JP2022069177A - Information processing apparatus, information output method, and information output program - Google Patents

Abstract

To provide an information processing apparatus, information output method, and information output program for allowing a user to easily confirm various opinions posted on SNS.SOLUTION: An information processing apparatus 10 comprises: a collection unit 12a for identifying a topic related to a specified keyword and collecting posted data on SNS related to the topic; an extraction unit 12b for analyzing a text of the collected posted data and extracting words related to opinions on the topic contained in the text; and an output unit 12d for outputting the words related to the opinions.SELECTED DRAWING: Figure 1

Description

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

In recent years, SNS (Social Networking Service) such as Twitter (registered trademark) has become widespread. A lot of information is sent from each individual's account on SNS. SNS users spread information by retransmitting based on the browsed information, but the truth remains questionable. If erroneous information is widely disseminated and trusted by SNS users, it may lead to social problems.

For example, as a method of preventing the spread of hoaxes, alert information is transmitted on SNS and information is transmitted on a website, but such information is rarely viewed as compared with hoax information. Further, as a conventional technique, a database for collecting user's error indication expressions on SNS is operated. The information collected in this way is stored and made available for viewing as information suspected of being hoax.

Japanese Unexamined Patent Publication No. 2013-77044

However, in the conventional technique, there is a problem that it may be difficult for the user to easily confirm various opinions posted on the SNS. In SNS, for example, if erroneous information is widely spread and trusted by SNS users, it may lead to social problems. As a method of preventing the spread of hoaxes, alert information is sent on SNS and information is sent on websites, but such information is rarely viewed compared to hoax information.

In addition, in the conventional technique, information that is considered to be a hoax is collected based on the sentences pointed out by the user, but as a characteristic of SNS, there is a strong tendency for users who are close to themselves and have similar ideas to connect with each other, and the pointed out information is It is possible that it will not occur. When there are two conflicting opinions on a topic, it is highly likely that the users who claim the opinions are far from each other and cannot recognize each other's existence.

In order to solve the above-mentioned problems and achieve the object, the information processing apparatus of the present invention has a collection unit that identifies a topic related to a specified keyword and collects posted data on the SNS related to the topic, and the collection unit. It is characterized by having an extraction unit that analyzes the text of the posted data collected by the text and extracts words related to the opinion on the topic contained in the text, and an output unit that outputs the words related to the opinion extracted by the extraction unit. And.

Further, the information output method of the present invention is an information output method executed by an information processing apparatus, and is a collection step of specifying a topic related to a designated keyword and collecting posted data on the SNS related to the topic, and the collection. It includes an extraction step of analyzing the text of the posted data collected by the process and extracting words related to the opinion on the topic contained in the text, and an output step of outputting the words related to the opinion extracted by the extraction step. It is a feature.

In addition, the information output program of the present invention identifies a topic related to the specified keyword, analyzes a collection step for collecting posted data on the SNS related to the topic, and analyzes the text of the posted data collected by the collection step. It is characterized in that a computer is made to execute an extraction step of extracting a word related to an opinion on a topic included in the sentence and an output step of outputting a word related to an opinion extracted by the extraction step.

According to the present invention, there is an effect that the user can easily confirm various opinions posted on the SNS.

FIG. 1 is a block diagram showing a configuration example of the information processing apparatus according to the first embodiment. FIG. 2 is a diagram illustrating an outline of processing of the information processing apparatus. FIG. 3 is a diagram showing a display example displayed on the user terminal. FIG. 4 is a flowchart showing an example of a processing flow in the information processing apparatus according to the first embodiment. FIG. 5 is a diagram showing a computer that executes a program.

Hereinafter, the information processing apparatus, the information output method, and the embodiment of the information output program according to the present application will be described in detail with reference to the drawings. Note that this embodiment does not limit the information processing apparatus, information output method, and information output program according to the present application.

[First Embodiment]
In the following embodiments, the configuration of the information processing apparatus according to the first embodiment and the flow of processing in the information processing apparatus will be described in order, and finally, the effects of the first embodiment will be described.

[Information processing device configuration]
First, the configuration of the information processing apparatus 10 will be described with reference to FIG. FIG. 1 is a block diagram showing a configuration example of the information processing apparatus according to the first embodiment. As shown in FIG. 1, the information processing apparatus 10 is connected to the user terminal 20 via a network 30. The information processing device 10 is a device such as a server that outputs a word related to an opinion on a topic of SNS to a user who owns a smartphone.

Further, the user terminal 20 is, for example, a terminal device such as a smartphone, a tablet terminal, a mobile phone, or a notebook PC. It is assumed that a dedicated application for outputting a word related to an opinion on a topic of SNS is downloaded to the user terminal 20, for example. The user terminal 20 may have a part or all of each functional unit of the information processing apparatus 10 described below, or the user terminal 20 may execute a part or all of the processing of the information processing apparatus 10. good.

As shown in FIG. 1, the information processing apparatus 10 includes a communication processing unit 11, a control unit 12, and a storage unit 13. The processing of each part of the information processing apparatus 10 will be described below.

The communication processing unit 11 controls communication related to various types of information. For example, the communication processing unit 11 receives the information of the keyword specified by the user from the user terminal 20. Further, the communication processing unit 11 transmits, for example, word data relating to an opinion on the topic of the SNS to the user terminal 20.

Further, the storage unit 13 stores data and programs necessary for various processes by the control unit 12, and has a posted data storage unit 13a as particularly related to the present embodiment. For example, the storage unit 13 is a semiconductor memory element such as a RAM or a flash memory, or a storage device such as a hard disk or an optical disk.

The posted data storage unit 13a stores the posted data collected by the collection unit 12a, which will be described later. For example, the posted data storage unit 13a stores the data of the text posted on the SNS in association with the subject related to the keyword designated by the user.

The control unit 12 has an internal memory for storing a program that defines various processing procedures and required data, and executes various processing by these. For example, the control unit 12 has a collection unit 12a, an extraction unit 12b, a calculation unit 12c, and an output unit 12d. Here, the control unit 12 is, for example, an electronic circuit such as a CPU or MPU, or an integrated circuit such as an ASIC or FPGA.

The collecting unit 12a identifies a topic related to the designated keyword and collects posted data on the SNS related to the topic. For example, the collecting unit 12a first receives a word (for example, "unidentified flying object") included in the text of the posted data on the SNS as a designated keyword that the user is interested in from the user terminal 20. Then, the collecting unit 12a collects the posted data of the text including the received keyword.

Further, for example, the collecting unit 12a specifies information on the date and time or place of the topic as a topic related to the designated keyword, and is post data including the keyword and is posted data related to the date and time or place of the topic. May be collected as posted data on the SNS regarding the topic.

That is, for example, the collecting unit 12a uses the place (place name) included in the text of the posted data for which the user has specified the keyword and the posting date and time of the posted data to determine when, where, and what the topic is related to the keyword. To identify. To give a specific example, the collection unit 12a specifies, for example, "the topic of XX days, Sendai, and unidentified flying objects" as the date, place, and content of the topic. Then, the collecting unit 12a, for example, is the posted data of the text including the keyword, and the posted data within one week before and after the specified date and time, or the posted data including the place name of the specified place in the text is stored in the external server ( Collected from (not shown) and stored in the posted data storage unit 13a.

The extraction unit 12b analyzes the text of the posted data collected by the collection unit 12a, and extracts words related to the opinion on the topic contained in the text. For example, the extraction unit 12b extracts a word co-occurring with a topical keyword from the text of the posted data stored in the posted data storage unit 13a. Then, the extraction unit 12b performs a dependency analysis of the text of the posted data, and among the words co-occurring with the keyword, the word related to the keyword (for example, "flying object") (for example, "genuine"). , "Lie", "Airplane", "Meteorite", etc.) are extracted as words related to opinions. The process of extracting words related to opinions is not limited to this. For example, dictionary data in which words related to opinions are set in advance is stored in the storage unit 13, and the extraction unit 12b stores the posted data. Among the included words, the words included in the words in the dictionary data may be extracted as the words related to the opinion.

The calculation unit 12c uses the words extracted by the extraction unit 12b to calculate a score indicating the degree of credibility for the topic. For example, the calculation unit 12c calculates a word vector for each word extracted by the extraction unit 12b using word-2-vec, and calculates a polarity score based on the word vector. Here, any method may be used for calculating the polarity score. For example, the calculation unit 12c is a predetermined method in the range of 1 to -1, and the higher the value, the more positive the value. The lower the value, the more the polarity score indicates that the word has a negative opinion. Then, the calculation unit 12c calculates the average of the polarity scores by dividing the polarity score calculated for each word by the number of words, and the average of the calculated polarity scores is a score indicating the degree of credibility for the topic. May be.

Further, the calculation unit 12c weights the posted data including the words extracted by the extraction unit 12b according to the attribute information of the posting source, and calculates a score indicating the degree of credibility of the topic. For example, if the posting source is a preset credible company (newspaper, etc.) or individual (scholar, etc.), the calculation unit 12c weights the score so that it is high, and the credibility of the topic. Calculate a score that indicates the degree of.

The output unit 12e outputs a word related to the opinion extracted by the extraction unit 12b. For example, the output unit 12e outputs and displays a predetermined number of words having a higher appearance number among the words related to the opinions extracted by the extraction unit 12b to the user terminal 20.

For example, the output unit 12e outputs a predetermined number of words having a higher number of appearances among the extracted words. To give a specific example, the output unit 12e outputs words such as "genuine", "lie", "airplane", and "meteorite" as words having the highest number of appearances. The output unit 12e may output in any format, for example, a higher-level word may be output in the word cloud.

Further, the output unit 12e may further output information indicating the credibility of the topic by using the score calculated by the calculation unit 12d. For example, the output unit 12e may output the ratio (%) of the opinions of the true and the lie as the information showing the credibility of the topic. Further, for example, the output unit 12e classifies the posted data including words having a polarity score of a predetermined value or more as a positive opinion with respect to the topic (an opinion that the topic is considered to be true), and the polarity score is equal to or less than the predetermined value. Post data including words is classified as negative opinions on the topic (opinions that are considered to be false on the topic), the number of posts of positive and negative opinions is totaled, and the ratio is the credibility of the topic. May be output and displayed on the user terminal 20 as information indicating the above. If opinions are diverged in more than three directions (“positive”, “negative”, “neutral”, etc.), the output unit 12e divides the words into genres based on the word genre classification information. Post data may be classified. For example, the output unit 12e may output and display a score indicating the degree of credibility of the topic calculated by the calculation unit 12c on the user terminal 20.

Further, in order to display the opinion of the conflict, the output unit 12e sets a word having a polarity score of a predetermined value or more and a word having a polarity score of a predetermined value or less and outputs the word to the user terminal 20 for display. May be good. Further, the output unit 12e has the post data including words having a polarity score of a predetermined value or more and the polarity score among the post data stored in the post data storage unit 13a in order to display the post data having disagreements. Post data containing words of a predetermined value or less may be combined and output to the user terminal 20 for display.

Here, the outline of the processing of the information processing apparatus 10 will be described with reference to FIG. FIG. 2 is a diagram illustrating an outline of processing of the information processing apparatus. In the example of FIG. 2, the information processing apparatus 10 acquires a designated keyword of interest to the user from the user terminal 20 (see (1) of FIG. 2).

Then, the information processing apparatus 10 collects posted data of the same topic (see (2) in FIG. 2). For example, the information processing apparatus 10 collects post data including keywords and is related to the date and time and place of the topic as post data on the SNS related to the topic, and stores the post data in the post data storage unit 13a. ..

Subsequently, the information processing apparatus 10 analyzes the text of the posted data and extracts words related to the opinion on the topic included in the text (see (3) in FIG. 2). For example, the extraction unit 12b extracts a word co-occurring with a topical keyword from the text of the posted data stored in the posted data storage unit 13a.

After that, the information processing apparatus 10 outputs the word related to the opinion to the topic to the user terminal 20 based on the word related to the opinion (see (4) in FIG. 2). For example, the information processing apparatus 10 outputs words such as "genuine", "lie", "airplane", and "meteorite" to the user terminal 20 as words having the highest number of appearances.

Here, a display example displayed on the user terminal 20 will be described with reference to FIG. FIG. 3 is a diagram showing a display example displayed on the user terminal. As illustrated in FIG. 3, the user terminal 20 displays posted data including the designated keyword "unidentified flying object" that the user is interested in, and also displays words related to opinions on the topic. In the example of FIG. 3, the user terminal 20 displays "really", "lie", "airplane", and "meteorite" as words related to opinions.

Further, the user terminal 20 may display post data including the tapped or clicked word when any of the displayed words related to the opinion is tapped or clicked. For example, when the character "really" is tapped or clicked by the user operation, the information processing apparatus 10 causes the user terminal 20 to display the posted data including the word "really". In this way, the information processing apparatus 10 makes it possible to confirm the posted data of various opinions, so that it is possible to prevent the assumption by one-sided opinions.

[Processing procedure of information processing device]
Next, an example of the processing procedure in the information processing apparatus 10 according to the first embodiment will be described with reference to FIG. FIG. 4 is a flowchart showing an example of a processing flow in the information processing apparatus according to the first embodiment.

As illustrated in FIG. 4, when the collecting unit 12a of the information processing apparatus 10 receives the designation of the keyword by the user of the user terminal 20 (step S101), the collection unit 12a identifies the topic related to the designated keyword, and on the SNS related to the topic. Post data is collected (step S102). For example, the collecting unit 12a specifies information on the date and time and place of the topic as a topic related to the specified keyword, and posts data including the keyword and is related to the date and time and place of the topic. Collect as posted data on SNS related to the topic.

Then, the extraction unit 12b analyzes the text of the posted data collected by the collection unit 12a, and extracts words related to the opinion on the topic included in the text (step S103). For example, the extraction unit 12b extracts a word related to the keyword from the text of the posted data stored in the posted data storage unit 13a as a word related to the opinion from the words co-occurring with the keyword of the topic by the dependency analysis. do.

Then, the calculation unit 12c calculates a score indicating the degree of credibility for the topic using the words extracted by the extraction unit 12b (step S104). For example, the calculation unit 12c calculates a word vector for each word extracted by the extraction unit 12b using word-2-vec, and calculates a polarity score based on the word vector.

The output unit 12d outputs the word related to the opinion on the topic to the user terminal 20 based on the word related to the opinion extracted by the extraction unit 12b (step S105). For example, the output unit 12d outputs words such as "genuine", "lie", "airplane", and "meteorite" to the user terminal 20 as words having the highest number of appearances. Further, the output unit 12d may further output a score indicating the degree of credibility to the topic calculated by the calculation unit 12c to the user terminal 20, and as information indicating the credibility to the topic, for example. , The ratio of the opinions of true and false may be output to the user terminal 20.

[Effect of the first embodiment]
The information processing apparatus 10 according to the first embodiment identifies a topic related to a designated keyword, collects posted data on the SNS related to the topic, analyzes the text of the collected posted data, and includes the text. Extract words related to opinions on topics. Then, the information processing apparatus 10 outputs information indicating the credibility of the topic based on the extracted words. Therefore, in the information processing apparatus 10, the user can easily confirm various opinions posted on the SNS.

Further, since the information processing apparatus 10 automatically collects the posted data of the same topic, the truth or falsehood of the generally unknown things or the information whose correct answer is ambiguous is not dependent on the user's knowledge or relationship. Collection is possible. Further, in the information processing apparatus 10, for example, the posted data classified as a positive opinion (opinion that is considered to be true to the topic) and the posted data that is classified as a negative opinion (opinion that is considered to be false to the topic). Since the words related to the opinions are displayed on the user terminal 20 at the same time, it is possible to prevent the assumption by one-sided opinions by confirming the conflicting opinions at the same time.

(System configuration, etc.)
Further, each component of each of the illustrated devices is a functional concept, and does not necessarily have to be physically configured as shown in the figure. That is, the specific form of distribution / integration of each device is not limited to the one shown in the figure, and all or part of them may be functionally or physically distributed / physically in any unit according to various loads and usage conditions. Can be integrated and configured. Further, each processing function performed by each device may be realized by a CPU and a program analyzed and executed by the CPU, or may be realized as hardware by wired logic.

Further, among the processes described in the present embodiment, all or part of the processes described as being automatically performed can be manually performed, or the processes described as being manually performed can be performed. All or part of it can be done automatically by a known method. In addition, the processing procedure, control procedure, specific name, and information including various data and parameters shown in the above document and drawings can be arbitrarily changed unless otherwise specified.

(program)
It is also possible to create a program in which the processing executed by the information processing apparatus 10 described in the above embodiment is described in a language that can be executed by a computer. For example, it is possible to create a program in which the processing executed by the information processing apparatus 10 according to the embodiment is described in a language that can be executed by a computer. In this case, the same effect as that of the above embodiment can be obtained by executing the program by the computer. Further, the same processing as that of the above embodiment may be realized by recording the program on a computer-readable recording medium, reading the program recorded on the recording medium into the computer, and executing the program.

FIG. 5 is a diagram showing a computer that executes a program. As illustrated in FIG. 5, the computer 1000 includes, for example, a memory 1010, a CPU (Central Processing Unit) 1020, a hard disk drive interface 1030, a disk drive interface 1040, a serial port interface 1050, a video adapter 1060, and the like. It has a network interface 1070 and each of these parts is connected by a bus 1080.

The memory 1010 includes a ROM (Read Only Memory) 1011 and a RAM 1012, as illustrated in FIG. The ROM 1011 stores, for example, a boot program such as a BIOS (Basic Input Output System). The hard disk drive interface 1030 is connected to the hard disk drive 1090, as illustrated in FIG. The disk drive interface 1040 is connected to the disk drive 1100 as illustrated in FIG. For example, a removable storage medium such as a magnetic disk or an optical disk is inserted into the disk drive 1100. The serial port interface 1050 is connected to, for example, a mouse 1110 and a keyboard 1120, as illustrated in FIG. The video adapter 1060 is connected, for example, to a display 1130, as illustrated in FIG.

Here, as illustrated in FIG. 5, the hard disk drive 1090 stores, for example, the OS 1091, the application program 1092, the program module 1093, and the program data 1094. That is, the above program is stored in, for example, the hard disk drive 1090 as a program module in which a command executed by the computer 1000 is described.

Further, the various data described in the above embodiment are stored as program data in, for example, a memory 1010 or a hard disk drive 1090. Then, the CPU 1020 reads the program module 1093 and the program data 1094 stored in the memory 1010 and the hard disk drive 1090 into the RAM 1012 as needed, and executes various processing procedures.

The program module 1093 and program data 1094 related to the program are not limited to those stored in the hard disk drive 1090, and may be stored in, for example, a removable storage medium and read by the CPU 1020 via a disk drive or the like. .. Alternatively, the program module 1093 and the program data 1094 related to the program are stored in another computer connected via a network (LAN (Local Area Network), WAN (Wide Area Network), etc.), and are stored via the network interface 1070. It may be read by the CPU 1020.

The above-described embodiments and modifications thereof are included in the invention described in the claims and the equivalent scope thereof, as included in the technique disclosed in the present application.

10 Information processing device 11 Communication processing unit 12 Control unit 12a Collection unit 12b Extraction unit 12c Calculation unit 12d Output unit 13 Storage unit 13a Post data storage unit 20 User terminal 30 Network

Claims (6)

A collection unit that identifies topics related to the specified keyword and collects posted data on SNS related to the topics.
An extraction unit that analyzes the text of the posted data collected by the collection unit and extracts words related to opinions on the topic contained in the text, and an extraction unit.
An information processing apparatus including an output unit that outputs a word related to an opinion extracted by the extraction unit. The collecting unit identifies information on the date and time or place of the topic as a topic related to the designated keyword, and posts data including the keyword and related to the date and time or place of the topic. The information processing apparatus according to claim 1, wherein the information processing device is collected as posted data on an SNS relating to the topic. It further has a calculation unit that calculates a score indicating the degree of credibility for the topic using the words extracted by the extraction unit.
The information processing apparatus according to claim 1, wherein the output unit further outputs information indicating credibility to the topic by using the score calculated by the calculation unit. The claim is characterized in that the calculation unit weights the posted data including the words extracted by the extraction unit according to the attribute information of the posting source, and calculates a score indicating the degree of credibility of the topic. Item 3. The information processing apparatus according to item 3. It is an information output method executed by an information processing device.
A collection process that identifies a topic related to the specified keyword and collects posted data on the SNS related to the topic, and
An extraction process that analyzes the text of the posted data collected by the collection process and extracts words related to opinions on the topic contained in the text.
An information output method including an output step of outputting a word related to an opinion extracted by the extraction step. A collection step that identifies a topic related to a specified keyword and collects posted data on the SNS related to that topic.
An extraction step that analyzes the text of the posted data collected by the collection step and extracts words related to opinions on the topic contained in the text, and an extraction step.
An information output program characterized by having a computer execute an output step that outputs a word related to an opinion extracted by the extraction step.

Images