score of the content using the individual score of the determination element JEX.

  For example, when the cited content of the content is fake news, the information processing apparatus 100 may determine that the content corresponds to the determination element JEX. For example, when the cited content of the content has the possibility of fake news, the information processing apparatus 100 may determine that the content corresponds to the determination element JEX. In this case, the information processing apparatus 100 may add the individual score of the determination element JEX to the fake score of the content.

[1-1-3. (Provider information)
In addition, the information processing apparatus 100 may determine whether the content has a fake possibility or not by using the content provider information. For example, the information processing apparatus 100 may calculate the fake score of the content using a determination element regarding the content provider. For example, the information processing apparatus 100 may calculate the fake score of the content using the individual score of the determination element regarding the content provider.

  For example, the information processing apparatus 100 may calculate the fake score of the content using a determination element regarding whether the content provider can be trusted (referred to as “determination element JEY”). For example, the information processing apparatus 100 may calculate the fake score of the content using the individual score of the determination element JEY.

  For example, when the reliability of the content provider is poor, the information processing apparatus 100 may determine that the content corresponds to the determination element JEY. For example, the information processing apparatus 100 may determine that the content corresponds to the determination element JEY when the reliability of the content provider is equal to or greater than a predetermined threshold (provider threshold). That is, the information processing apparatus 100 may determine that the content corresponds to the determination element JEY when the fake rate of the content provider is equal to or greater than a predetermined threshold (provider threshold). In this case, the information processing apparatus 100 may add the individual score of the determination element JEY to the fake score of the content.

[1-2. (Calculation of individual score)
As described above, the information processing apparatus 100 may generate (calculate) the individual score of the determination element used for calculating the fake score in the example of FIG. For example, the information processing apparatus 100 may derive (calculate) the individual score of each determination element using the content information stored in the authenticity result information storage unit 125 (see FIG. 8).

  For example, the truth / false result information storage unit 125 in FIG. 8 stores various pieces of information related to content that has been determined whether it was fake news among the content provided in the past. For example, the authenticity result information storage unit 125 stores various types of information related to content for which authenticity (authenticity) is confirmed. Therefore, the information processing apparatus 100 receives information corresponding to each determination element extracted from the content information in the authenticity result information storage unit 125 as input, and uses information indicating whether or not the fake shown in the confirmed fake result is correct information. An individual score may be calculated.

  For example, the information processing apparatus 100 may derive (calculate) each discriminating element as a feature (feature amount) and the weight of each discriminating element as an individual score. For example, the information processing apparatus 100 calculates an individual score by performing learning using content information stored in the authenticity result information storage unit 125 as learning data (teacher data). For example, the information processing apparatus 100 generates a model by learning processing (model generation) using content information stored in the authenticity result information storage unit 125, and thereby features (determination elements) in the model. The weight corresponding to each of these may be calculated as an individual score.

  For example, the information processing apparatus 100 may calculate the individual score regarding the determination element by learning the weight (individual score) of each feature (determination element) using the above formula (1).

  The information processing apparatus 100 may calculate the individual score information of each determination element by learning the weight (individual score) of each feature (determination element) using the content determined to be fake as a positive example. For example, the information processing apparatus 100 may calculate the individual score information of each determination element, using the content CT1 determined as fake news in the authenticity result information storage unit 125 in FIG. 8 as a positive example. For example, when the content information CDT1 of the content CT1 is input, the information processing apparatus 100 performs the learning process so that the score output by the model is a score that is equal to or higher than a predetermined threshold (eg, “10”). Do. For example, when the content CT1 is a target, the information processing apparatus 100 learns that the value (score) of “y” in the above formula (1) is equal to or greater than a determination threshold (for example, “10”). Process.

  In addition, for example, the information processing apparatus 100 may calculate the individual score information of each determination element using the content CT2 that is determined not to be fake news in the authenticity result information storage unit 125 in FIG. 8 as a negative example. Good. For example, when the content information CDT2 of the content CT2 is input, the information processing apparatus 100 performs the learning process so that the score output by the model becomes a score (for example, “0” or the like) smaller than a predetermined threshold. Do. For example, when the content CT2 is targeted, the information processing apparatus 100 has a value (score) of “y” in the above formula (1) that is smaller than a determination threshold (for example, “0”). Thus, the learning process is performed.

  Further, for example, the information processing apparatus 100 may calculate the individual score information of each determination element by using the content CT3 that is determined not to be fake news in the authenticity result information storage unit 125 in FIG. 8 as a negative example. Good. For example, when the content information CDT3 of the content CT3 is input, the information processing apparatus 100 performs the learning process so that the score output by the model is a score (for example, “0” or the like) smaller than a predetermined threshold. Do. For example, when the content CT3 is targeted, the information processing apparatus 100 has a value (score) of “y” in the above formula (1) that is smaller than a determination threshold (for example, “0”). Thus, the learning process is performed.

  For example, the information processing apparatus 100 may calculate an individual score for each category of content. That is, the information processing apparatus 100 may generate a model for each content category. In the above example, the information processing apparatus 100 may calculate the individual score for the category “politics” using the contents CT1 and CT2 to which the category “politics” belongs. Further, the information processing apparatus 100 may calculate an individual score for the category “entertainment” using the content CT3 to which the category “entertainment” belongs. In this case, the information processing apparatus 100 may calculate the fake score of the content using the individual score corresponding to the content category.

  Note that the method of learning (generating) the model in the calculation of the individual score is not limited to the above-described method, and any known technique can be applied. Each model may be generated using various conventional techniques relating to machine learning as appropriate. For example, the model generation may be performed using a technique related to machine learning of supervised learning such as SVM (Support Vector Machine). Further, for example, the model generation may be performed using a technique related to machine learning of unsupervised learning. For example, the generation of the model may be performed using a deep learning technique. For example, the model generation may be performed by appropriately using various deep learning techniques such as DNN (Deep Neural Network), RNN (Recurrent Neural Network), and CNN (Convolutional Neural Network). The description relating to the generation of the model is merely an example, and the generation of the model may be performed by a learning method appropriately selected according to information that can be acquired.

[1-3. (Content display)
In the example of FIG. 1, the information processing apparatus 100 provides one content CT11 to the terminal apparatus 10, and the terminal apparatus 10 displays the fake opinion information INF11 of the content CT11 including the fake score and the like together with the content CT11. Although shown, the display mode may be various modes. For example, the information processing apparatus 100 may provide the terminal apparatus 10 with a list content in which a plurality of contents and fake opinion information of each content are displayed side by side.

  For example, the information processing apparatus 100 may provide the terminal device 10 with a list content in which a plurality of similar contents and fake opinion information of each content are displayed side by side. For example, the information processing apparatus 100 may provide the terminal apparatus 10 with a list content in which a plurality of contents distributed by a similar provider (medium) and fake opinion information of each content are displayed side by side. For example, the information processing apparatus 100 generates list content in which a plurality of contents and fake opinion information of each content are displayed side by side based on various types of information stored in the storage unit 120 (see FIG. 3). This point will be described with reference to FIG. FIG. 11 is a diagram illustrating an example of display of fake opinion information according to the embodiment. Note that description of points similar to those in FIG.

  In the example of FIG. 11, the information processing apparatus 100 provides the terminal device 10 with a list content in which the content CT51, the content CT52, and the content CT53 are displayed in a list in the vertical direction. Further, the information processing apparatus 100 displays the list contents arranged in the vicinity of the contents corresponding to the fake opinion information INF51 of the content CT51, the fake opinion information INF52 of the content CT52, and the fake opinion information INF53 of the content CT53. The case where it provides to is shown.

  As shown in FIG. 11, the terminal device 10 is a list in which content CT51 whose information source is XX newspaper, content CT52 whose information source is YY newspaper, and content CT53 whose information source is ZZ newspaper are arranged in the vertical direction. indicate. Further, the terminal device 10 displays the fake opinion information INF51 of the content CT51 in the vicinity of the content CT51. Specifically, the terminal device 10 displays opinion information INF51 indicating that the fake score of the content CT51 is “15” and the fake degree is “high” below the content CT51.

  Further, the terminal device 10 displays the fake opinion information INF52 of the content CT52 in the vicinity of the content CT52. Specifically, the terminal apparatus 10 displays opinion information INF52 indicating that the fake score of the content CT52 is “0.5” and the fake degree is “low” below the content CT52. Further, the terminal device 10 displays the fake opinion information INF53 of the content CT53 in the vicinity of the content CT53. Specifically, the terminal apparatus 10 displays the opinion information INF53 indicating that the fake score of the content CT53 is “7” and the fake degree is “medium” below the content CT53. Thereby, the user provided with the list content from the information processing apparatus 100 can perform browsing while comparing a plurality of contents. In this way, the user can browse the content while comparing each content while referring to the fake opinion information of each content.

[1-4. (Level judgment)
For example, the information processing apparatus 100 may perform the determination of the degree of fake at a plurality of levels as described above using a plurality of threshold values. For example, the information processing apparatus 100 may determine the fake degree of content using two threshold values, a first threshold value and a second threshold value.

  For example, the information processing apparatus 100 may determine that the fake degree of the content is “high” when the fake score of the content is greater than or equal to a first threshold (for example, “10” or the like). For example, when the fake score is less than a first threshold value (for example, “10” or the like) and greater than or equal to a second threshold value (for example, “5” or the like), the prediction device 100 determines that the fake degree of the content is “medium”. May be. For example, when the fake score is less than a second threshold (for example, “5” or the like), the prediction device 100 may determine that the fake degree of the content is “low”.

[1-5. (Change content)
Note that the information processing apparatus 100 may provide various services using information collected in the determination regarding the fake news. The information processing apparatus 100 may provide a service using information that ensures the authenticity among the information collected in the determination regarding the fake news. The information processing apparatus 100 may be able to detect alteration of content by appropriately using various conventional techniques. For example, the information processing apparatus 100 may make it possible to detect alteration of content by appropriately using various encryption techniques. For example, the information processing apparatus 100 may determine the authenticity of the content by using various encryption techniques as appropriate to confirm that the content has not been tampered with.

  For example, the information processing apparatus 100 may be able to grasp the alteration of the content by using a technique related to the block chain. For example, the information processing apparatus 100 may make it possible to grasp the alteration of the content by connecting one content as one block and connecting the dependency relationship like a chain. For example, the information processing apparatus 100 may maintain the information after certifying the authenticity by associating the information that guarantees the authenticity with a block chain. Further, for example, the information processing apparatus 100 may maintain the information by linking the information indicating that it is false with a block chain to prove the falseness. For example, the information processing apparatus 100 may use various conventional techniques related to hashes such as various hash functions. For example, the information processing apparatus 100 may use SHA (Secure Hash Algorithm) technology such as SHA-256 and SHA-512. For example, the information processing apparatus 100 may use the technique of RIPEMD-160. Note that the information processing apparatus 100 is not limited to the hash, and any technique may be used as long as it can be detected that the content has not been tampered (changed). For example, the information processing apparatus 100 may use various conventional techniques related to elliptic curve encryption such as elliptic curve DSA (Digital Signature Algorithm).

  For example, the information processing apparatus 100 may make it possible to grasp the alteration of the content by connecting each content as one block and connecting the citation relationship between the content like a chain. For example, the information processing apparatus 100 uses cipher information (for example, a hash value) generated based on content (origin content) that is the origin of a certain content to link citation relationships between the contents like a chain. Thus, it may be possible to grasp the alteration of the content.

  For example, when there is content that cites the origin content (first citation content), the information processing apparatus 100 may generate encryption information (first citation encryption information) that is generated based on the first citation content. For example, the information processing apparatus 100 may generate block data (first citation block data) corresponding to the first citation content based on the origin encryption information and the first citation encryption information.

  Further, for example, when there is content that cites the first citation content (second citation content), the information processing apparatus 100 may generate encryption information (second citation encryption information) based on the second citation content. . For example, the information processing apparatus 100 may generate block data (second quote block data) corresponding to the second quote content based on the first quote cipher information and the second quote cipher information. As described above, the information processing apparatus 100 may generate information (block chain information) in which blocks of content (block data) are linked based on a citation relationship between the contents.

  In this case, for example, the information processing apparatus 100 may determine whether it is fake news by a technique related to a block chain. For example, when a certain origin content is not fake news (for example, fact), the information processing apparatus 100 has been tampered with each block (quoted block) connected by a chain (genuine chain) starting from the origin content. It may be determined whether it is not (not fake news). For example, the information processing apparatus 100 may determine that the target content is not fake news when it is verified that the content (target content) from which the content is cited is not falsified in the genuine chain. Good.

  For example, when a certain origin content is fake news, the information processing apparatus 100 determines whether each block (quoted block) connected in a chain (fake chain) starting from the origin content has been changed. Also good. For example, the information processing apparatus 100 determines that the target content is fake news when it is verified in the fake chain that the content (target content) from which the content is cited is not changed to the source content. Also good.

  Thereby, the information processing apparatus 100 can suppress the possibility that the content is falsified while guaranteeing the content. The information processing apparatus 100 can perform proof of authenticity or falseness. Therefore, the information processing apparatus 100 can suppress the possibility that the altered content will be distributed. Thus, the information processing apparatus 100 can suppress the possibility that fake news is distributed.

[2. Configuration of information processing apparatus]
Next, the configuration of the information processing apparatus 100 according to the embodiment will be described with reference to FIG. FIG. 3 is a diagram illustrating a configuration example of the information processing apparatus 100 according to the embodiment. As illustrated in FIG. 3, the information processing apparatus 100 includes a communication unit 110, a storage unit 120, and a control unit 130. The information processing apparatus 100 includes an input unit (for example, a keyboard and a mouse) that receives various operations from an administrator of the information processing apparatus 100 and a display unit (for example, a liquid crystal display) for displaying various types of information. You may have.

(Communication unit 110)
The communication unit 110 is realized by, for example, a NIC (Network Interface Card). The communication unit 110 is connected to the network by wire or wirelessly, and transmits / receives information to / from the terminal device 10 and the provider device 20.

(Storage unit 120)
The storage unit 120 is realized by, for example, a semiconductor memory device such as a RAM (Random Access Memory) or a flash memory, or a storage device such as a hard disk or an optical disk. As illustrated in FIG. 3, the storage unit 120 according to the embodiment includes a provider information storage unit 121, a content information storage unit 122, an individual score information storage unit 123, a determination information storage unit 124, and authenticity result information. And a storage unit 125.

(Provider information storage unit 121)
The provider information storage unit 121 according to the embodiment stores various types of information regarding the content provider. FIG. 4 is a diagram illustrating an example of the provider information storage unit according to the embodiment. The provider information storage unit 121 illustrated in FIG. 4 includes items such as “provider ID”, “name”, “type”, and “credit (fake rate)”.

  The “provider ID” indicates identification information for identifying the content provider. The content provider may be various providers such as a newspaper company, a magazine company, a content provider, and an individual user. “Name” indicates the name of the provider identified by the corresponding provider ID. FIG. 5 shows an example in which conceptual information such as “A medium” is stored in “name”, but in actuality, a specific business name such as “XX newspaper” may be used. . “Type” indicates the type of the provider identified by the corresponding provider ID. For example, “type” stores information indicating whether the provider identified by the corresponding provider ID is an individual or an organization (corporate), and information indicating the type of the medium. “Credit rating (fake rate)” indicates the credit rating of the provider identified by the corresponding provider ID. For example, “credibility (fake rate)” indicates the proportion of content corresponding to fake news among the content provided by the provider. For example, when the credit rating (fake rate) is “5”, the probability that the content provided by the provider is fake news is 5%. In this case, the creditworthiness (fake rate) of the provider indicates that the provider cannot be trusted as the value increases.

  For example, in the example illustrated in FIG. 4, the provider (provider CP1) identified by the provider ID “CP1” indicates that the name is “A medium” and the type is “newspaper”. Further, the provider CP1 indicates that the reliability (fake rate) is “2” and the probability that the content provided by the provider CP1 is fake news is 2%.

  Note that the provider information storage unit 121 is not limited to the above, and may store various types of information according to the purpose. For example, the provider information storage unit 121 may store information on the business scale such as the location of the provider, the number of employees of the provider, and sales. For example, the provider information storage unit 121 may store information related to the number of years since the provider started providing content.

(Content information storage unit 122)
The content information storage unit 122 according to the embodiment stores various types of information related to content (articles). FIG. 5 is a diagram illustrating an example of a content information storage unit according to the embodiment. The content information storage unit 122 illustrated in FIG. 5 includes items such as “content ID”, “content information”, “provider ID”, “category”, “quoted content”, and “content”. In addition, although illustration is abbreviate | omitted in FIG. 5, the content information storage part 122 memorize | stores the information regarding the date when each content was produced.

  “Content ID” indicates identification information for identifying the content. “Content information” indicates the content identified by the corresponding content ID. In the example of FIG. 5, the content information is indicated by an abstract code such as “CDT11”, but each content information may include specific information of the content such as character information and image information included in the article. For example, the content information stores information corresponding to the content indicated in parentheses such as “article A” and “article B”. Further, for example, “content information” stores a file path name indicating the storage location of the content.

  The “provider ID” indicates identification information for identifying the provider of the corresponding content. “Category” indicates classification information based on the content. “Quoted content” indicates the content on which the corresponding content is generated. “Content” indicates the specific content of information included in the corresponding content. For example, the information processing apparatus 100 extracts an important keyword (topic) from character information included in the content. Note that the information processing apparatus 100 may extract a topic from character information by appropriately using various conventional methods such as topic analysis (analysis). For example, the information processing apparatus 100 may extract a topic from character information by appropriately analyzing the character information using a natural language processing technique such as morphological analysis. Further, for example, the information processing apparatus 100 may determine whether the content is positive or negative about the topic based on the syntactic relationship between the extracted topic and a keyword indicating topic affirmation or denial. . Then, the information processing apparatus 100 stores information indicating whether the content is positive or negative about the topic in “content”.

  In the example of FIG. 5, the content (content CT11) identified by the content ID “CT11” is the article A provided by the providing source CP11. The content CT11 indicates that it is classified into the category “politics”. The content CT11 indicates that there is no cited content. In addition, the content CT11 indicates that the tax increase after the election is positive. That is, the content CT11 indicates that it is a news article about a tax increase after the election.

  The content information storage unit 122 is not limited to the above, and may store various types of information according to the purpose. For example, the content information storage unit 122 may store information related to the date and time when the content is acquired.

(Individual score information storage unit 123)
The individual score information storage unit 123 according to the embodiment stores individual score information regarding materials (elements) used for determination of fake news. For example, the individual score information storage unit 123 stores individual score information regarding each determination element (determination element) used when determining whether the content is fake news. FIG. 6 is a diagram illustrating an example of the individual score information storage unit according to the embodiment. The individual score information storage unit 123 illustrated in FIG. 6 includes items such as “determination element ID”, “determination element”, and “individual score”.

  The “determination element ID” indicates identification information for identifying each determination element. The “determination element” indicates the content of the determination element identified by the corresponding determination element ID. “Individual score” indicates an individual score of each determination element.

  In the example of FIG. 6, the determination element (determination element JE11) identified by the determination element ID “JE11” indicates that there is a content creation date. Judgment element JE11 indicates that an individual score “0.2” is assigned to content that has no creation date, which may be fake news.

  Further, the determination element (determination element JE12) identified by the determination element ID “JE12” indicates the presence or absence of evidence citation. Judgment element JE12 indicates that an individual score “0.5” is assigned to content with no evidence citation, which may be fake news. Further, the determination element (determination element JE13) identified by the determination element ID “JE13” indicates that there is a difference in content from the content of the other provider. The determination element JE13 indicates that the content having a difference in content from the content of the other provider is assigned with the individual score “7” because there is a possibility that the content is fake news.

  Note that the individual score information storage unit 123 is not limited to the above, and may store various individual score information according to the purpose.

(Decision information storage unit 124)
The determination information storage unit 124 according to the embodiment stores various types of information regarding determination of whether the content is fake news. FIG. 7 is a diagram illustrating an example of the determination information storage unit according to the embodiment. The determination information storage unit 124 illustrated in FIG. 7 includes items such as “content ID”, “fake score”, and “determination information”.

  “Content ID” indicates identification information for identifying the content. “Fake score” indicates the fake score of the content identified by the corresponding content ID. The “fake score” stores a score indicating the degree of possibility that the corresponding content is fake news. “Determination information” indicates a determination as to whether or not the corresponding content is fake news.

  In the example of FIG. 7, the content identified by the content ID “CT11” (content CT11) indicates that the fake score is “15”. Further, the content CT11 indicates that there is a possibility that it is fake news.

  The determination information storage unit 124 is not limited to the above, and may store various types of information depending on the purpose. For example, the determination information storage unit 124 may store information related to the date and time when the score is calculated and the date and time when the determination is performed.

(Authentication result information storage unit 125)
The true / false result information storage unit 125 according to the embodiment stores various types of information regarding the true / false result indicating whether the content is fake news. For example, the true / false result information storage unit 125 stores various pieces of information related to content that has been determined whether it was fake news among the content provided in the past. FIG. 8 is a diagram illustrating an example of the authenticity result information storage unit according to the embodiment. The authenticity result information storage unit 125 illustrated in FIG. 8 includes items such as “result ID”, “content ID”, “content information”, “provider ID”, “category”, “cited content”, and “determined fake result”. Have In addition, although illustration is abbreviate | omitted in FIG. 8, the authenticity result information storage part 125 memorize | stores the information regarding the date when each content was produced.

  “Result ID” indicates identification information for identifying a true / false result indicating whether the content is fake news. “Content ID” indicates identification information for identifying the content. “Content information” indicates the content identified by the corresponding content ID. In the example of FIG. 8, the content information is indicated by an abstract code such as “CDT1”, but each content information may include specific information of the content such as character information and image information included in the article. For example, the content information stores information corresponding to the content indicated in parentheses such as “article PA” and “article PB”. Further, for example, “content information” stores a file path name indicating the storage location of the content.

  The “provider ID” indicates identification information for identifying the provider of the corresponding content. “Category” indicates classification information based on the content. “Quoted content” indicates the content on which the corresponding content is generated. “Finalized fake result” indicates whether or not the corresponding content is fake news.

  In the example of FIG. 8, the true / false result identified by the result ID “RID1” indicates that the content (content CT1) identified by the content ID “CT1” is targeted. The content CT1 indicates that the article PA is provided by the providing source CP1. The content CT1 indicates that it is classified into the category “politics”. The content CT1 indicates that there is no cited content. Further, the confirmed fake result of the content CT1 indicates that it is fake (erroneous information). That is, the content CT1 is erroneous information and indicates that it corresponds to fake news.

  The authenticity result information storage unit 125 is not limited to the above, and may store various types of information according to the purpose. For example, the authenticity result information storage unit 125 may store information related to the date and time when the authenticity is confirmed.

(Control unit 130)
Returning to the description of FIG. 3, the control unit 130 is a controller, and is stored in a storage device inside the information processing apparatus 100 by, for example, a CPU (Central Processing Unit) or an MPU (Micro Processing Unit). Various programs (corresponding to an example of a distribution program) are executed by using the RAM as a work area. The control unit 130 is a controller, and is realized by an integrated circuit such as an application specific integrated circuit (ASIC) or a field programmable gate array (FPGA).

  As illustrated in FIG. 3, the control unit 130 includes an acquisition unit 131, a calculation unit 132, a determination unit 133, a determination unit 134, and a provision unit 135, and functions and functions of information processing described below. Realize or execute. Note that the internal configuration of the control unit 130 is not limited to the configuration illustrated in FIG. 3, and may be another configuration as long as the information processing described below is performed. Further, the connection relationship between the processing units included in the control unit 130 is not limited to the connection relationship illustrated in FIG. 3, and may be another connection relationship.

(Acquisition part 131)
The acquisition unit 131 acquires various types of information. The acquisition unit 131 acquires various information from an external information processing apparatus. The acquisition unit 131 acquires various information from the terminal device 10. The acquisition unit 131 acquires a content request from the terminal device 10. The acquisition unit 131 acquires various information from the providing source device 20. The acquisition unit 131 acquires information related to the provider from the provider device 20. The acquisition unit 131 acquires content related information related to the content from the providing source device 20. The acquisition unit 131 acquires various types of information from the storage unit 120. The acquisition unit 131 acquires various types of information from the provider information storage unit 121, the content information storage unit 122, the individual score information storage unit 123, the determination information storage unit 124, and the authenticity result information storage unit 125.

  The acquisition unit 131 acquires content related information related to the content. The acquisition unit 131 acquires content related information including information indicating content. The acquisition unit 131 acquires content related information including information indicating the creation date of the content. The acquisition unit 131 acquires content related information including presence / absence information of evidence corresponding to the content indicated by the content. The acquisition unit 131 acquires content related information including information indicating a content provider. The acquisition unit 131 acquires content related information including information indicating the reliability of the content provider.

  The acquisition unit 131 acquires content related information including related content information that is information of related content having a predetermined relationship with the content. The acquisition unit 131 acquires content related information including information indicating a provider of related content. The acquisition unit 131 acquires content related information including information indicating the reliability of the related content provider.

  In the example of FIG. 1, the acquiring unit 131 acquires the content CT11 of the providing source CP11 from the providing source device 20-1. The acquiring unit 131 acquires the content CT12 of the providing source CP12 from the providing source device 20-2. The acquisition unit 131 acquires the content CT13 of the provider CP13 from the provider device 20-3. The acquisition unit 131 acquires the content CT14 of the provider CP14 from the provider device 20-4.

(Calculation unit 132)
The calculation unit 132 calculates various information. The calculation unit 132 calculates various information based on the information stored in the storage unit 120. The calculation unit 132 calculates various information based on the information acquired by the acquisition unit 131. The calculation unit 132 calculates a score based on the information acquired by the acquisition unit 131. The calculation unit 132 calculates a score indicating the degree of possibility that the content is fake nice based on the content-related information.

  In the example of FIG. 1, the calculation unit 132 calculates the score (fake score) of each content. For example, the calculation unit 132 calculates the fake scores of the contents CT11 to CT14. Based on the information stored in the individual score information 123, the calculation unit 132 calculates the fake scores of the contents CT11 to CT14.

  For example, the calculation unit 132 calculates a score (fake score) using the above formula (1). The calculation unit 132 calculates a fake score for each content, as shown in the determination information storage unit 124 in FIG. The calculation unit 132 calculates the fake score of each content based on the above formula (1) and the content information of each content. The calculating unit 132 calculates the fake score of the content CT11 as “15”. The calculating unit 132 calculates the fake score of the content CT12 as “0.02”. The calculating unit 132 calculates the fake score of the content CT13 as “0.5”. Further, the calculation unit 132 calculates the fake score of the content CT14 as “1”.

  Further, the calculation unit 132 may generate (calculate) an individual score of the determination element. For example, the calculation unit 132 may derive (calculate) the individual score of each determination element using the content information stored in the authenticity result information storage unit 125 (see FIG. 8). In this case, the calculation part 132 may have a function as a production | generation part which produces | generates the information regarding an individual score. In addition to the calculation unit 132, the information processing apparatus 100 may include a generation unit (not illustrated) that generates information on individual scores such as the following model.

  For example, the calculation unit 132 may derive (calculate) each discrimination element as a feature (feature amount) and the weight of each discrimination element as an individual score. For example, the calculation unit 132 calculates the individual score by performing learning using the content information stored in the authenticity result information storage unit 125 as learning data (teacher data). For example, the calculation unit 132 generates a model by learning processing (model generation) using content information stored in the true / false result information storage unit 125, and thereby calculates the feature amount (determination element) in the model. The weight corresponding to each may be calculated as an individual score.

  For example, the calculation unit 132 may calculate the individual score regarding the determination element by learning the weight (individual score) of each feature (determination element) using the above formula (1).

  The calculation unit 132 may calculate the individual score information of each determination element by learning the weight (individual score) of each feature (determination element) using the content determined to be fake as a positive example. For example, the calculation unit 132 may calculate the individual score information of each determination element, using the content CT1 determined as fake news in the authenticity result information storage unit 125 in FIG. 8 as a positive example. For example, when the content information CDT1 of the content CT1 is input, the calculation unit 132 performs a learning process so that the score output by the model is a score that is equal to or higher than a predetermined threshold (for example, “10” or the like). . For example, when the content CT1 is a target, the calculation unit 132 performs a learning process so that the value (score) of “y” in the formula (1) is equal to or greater than a determination threshold (for example, “10” or the like). I do.

  In addition, for example, the calculation unit 132 may calculate the individual score information of each determination element using the content CT2 that is determined not to be fake news in the truth / false result information storage unit 125 in FIG. 8 as a negative example. . For example, when the content information CDT2 of the content CT2 is input, the calculation unit 132 performs a learning process so that the score output by the model is a score (for example, “0” or the like) smaller than a predetermined threshold. . For example, when the content CT2 is targeted, the calculation unit 132 sets the value (score) of “y” in the above formula (1) to a value (for example, “0”, etc.) that is smaller than the determination threshold. Next, a learning process is performed.

  Further, for example, the calculation unit 132 may calculate the individual score information of each determination element by using the content CT3 that is determined not to be fake news in the truth / false result information storage unit 125 in FIG. 8 as a negative example. . For example, when the content information CDT3 of the content CT3 is input, the calculation unit 132 performs a learning process so that the score output by the model is a score (for example, “0” or the like) smaller than a predetermined threshold. . For example, when the content CT3 is targeted, the calculation unit 132 sets the value (score) of “y” in the above formula (1) to a value (for example, “0” or the like) smaller than the determination threshold value. Next, a learning process is performed.

  For example, the calculation unit 132 may calculate an individual score for each category of content. That is, the calculation unit 132 may generate a model for each content category. In the above example, the calculation unit 132 may calculate the individual score for the category “politics” using the contents CT1 and CT2 to which the category “politics” belongs. Further, the calculation unit 132 may calculate an individual score for the category “Entertainment” using the content CT3 to which the category “Entertainment” belongs. In this case, the calculation unit 132 may calculate the fake score of the content using the individual score corresponding to the content category.

(Determination part 133)
The determination unit 133 determines various information. The determination unit 133 determines various information based on the information stored in the storage unit 120. The determination unit 133 determines various information based on the information acquired by the acquisition unit 131. The determination unit 133 determines various types of information based on the information calculated by the calculation unit 132. Based on the information acquired by the acquisition unit 131, the determination unit 133 determines whether or not the content corresponds to fake news.

  Based on the content-related information acquired by the acquisition unit 131, the determination unit 133 determines whether the content satisfies a condition related to fake nice. The determination unit 133 determines whether the content satisfies a condition based on a comparison between the content indicated by the content and the content indicated by the related content. The determination unit 133 determines whether the content satisfies a condition based on a comparison between the content indicated by the content and the content indicated by the related content. The determination unit 133 determines whether the content satisfies a condition based on the score calculated by the calculation unit 132. The determination unit 133 determines whether the content satisfies a condition based on a comparison between the score calculated by the calculation unit 132 and a predetermined threshold value.

  In the example of FIG. 1, the determination unit 133 determines whether a condition regarding fake nice is satisfied. For example, the determination unit 133 may determine that the one content is fake news if the one content satisfies the condition regarding the fake nice (the determination unit 133 determines that the fake possibility exists. When the content does not satisfy the condition regarding fake nice, it is determined that there is no possibility that the one content is fake news (no fake possibility).

  For example. If the fake score of the content is equal to or greater than a predetermined threshold (determination threshold), the determination unit 133 determines that the content has the possibility of fake. In the example of FIG. 1, if the fake score of the content is equal to or greater than the determination threshold “10”, the determination unit 133 determines that the content has the possibility of fake.

  For example, since the fake score “15” of the content CT11 is equal to or greater than the determination threshold “10”, the determination unit 133 determines that the content CT11 has the possibility of fake. Further, the determination unit 133 determines that the content CT12 has no possibility of fake because the fake score “0.02” of the content CT12 is less than the determination threshold “10”. Since the fake score “0.5” of the content CT13 is less than the determination threshold “10”, the determination unit 133 determines that the content CT13 has no possibility of fake. Further, the determination unit 133 determines that the content CT14 has no possibility of fake because the fake score “1” of the content CT14 is less than the determination threshold “10”. Thereby, the determination unit 133 determines that the content CT11 is likely to be fake, and determines that the contents CT12 to CT14 are not likely to fake.

(Determining unit 134)
The determination unit 134 determines various information. The determination unit 134 determines various information based on the information stored in the storage unit 120. The determination unit 134 determines various types of information based on the information acquired by the acquisition unit 131. The determination unit 134 determines various information based on the information calculated by the calculation unit 132. The determination unit 133 determines various information based on the information determined by the determination unit 133.

  In the example of FIG. 1, the determination unit 134 determines content to be provided to the user U1 in response to a content request from the terminal device 10. The determination unit 134 determines content to be provided to the user U1 using various information as appropriate, but the determination unit 134 determines the content CT11 to be content to be provided to the user U1. For example, the determination unit 134 may determine content to be provided to the user U1 based on the attribute information of the user U1. For example, when the user U1 is a user interested in politics, the determination unit 134 may determine content belonging to the category “politics” as content to be provided to the user U1. Further, the determination unit 134 may determine not to provide the content determined by the determination unit 133 as having the possibility of fake. In this case, the determination unit 134 may determine content other than the content CT11 determined by the determination unit 133 as having fake possibility as content to be provided to the user U1.

(Providing unit 135)
The providing unit 135 provides various types of information. The providing unit 135 transmits various information to the terminal device 10. The providing unit 135 distributes various information to the terminal device 10. For example, the providing unit 135 distributes fake opinion information to the terminal device 10.

  Based on the determination by the determination unit 133, the providing unit 135 is fake opinion information that is used to determine whether the content corresponds to fake nice, and is displayed together with the content on the terminal device 10 used by the user Is provided to the terminal device 10. The providing unit 135 provides fake opinion information including the score calculated by the calculating unit 132.

  In FIG. 1, the providing unit 135 adds information to the content CT11 determined as the content to be provided to the user U1. For example, the providing unit 135 adds fake opinion information including fake score “15” and fake possibility information to the information to be provided to the user U1. As shown in the providing content DC11, the providing unit 135 adds fake information as information to be provided to the user U1 together with the content information CDT11 (article A) of the content CT11.

  The providing unit 135 provides the terminal device 10 with the content CT11 and information indicating that there is a fake score “15” and the possibility of fake. The providing unit 135 transmits the content CT11, the fake score “15”, and the fake opinion information INF11 indicating the possibility of fake to the terminal device 10.

[3. Information processing flow)
Next, the procedure of information processing by the information processing system 1 according to the embodiment will be described with reference to FIG. FIG. 9 is a flowchart illustrating an example of information processing according to the embodiment. Specifically, FIG. 9 is a flowchart illustrating an example of information processing related to content determination.

  As illustrated in FIG. 9, the information processing apparatus 100 acquires content related information related to content (step S101). For example, the information processing apparatus 100 acquires content related information related to the content from the storage unit 120 (see FIG. 3).

  Further, the information processing apparatus 100 determines whether the content satisfies a condition regarding fake nice based on the content related information (step S102). For example, the information processing apparatus 100 determines whether or not the content satisfies a condition related to fake nice based on the fake score of the content calculated using the above formula (1). For example, if the fake score of the content is equal to or greater than the determination threshold, the information processing apparatus 100 determines that the content has the possibility of fake. In the example of FIG. 1, the information processing apparatus 100 determines that the content has the possibility of fake when the fake score of the content is equal to or greater than the determination threshold “10”.

  Next, the procedure of information processing by the information processing system 1 according to the embodiment will be described with reference to FIG. FIG. 10 is a flowchart illustrating an example of information processing according to the embodiment. Specifically, FIG. 10 is a flowchart illustrating an example of information processing related to content provision.

  As illustrated in FIG. 10, the information processing apparatus 100 acquires a content request from the terminal apparatus 10 (step S201). Thereafter, the information processing apparatus 100 determines whether the provided content has a possibility of fake (step S202). For example, the information processing apparatus 100 determines whether the content to be transmitted (distributed) to the terminal apparatus 10 has a fake possibility or not.

  When the provided content has a possibility of fake (step S202: Yes), the information processing apparatus 100 provides the fake opinion information together with the content (step S203). For example, when the content to be provided is likely to be fake, the information processing apparatus 100 displays the fake opinion information including the fake score of the content and information indicating that the content is likely to be fake together with the content. 10 to provide.

  On the other hand, if the provided content does not have the possibility of fake (step S202: No), the information processing apparatus 100 provides the content (step S204). For example, when the provided content is not likely to be fake, that is, when the provided content is not likely to fake, only the content is provided to the terminal device 10. In addition, even if the content to be provided has no possibility of fake, the information processing apparatus 100 displays the fake opinion information including information indicating that the content has no fake score and no fake possibility together with the content. It may be provided to the device 10.

[4. effect〕
As described above, the information processing apparatus 100 according to the embodiment includes the acquisition unit 131, the determination unit 133, and the provision unit 135. The acquisition unit 131 acquires content related information related to the content. Further, the determination unit 133 determines whether the content satisfies a condition regarding fake nice based on the content-related information acquired by the acquisition unit 131. Based on the determination by the determination unit 133, the providing unit 135 is fake opinion information that is used to determine whether the content corresponds to fake nice, and is displayed together with the content on the terminal device 10 used by the user Is provided to the terminal device 10.

  As described above, the information processing apparatus 100 according to the embodiment determines whether the content satisfies the condition regarding fake nice based on the content related information, and determines whether the content corresponds to fake nice based on the determination. By providing the terminal device 10 with the fake opinion information that is the material, it is possible to provide appropriate information to the user.

  In the information processing apparatus 100 according to the embodiment, the acquisition unit 131 acquires content-related information including information indicating content.

  As described above, since the information processing apparatus 100 according to the embodiment can determine the content related information including the information indicating the content by taking the information of the content itself into consideration, the information processing apparatus 100 provides appropriate information to the user. be able to.

  In the information processing apparatus 100 according to the embodiment, the acquisition unit 131 acquires content-related information including information indicating a content creation date.

  As described above, the information processing apparatus 100 according to the embodiment can determine the content related information including the information indicating the creation date of the content, so that the determination can be made in consideration of the information on the creation date of the content. Information can be provided.

  In the information processing apparatus 100 according to the embodiment, the acquisition unit 131 acquires content-related information including presence / absence information of evidence corresponding to the content indicated by the content.

  As described above, since the information processing apparatus 100 according to the embodiment can determine the presence or absence of content evidence by acquiring content related information including the presence or absence information of evidence corresponding to the content indicated by the content, Can provide appropriate information.

  In the information processing apparatus 100 according to the embodiment, the acquisition unit 131 acquires content-related information including information indicating a content provider.

  As described above, since the information processing apparatus 100 according to the embodiment can determine the content related information including the information indicating the content providing source in consideration of the content provision, the information processing apparatus 100 can provide appropriate information to the user. It can be carried out.

  In the information processing apparatus 100 according to the embodiment, the acquisition unit 131 acquires content-related information including information indicating the reliability of the content provider.

  As described above, the information processing apparatus 100 according to the embodiment can determine the content provision information by including the content related information including the information indicating the reliability of the content providing source. Can provide appropriate information.

  In the information processing apparatus 100 according to the embodiment, the acquisition unit 131 acquires content-related information including related content information that is related content information having a predetermined relationship with the content.

  As described above, the information processing apparatus 100 according to the embodiment can make a determination in consideration of related content by acquiring content related information including related content information that is related content information having a predetermined relationship with the content. It is possible to provide appropriate information to the user.

  In the information processing apparatus 100 according to the embodiment, the acquisition unit 131 acquires content-related information including information indicating a related content provider.

  As described above, since the information processing apparatus 100 according to the embodiment can determine the content related information including the information indicating the related content providing source, in consideration of the related content providing source, it is appropriate for the user. Information can be provided.

  In the information processing apparatus 100 according to the embodiment, the acquisition unit 131 acquires content-related information including information indicating the reliability of the related content provider.

  As described above, the information processing apparatus 100 according to the embodiment can determine by considering the reliability of the provider of the related content by acquiring the content related information including the information indicating the reliability of the provider of the related content. Therefore, it is possible to provide appropriate information to the user.

  In the information processing apparatus 100 according to the embodiment, the determination unit 133 determines whether the content satisfies the condition based on a comparison between the content indicated by the content and the content indicated by the related content.

  As described above, the information processing apparatus 100 according to the embodiment determines whether the content satisfies the condition based on the comparison between the content indicated by the content and the content indicated by the related content, thereby comparing the content details. Based on this, it is possible to provide appropriate information to the user.

  In the information processing apparatus 100 according to the embodiment, the determination unit 133 determines whether the content satisfies the condition based on a comparison between the content indicated by the content and the content indicated by the related content.

  As described above, the information processing apparatus 100 according to the embodiment provides appropriate information to the user by determining whether the content satisfies the condition based on the comparison between the content indicated by the content and the content indicated by the related content. It can be performed.

  In addition, the information processing apparatus 100 according to the embodiment includes a calculation unit 132. The calculation unit 132 calculates a score indicating the degree of possibility that the content is fake nice based on the content-related information. The determination unit 133 determines whether the content satisfies a condition based on the score calculated by the calculation unit 132.

  As described above, the information processing apparatus 100 according to the embodiment provides appropriate information to the user by determining whether the content satisfies the condition based on the comparison between the content indicated by the content and the content indicated by the related content. It can be performed.

  In the information processing apparatus 100 according to the embodiment, the determination unit 133 determines whether the content satisfies the condition based on a comparison between the score calculated by the calculation unit 132 and a predetermined threshold.

  As described above, the information processing apparatus 100 according to the embodiment determines whether or not the content satisfies the condition based on the comparison between the score calculated by the calculation unit 132 and the predetermined threshold value. Information can be provided.

  In the information processing apparatus 100 according to the embodiment, the providing unit 135 provides fake opinion information including the score calculated by the calculating unit 132.

  As described above, the information processing apparatus 100 according to the embodiment can provide appropriate information to the user by providing the fake opinion information including the score calculated by the calculation unit 132.

[5. Hardware configuration)
The information processing apparatus 100 according to the embodiment described above is realized by a computer 1000 configured as shown in FIG. 12, for example. FIG. 12 is a hardware configuration diagram illustrating an example of a computer that implements the functions of the information processing apparatus. The computer 1000 includes a CPU 1100, RAM 1200, ROM 1300, HDD 1400, communication interface (I / F) 1500, input / output interface (I / F) 1600, and media interface (I / F) 1700.

  The CPU 1100 operates based on a program stored in the ROM 1300 or the HDD 1400 and controls each unit. The ROM 1300 stores a boot program executed by the CPU 1100 when the computer 1000 is started up, a program depending on the hardware of the computer 1000, and the like.

  The HDD 1400 stores programs executed by the CPU 1100, data used by the programs, and the like. The communication interface 1500 receives data from other devices via the network N and sends the data to the CPU 1100, and transmits data determined by the CPU 1100 to other devices via the network N.

  The CPU 1100 controls an output device such as a display and a printer and an input device such as a keyboard and a mouse via the input / output interface 1600. The CPU 1100 acquires data from the input device via the input / output interface 1600. Further, the CPU 1100 outputs the determined data to the output device via the input / output interface 1600.

  The media interface 1700 reads a program or data stored in the recording medium 1800 and provides it to the CPU 1100 via the RAM 1200. The CPU 1100 loads such a program from the recording medium 1800 onto the RAM 1200 via the media interface 1700, and executes the loaded program. The recording medium 1800 is, for example, an optical recording medium such as a DVD (Digital Versatile Disc) or PD (Phase change rewritable disk), a magneto-optical recording medium such as an MO (Magneto-Optical disk), a tape medium, a magnetic recording medium, or a semiconductor memory. Etc.

  For example, when the computer 1000 functions as the information processing apparatus 100 according to the embodiment, the CPU 1100 of the computer 1000 implements the function of the control unit 130 by executing a program loaded on the RAM 1200. The CPU 1100 of the computer 1000 reads these programs from the recording medium 1800 and executes them. However, as another example, these programs may be acquired from other devices via the network N.

  As described above, some of the embodiments and modifications of the present application have been described in detail with reference to the drawings. It is possible to carry out the present invention in other forms that have been modified and improved.

[6. Others]
In addition, among the processes described in the above-described embodiments and modifications, all or a part of the processes described as being automatically performed can be manually performed, or are described as being performed manually. All or part of the processing can be automatically performed by a known method. In addition, the processing procedures, specific names, and information including various data and parameters shown in the document and drawings can be arbitrarily changed unless otherwise specified. For example, the various types of information illustrated in each drawing is not limited to the illustrated information.

  Further, each component of each illustrated apparatus is functionally conceptual, and does not necessarily need to be physically configured as illustrated. In other words, the specific form of distribution / integration of each device is not limited to that shown in the figure, and all or a part thereof may be functionally or physically distributed or arbitrarily distributed in arbitrary units according to various loads or usage conditions. Can be integrated and configured.

  In addition, the above-described embodiments and modifications can be combined as appropriate within a range that does not contradict processing contents.

  In addition, the “section (module, unit)” described above can be read as “means” or “circuit”. For example, the acquisition unit can be read as acquisition means or an acquisition circuit.

DESCRIPTION OF SYMBOLS 1 Information processing system 100 Information processing apparatus 121 Provider information storage unit 122 Content information storage unit 123 Individual score information storage unit 124 Judgment information storage unit 125 Truth / false result information storage unit 130 Control unit 131 Acquisition unit 132 Calculation unit 133 Determination unit 134 Determining unit 135 Providing unit 10 Terminal device N Network

Claims (15)

An acquisition unit for acquiring content-related information related to the content;
A determination unit that determines whether the content satisfies a condition regarding fake nice based on the content-related information acquired by the acquisition unit;
Based on the determination by the determination unit, the fake opinion information is used to determine whether the content corresponds to the fake nice, and the fake opinion information displayed together with the content on the terminal device used by the user, A providing unit provided to the terminal device;
An information processing apparatus comprising: The acquisition unit
The information processing apparatus according to claim 1, wherein the content related information including information indicating the content is acquired. The acquisition unit
The information processing apparatus according to claim 2, wherein the content related information including information indicating a creation date of the content is acquired. The acquisition unit
The information processing apparatus according to claim 2, wherein the content related information including presence / absence information of evidence corresponding to the content indicated by the content is acquired. The acquisition unit
The information processing apparatus according to claim 2, wherein the content related information including information indicating a provider of the content is acquired. The acquisition unit
The information processing apparatus according to claim 5, wherein the content related information including information indicating reliability of the content provider is acquired. The acquisition unit
The information processing apparatus according to any one of claims 1 to 6, wherein the content related information including related content information that is related content information having a predetermined relationship with the content is acquired. The acquisition unit
The information processing apparatus according to claim 7, wherein the content related information including information indicating a provider of the related content is acquired. The acquisition unit
The information processing apparatus according to claim 8, wherein the content related information including information indicating reliability of a provider of the related content is acquired. The determination unit
The information according to any one of claims 7 to 9, wherein whether or not the content satisfies the condition is determined based on a comparison between the content indicated by the content and the content indicated by the related content. Processing equipment. A calculation unit that calculates a score indicating a degree of possibility that the content is the fake nice based on the content-related information;
Further comprising
The determination unit
The information processing apparatus according to claim 1, wherein it is determined whether or not the content satisfies the condition based on the score calculated by the calculation unit. The determination unit
The information processing apparatus according to claim 11, wherein the content is determined to satisfy the condition based on a comparison between the score calculated by the calculation unit and a predetermined threshold. The providing unit includes:
The information processing apparatus according to claim 11, wherein the fake opinion information including the score calculated by the calculation unit is provided. An information processing method executed by a computer,
An acquisition step of acquiring content related information related to the content;
A determination step of determining whether the content satisfies a condition regarding fake nice based on the content related information acquired by the acquisition step;
Based on the determination by the determination step, the fake opinion information is used as a determination material as to whether the content corresponds to the fake nice, and the fake opinion information displayed together with the content on the terminal device used by the user, A providing process to be provided to the terminal device;
An information processing method comprising: An acquisition procedure for acquiring content-related information related to the content;
A determination procedure for determining whether the content satisfies a condition regarding fake nice based on the content-related information acquired by the acquisition procedure;
Based on the determination by the determination procedure, the fake opinion information is used as a determination material as to whether the content corresponds to the fake nice, and the fake opinion information displayed together with the content on the terminal device used by the user, A provision procedure to be provided to the terminal device;
An information processing program for causing a computer to execute.

Images