KR102228585B1 - An automatic sentiment information labeling method to news articles for providing sentiment information - Google Patents

Abstract

A method of operating a news article labeling apparatus according to an embodiment of the present invention includes: acquiring document data of a news article; Extracting paragraph information from the document data; Comparing the paragraphs obtained from the document data with the learning-based dictionary unit built in advance based on learning according to the paragraph information, and determining a corporate emotion information label corresponding to the company-related paragraph; And tagging the corporate sentiment information label on the one or more paragraphs, and processing it into article information tagged with the sentiment label.

Description

How to label emotional information of news articles to provide emotional information {AN AUTOMATIC SENTIMENT INFORMATION LABELING METHOD TO NEWS ARTICLES FOR PROVIDING SENTIMENT INFORMATION}

The present invention relates to a labeling method. More specifically, the present invention relates to a method for labeling emotional information of a news article for providing information.

Online news information is provided through various newspapers, media magazines, broadcasting stations, and a search portal that collects and provides information from them.Usually, one-sided information is supplied according to the presentation format of articles supplied by the news information provider. Most of them are subscribed to.

However, in recent years, by collecting such news information and building big data, labeling and analyzing, there has been an attempt to develop various applications and provide services to grasp the awareness or propensity of a specific person or company, etc., or to identify recent trends. This is being done, and this is being accelerated by the introduction of artificial intelligence technology based on the 4th industrial revolution.

In particular, with the recent increase in the use of social media such as Twitter, Facebook, and blogs, an attempt to check emotion information through analysis of various opinion information, such as satisfaction with products and satisfaction with movies, automatically through big data. Are being actively carried out.

In particular, companies can refer to marketing strategies by grasping how their products or services are being evaluated on social media, and policy agencies can determine policy revision directions and promotion methods through public opinion analysis on policies. As such a need arises, brand monitoring services specializing in sentiment analysis through data mining are also becoming active.

However, the method of analyzing news information based on artificial intelligence technology to date mainly uses semi-supervised learning, and a small number of experts on news information directly read articles and assign labels to create a small set of reference data. It is a method of processing emotional labeling for all news information by utilizing this, and in the end, excessive time and cost are consumed in the process of handling all news articles directly by an expert person.

In addition, the performance and efficiency of this classmate learning method is still low, so only high-cost and low-efficiency services can be provided, and commercialization and popularization are practically difficult.

The present invention was conceived to solve the above problems, constructing dictionary data based on paragraph-based sentence structure and terminological analysis of documents, and processing automated emotional label tagging corresponding to a large amount of online news articles, which are unstructured texts. Thus, by processing and providing information on articles tagged with emotional labels corresponding to analysis targets that require sentiment prediction analysis, such as companies and companies, it is possible to perform more accurate news information-based sentiment analysis while minimizing the time and cost of manpower input. It is an object of the present invention to provide a method and apparatus for labeling emotional information of a news article that makes it possible to do so.

A method according to an embodiment of the present invention for solving the above-described problems, in the operating method of a news article labeling apparatus, comprising: acquiring document data of a news article; Extracting paragraph information from the document data; Comparing the paragraphs obtained from the document data according to the paragraph information with a pre-built dictionary unit, and determining an analysis target emotion information label corresponding to a related paragraph to be analyzed; And tagging the analysis target emotion information label on the one or more paragraphs, and processing it into article information tagged with the emotion label.

An apparatus according to an embodiment of the present invention for solving the above-described problems includes: an input unit for obtaining document data of a news article in a news article labeling apparatus; A paragraph information extracting unit for extracting paragraph information from the document data; A label determination unit that compares the paragraphs obtained from the document data according to the paragraph information with a pre-built dictionary unit, and determines an analysis target emotion information label corresponding to a related paragraph to be analyzed; And an article information processing unit for tagging the analysis target emotional information label on the one or more paragraphs and processing the article information tagged with the emotional label.

Meanwhile, the method according to an embodiment of the present invention for solving the above-described problems may be implemented with a program for executing the method on a computer and a recording medium in which the program is recorded.

According to an embodiment of the present invention, dictionary data based on sentence structure and terminology analysis based on paragraphs of a document are constructed, and automated emotional label tagging corresponding to a large amount of online news articles as unstructured texts is processed. Similarly, by processing and providing information on articles tagged with emotional labels corresponding to analysis targets that require sentiment prediction analysis, the sentiment of news articles enables more accurate news information-based sentiment analysis while minimizing the time and cost of manpower input. A method and apparatus for labeling information can be provided.

In particular, embodiments of the present invention can be used for various purposes of analyzing sentiment information using large-scale news data of a big data scale. It can also be applied to forecasting, industry-specific analysis or other forecasting service development.

In addition, according to an embodiment of the present invention, it can be applied not only to long news articles or reports, but also to various newsletters composed of relatively short texts, online comments, and SNS data. In particular, various services such as statistical analysis for performing opinion mining using various text-based documents or data preparation process for machine learning in fields such as products for export of Hallyu and celebrity marketing in a situation where interest in the Korean Wave is hot recently. As it can be used in the provision process, its application has a wide range of advantages.

1 is a conceptual diagram schematically showing an entire system according to an embodiment of the present invention.
2 is a more detailed block diagram of a labeling device according to an embodiment of the present invention.
3 is a flowchart illustrating a labeling method according to an embodiment of the present invention in more detail.
4 is a diagram illustrating a labeling process according to an embodiment of the present invention.
5 is an exemplary diagram of log information extracted according to an embodiment of the present invention.
6 is a diagram illustrating a document verification and filtering process according to an embodiment of the present invention.

The following content merely exemplifies the principles of the present invention. Therefore, those skilled in the art can implement the principles of the present invention and invent various devices included in the concept and scope of the present invention, although not clearly described or illustrated herein. In addition, it is understood that all conditional terms and examples listed in this specification are, in principle, expressly intended only for the purpose of making the concept of the present invention understood, and are not limited to the embodiments and states specifically listed as such. It should be.

In addition, it is to be understood that all detailed descriptions listing specific embodiments as well as principles, aspects and embodiments of the present invention are intended to include structural and functional equivalents of these matters. It should also be understood that these equivalents include not only currently known equivalents, but also equivalents to be developed in the future, that is, all devices invented to perform the same function regardless of the structure.

Thus, for example, the block diagrams herein are to be understood as representing a conceptual perspective of exemplary circuits embodying the principles of the invention. Similarly, all flowcharts, state transition diagrams, pseudocodes, etc. are understood to represent the various processes performed by a computer or processor, whether or not the computer or processor is clearly depicted and that can be represented substantially in a computer-readable medium. It should be.

In addition, the explicit use of terms presented as processor, control, or similar concepts should not be interpreted exclusively by quoting hardware capable of executing software, and without limitation, digital signal processor (DSP) hardware, ROM for storing software. It should be understood to implicitly include (ROM), RAM (RAM) and non-volatile memory. Other commonly used hardware may also be included.

The above-described objects, features, and advantages will become more apparent through the following detailed description in connection with the accompanying drawings, whereby those of ordinary skill in the technical field to which the present invention pertains can easily implement the technical idea of the present invention. There will be. In addition, in describing the present invention, when it is determined that a detailed description of a known technology related to the present invention may unnecessarily obscure the subject matter of the present invention, a detailed description thereof will be omitted.

Hereinafter, a preferred embodiment according to the present invention will be described in detail with reference to the accompanying drawings.

1 is a diagram schematically showing an entire system according to an embodiment of the present invention.

Referring to FIG. 1, a system according to an embodiment of the present invention may include an emotion information labeling device 100, an analysis target information service providing device 200, and a user terminal 300, and the emotion information labeling device ( 100) may be connected to the news article database 400.

More specifically, the emotional information labeling apparatus 100 obtains news document data from the news article database 400, extracts paragraph information from the obtained document data, and is obtained from the document data according to the paragraph information. Articles in which the emotional label is tagged by comparing the paragraphs with the pre-built learning-based dictionary unit, determining the emotional information label to be analyzed corresponding to the relevant paragraph to be analyzed, and tagging the emotional information label to be analyzed to the one or more paragraphs Process it into information.

Accordingly, the processed article information may be provided to the analysis target information service providing device 200, and the analysis target information service providing device 200 is sentiment information based on news data on the analysis target through the analysis target emotion information label. It is possible to collect and process evaluation information corresponding thereto and a service provided to the user terminal 300.

In particular, the analysis target may be a company or a company, and the analysis target information service providing device 200 uses the article information tagged with the emotional label, the possibility of insolvency, credit, stock market prediction or growth potential of the company or company. At least one process of prediction may be performed, and a result of the execution may be provided to the user terminal 300.

Meanwhile, the emotional information labeling device 100, the service providing device 200, and the user terminal 300 may be connected by wire or wirelessly through a network. The providing device 200 and the user terminal 300 are provided through an Internet network, LAN, WAN, PSTN (Public Switched Telephone Network), PSDN (Public Switched Data Network), cable TV network, WIFI, mobile communication network, and other wireless communication networks. You can send and receive data. In addition, each of the emotional information labeling apparatus 100, the service providing apparatus 200, and the user terminal 300 may include respective communication modules for communicating with a protocol corresponding to each communication network.

In addition, the user terminal 100 described in the present specification includes a mobile phone, a smart phone, a laptop computer, a terminal for digital broadcasting, a personal digital assistant (PDA), a portable multimedia player (PMP), and a navigation system. Although it may be included, the present invention is not limited thereto, and may be various devices capable of user input and information display.

In such a system, the user terminal 300 may be connected to the service providing device 200 that receives article information from the emotional information labeling device 100 and receive the above-described news data-based analysis target information providing service.

2 is a block diagram illustrating a document learning apparatus according to an embodiment of the present invention in more detail.

Referring to FIG. 2, the emotional information labeling apparatus 100 according to an embodiment of the present invention includes an input unit 110, a paragraph information extraction unit 120, a label determination unit 130, a dictionary unit 140, and a log generation unit. It includes a unit 160, a verification unit 170, and an article information processing unit 180.

First, the input unit 110 receives a news document for processing article information from the news article database 400 and transmits it to the paragraph information extraction unit 120.

The input unit 110 may include one or more input interfaces for receiving the above-described news article data from the news article database 400. For example, the news document may be determined according to a news service, may be a comprehensive article document of each portal site, an article document of a news provider, and further include an article evaluation comment or an article-related novel media (SNS) document. .

In addition, the input unit 110 may receive information to be analyzed. The information to be analyzed may include, for example, a company name, a company name, a person name, and the like.For example, article information to which an emotional information label corresponding to a specific company is assigned is analysis target information that provides prediction information of the company. It may be provided to the service providing device 200.

The paragraph information extracting unit 120 may extract paragraph information for dividing the news document into one or more paragraph data that can be assigned a label.

In particular, in the case of online news articles, especially economic-related articles, there are not many articles that are filled with only one company in one article, and in many cases, they are filled with information about two or more companies. In this case, it is difficult to automatically classify the positive or negative evaluation of a specific company, and the positive or negative evaluation corresponding to the entire document and the positive or negative evaluation for each individual company are often inconsistent. Evaluation can be difficult.

Therefore, the paragraph information extraction unit 120 according to an embodiment of the present invention extracts only the paragraph containing a specific analysis object (company, etc.), rather than using the entire original text of the news article as it is, and processes it as article information tagged with a relevant emotional label. Output is possible, a process of extracting paragraph information for this is performed, and the extracted paragraph information may be transmitted to the label determination unit 130.

In addition, the label determining unit 130 indexes each paragraph of the document by referring to the paragraph information and the keyword and sentiment data set of the dictionary unit 140, and scores according to a specific keyword or sentiment word of the analysis target information for each paragraph. According to the matching comparison operation, the emotion information label to be tagged may be primarily determined, and the determined emotion information label and paragraph information may be transmitted to the verification unit 170.

Here, the dictionary unit 140, which is used for extracting paragraph information by the paragraph information extracting unit 120 and comparing score matching by the label determining unit 130, is based on a keyword or sentiment word frequency of a paragraph related to the analysis object. It may include a keyword set and a sentiment word set that enable the determination of the sentiment label score of the analysis target.

More specifically, the dictionary unit 140 according to an embodiment of the present invention may be pre-built and provided in the emotional information labeling apparatus 100. The dictionary unit 140 includes a plurality of language data sets built on a learning basis to determine an analysis target emotional information label of a paragraph obtained from the document data, and the language data set is an analysis target from the paragraph. Includes a keyword set capable of identifying a noun-type term having a positive or negative meaning corresponding to the economy or credit of, or the language data set is a verb having a positive or negative meaning corresponding to the reputation of the analysis object from the paragraph or It may include a set of sentiment words that can identify adjective-type terms.

Here, the positive keyword set and the negative keyword set enable positive and negative identification of individual news articles, and may include document feature words (or feature words) used for machine learning based on this.

For example, the positive keyword set and the negative keyword set may include keywords having a positive or negative meaning related to economic information or credit information of an analysis target company expressed in a news article, and may generally be a noun-type word. , It can be used as a marker in evaluating whether a news article is positive or negative.

The dictionary unit 140 receives predetermined keywords in advance, collects keywords from expert documents or various technical documents in a related field, or searches related words in order to construct keywords constituting the positive keyword set and the negative keyword set. (For example, Word2vec) creates a keyword list of related words related to existing keywords, or registers only the keywords determined by filtering among the derived keywords, and performs a process of registering positive keyword sets and negative keywords. You can create and store keyword sets.

On the other hand, the dictionary unit 140 may include a set of positive and negative emotional words, and the emotional word set is, for example, a verb form such as'increase' or'decrease' in a news article, or'good' or'bad'. It may have an adjective form such as, and may include one or more sentiment words representing the sentiment of the analysis target through combination with keywords.

The sentiment word can be used as a value variable to determine the emotional affirmation or negativity of a news article, and a document feature (or feature word, features) for machine learning in the information service providing device 200 to be analyzed, such as a keyword set. ) Can also be used.

Accordingly, the dictionary unit 140 constructs a set of sentiment words only with terms that are not limited to a specific domain area, but collects sentiment words from expert documents or various technical documents in a related field, or a related word search method (for example, Word2vec) generates a list of related sentiment words related to the previously collected sentiment words, or registers only sentiment words determined by filtering among the derived list of sentiment words, positive sentiment set and negative. You can create and store a set of sentiment words.

Accordingly, for terms registered in the dictionary unit 140, the label determination unit 130 may give different scores according to the type of the term (positive, negative, keyword, sentiment word), and the total is It can be used when determining the final positive or negative emotional label.

The label determination unit 130 identifies a paragraph related to the actual analysis object from the news document using the dictionary unit 140 generated as described above and the paragraph information of the paragraph information extraction unit 120, and responds to the identified paragraph. You can decide which emotional label you want. Here, the emotional label may be an automated label classified as positive or negative. In addition, news documents are news of various fields produced by various media outlets, and there may be no significant differences in terms of publication format, although there is a difference in description method for each medium.

More specifically, when a single news article is input, the label determination unit 130 may perform indexing for each paragraph based on the paragraph information extracted by the paragraph information extraction unit 120 and check the indication variable. Here, a paragraph may mean a set of sentences above and below in a document divided by one or more blank lines. Therefore, a single sentence can be a paragraph.

To this end, the paragraph information extracting unit 120 first performs paragraph indexing of news document data, identifies a paragraph containing information to be analyzed among the indexed paragraphs, and sets the center of the index range corresponding to the identified paragraph. The indicator variable for can be assigned to the identified paragraph.

In addition, the label determination unit 130 may determine at least one of an index range and an index order of a target paragraph for determining an emotional label based on the indicator variable. In addition, the label determination unit 130 may determine a positive or negative sentiment score of the relevant paragraph to be analyzed according to a matching comparison operation with the dictionary unit 140.

More specifically, the label determination unit 130 uses the analysis target information (eg, company name list) input through the input unit 110 to determine in which paragraph the analysis target information exists in the news document. You can index within the index range centered on.

If the analysis target information does not exist in any paragraph in the document, the corresponding news article index is terminated, and the input unit 110 receives the next news article.

For example, if the number of searched paragraphs in the news document is 5 and a specific company name is found in the third paragraph, the paragraph information extracting unit 120 may assign 2 to index_p (an indicator variable for paragraph indication). Then, the label determination unit 130 may repeatedly perform a label score operation corresponding to the specific company name within the upper and lower two paragraphs centering on the 2, and processing of article information or news according to the result of performing the score operation. You can decide to skip the document.

In addition, the label determination unit 130 may determine an analysis target emotional information label to be tagged in the paragraph according to the score determination. It may be determined whether the paragraph tagged with the emotional information label is processed into article information by the verification unit 170, and the processing unit 180 determines article information tagged with the emotional label based on the verified paragraph and the emotional information label. Can be processed.

For example, the label determination unit 130 calculates +2 in response to a positive keyword generated within a paragraph based on the paragraph information, calculates -2 in response to a negative keyword, and calculates +2 in response to a positive sentiment word. By calculating 1.5 and calculating -1.5 in response to negative sentiment words, the sentiment label comparison matching score with the dictionary 140 may be determined. Here, the score is an example and may be changed as necessary. A more specific operation of the label determination unit 130 will be described with reference to FIG. 3.

And, after the emotional label for each positive or negative is determined in the label determination unit 130, various evidence records used to determine the label are composed of log data through the log generation unit 160, and the external file (or database) is It can be stored in the form. Log data can be used as a basis for labeling emotion information.

In addition, when a plurality of article documents each including paragraphs to which the label of the emotion information to be analyzed is first tagged are output according to the score comparison in the label determination unit 130, the verification unit 170 performs the emotion of the plurality of article documents. A verification value is calculated according to a similarity comparison operation for each classification, and based on the verification value, a document to be processed into article information and an analysis target emotion information label to be tagged to the article information are finally determined.

Accordingly, the verification unit 170 may perform a verification process to secure stability of the emotional information label tagging result. However, the verification process at this time can also perform a mechanical process to minimize human intervention and perform automatic processing.

More specifically, the verification unit 170 collects the labeling result of the label determination unit 130, calculates the similarity between news article paragraphs tagged with the same emotional label, and calculates the similarity level for each news article paragraph according to the document similarity measurement method. After accumulating, ranking may be determined according to the accumulated size, and a process of removing subordinate news article paragraphs may be performed. Such a process may include a process of normalizing the result for convenience of the customer and dividing the section into [1, 0~1, 0], and the verification unit 170 sets a threshold value corresponding thereto, Only paragraphs that fall within the range of or do not exceed, can be determined for a negative or negative emotional label. This will be described later in more detail with reference to FIG. 6.

On the other hand, the article information processing unit 180 may output the paragraph tagged with the finally determined emotional label as article information, which is provided to the analysis target information service providing device 200 and used for the prediction service of the analysis target. The prediction service may be provided to the user terminal 300.

For example, the forecasting service to be analyzed may include various forecasting services that utilize large-scale news data of a big data scale, forecasting the possibility of a company's insolvency or managing credit, forecasting the stock market of listed companies, analyzing by industry, or developing other forecasting services. It may include a prediction service used for.

In addition, the emotional information labeling device 100 according to an embodiment of the present invention can be applied not only to news articles or report data composed of long texts, but also to various newsletters composed of relatively short texts, online comments, and SNS data. have.

3 is a flowchart illustrating a method of operating the emotional information labeling apparatus 100 according to an embodiment of the present invention in more detail.

3 illustrates a process of outputting article information tagged with a positive or negative emotional label associated with a company name when an analysis target is a company name according to an embodiment of the present invention. The company name may be composed of a list, and analysis target information is set. Depending on the company name, group name, corporation name, person name, etc. may also be changed.

First, referring to FIG. 3, the emotional information labeling apparatus 100 according to an embodiment of the present invention receives a new target article document through the input unit 110 (S101).

In addition, the emotional information labeling apparatus 100 performs paragraph indexing by extracting paragraph information corresponding to a new target document through the paragraph information extracting unit 120 (S102), and checks whether the company name information for each paragraph is indexed ( S103).

Here, a paragraph may mean a set of sentences that are divided into upper and lower blank lines while the document is divided into one or more blank lines. Therefore, a single sentence can be a paragraph.

In addition, the emotional information labeling apparatus 100 may index where the company name in the company name list exists in the news document through the paragraph information extracting unit 120. If the company name is not indexed in any paragraph in the news article document, the news article is ignored and the next news article document is entered.

When the company name is indexed, the emotional information labeling apparatus 100 allocates an indicator variable corresponding to the paragraph in which the company name information is indexed through the paragraph information extracting unit 120 (S105).

For example, if the number of searched paragraphs is 5 and the name of the company to be analyzed is found in the third paragraph, 2 may be assigned to index_p (indicating variable for paragraph indication).

Accordingly, the paragraph information extraction unit 120 may request the label determination unit 130 to perform a label determination process by moving to the paragraph designated by the index_p by using the index_p.

In addition, the emotion information labeling apparatus 100 designates a target paragraph range and an order to determine the emotion label centered on the indicator variable index_p through the label determination unit 130.

Thereafter, the emotional information labeling apparatus 100 performs positive or negative keywords corresponding to each paragraph and positive or negative keywords according to the target paragraph range and order corresponding to the current news article document through repeated execution of steps S109 to S121. After indexing negative sentiment words, scoring is performed to output a paragraph tagged with a final sentiment information label.

More specifically, these repetitive processes can be processed only for paragraphs determined by the target paragraph range and order indicated by a specific indicator variable, not all paragraphs of a news article. One upper paragraph of a paragraph, two lower paragraphs, and the title paragraph of a news article document may be set as the target paragraph range.

In addition, the sequential processing order of the target document is preferably set in the order of the current paragraph, the lower first paragraph, the upper paragraph, the lower second paragraph, and the title paragraph, and the label determination unit 130 is registered in the dictionary unit 140. The scoring process may be performed according to whether terms are indexed, and the log generator 160 may record log information corresponding to the label determination.

First, the emotional information labeling apparatus 100 designates a current paragraph as a target paragraph through the label determination unit 130 (S109).

In addition, the label determination unit 130 determines the type of the target paragraph based on the term information of the dictionary unit 140 (S111).

Here, the type is whether to process as separate article information (go to step S112), move to the next paragraph (go to step S121), or skip the current news article document and receive the next article document (go to step S101). It may be an index to represent, and the label determiner 130 may determine a paragraph type according to whether or not a keyword and a sentiment word registered in the dictionary unit 140 are indexed, and a frequency number.

More specifically, if the paragraph type is 0 to 2, the label determination unit 130 may extract and generate the paragraph currently designated as index_p as a separate article to which relationship information with the originally input article document is allocated (S112). ).

For example, when the original article id is 12345678, the article id of the separately extracted and generated paragraph may be designated as 12345678_1, or separate common relationship metadata within the article may be included.

In addition, the label determination unit 130 may determine a positive or negative score according to a matching comparison operation with the dictionary unit 140 in response to the extracted and generated article (S113), and determine an emotional label based on the score to generate a log. A log is recorded through the unit 160 (S115), and the determined emotional label is tagged to the target paragraph and output to the verification unit 170 (S117).

More specifically, the label determination unit 130 may assign a score for each registered keyword and sentiment words of the dictionary unit 140 indexed within the extracted paragraph, and determine the sum score. And basically, the'positive' emotional label or the'negative' emotional label can be determined according to the positive or negative total score of the paragraph. In addition, when the total score is within a certain range (eg, -1.5 to 1.5), the emotional label may be determined as'neutral'. The range of these values can be adjusted according to the properties of the data or news article.

Thereafter, the emotional information labeling device 100 checks whether the last paragraph is through the label determination unit 130 (S119), and moves to the next paragraph within the target paragraph range according to the specified order (S121), or the next news article document is It is possible to return to the input step S101.

Meanwhile, the step S121 may be performed even when the type index is 3, and when the type index is repeatedly determined to be 3, the label determination unit 130 moves the target paragraph to the top, bottom, etc. The decision process can be repeated. However, when 3 is repeated even after processing the repetitive type determination within the target paragraph range, the label determiner 130 may determine the type index as 4. In this case, the current article is set to type 4, and may be performed again from step S101 in which the next news article document is input.

4 is a diagram illustrating a labeling process according to an embodiment of the present invention.

Referring to FIG. 4, it can be seen that the inputted news article document is composed of seven paragraphs P1, P2, P3, P4, P5, and P7.

Accordingly, the emotional information labeling apparatus 100 obtains the paragraph composition information through the paragraph information extracting unit 120, and among them, the fourth paragraph (P4) in which the name of the company ('company B'), which is the information to be analyzed, is found. ) Can be set as the reference paragraph (index_p) and the pointer can be moved to index_p.

In addition, the emotional information labeling apparatus 100 processes a keyword (kword) and an emotional word (eword) index through the label determination unit 130. In FIG. 4, keywords and sentiment words do not exist in the current fourth index_pth paragraph P5, so the label determiner 130 may move to the index_p+1th paragraph P5. Since there are positive keyword 1, positive sentiment 1, negative keyword 2, and negative sentiment 2,3 in the P5 paragraph, if the sentiment score is calculated, sentiment_score = +2+1.5-2-1.5-1.5 = -1.5, accordingly. The label determination unit 130 may determine that it has a final negative sensibility, and may output a paragraph article labeled with negative sensibility information.

5 is an exemplary diagram of log information extracted according to an embodiment of the present invention.

The table shown in FIG. 5 is an example of the configuration of log data recorded as the label determination unit 130 performs an automated labeling process.

The news information log (News info.) is a log record of the news article itself, and may be composed of an article ID and original content.

Paragraph info. is a log record of extracted paragraphs, including the paragraph id and the extracted paragraph content (filtered paragraph), the scored sum obtained through labeling corresponding to the terms that occurred, and It includes a decided label based on this.

The term information log (Lexicon info.) is a log record of terms constituting the extracted paragraph, and the term and type that occurred (terms per type), frequency, score, and counts per type ).

6 is a diagram illustrating a document verification and filtering process according to an embodiment of the present invention.

Referring to FIG. 6, the verification unit 170 according to an embodiment of the present invention verifies a news article to be processed into article information labeled with emotional information based on a document similarity measurement and a similarity accumulated value, and finally, a service providing device. It is possible to determine the articles to be output to 200.

For example, as shown in FIG. 6, assuming that news data with 10 positive emotion labels are generated, the verification unit 170 may generate a document verification model using terms registered in the dictionary unit 140. The similarity between articles including the paragraphs labeled with emotional information and other news articles that have been previously generated is calculated using a document verification model, and then an accumulated similarity value is calculated.

In this case, the verification unit 170 may perform normalization as necessary to calculate the cumulative value of the similarity for each news article, and then position each article in three sections such as [1, 0 to 1, 0]. An article whose value is 1 indicates that it is almost similar to other documents in terms of similarity and, for example, may be a case that is judged to be an article sufficiently expressing a positive emotion. However, when the value is 1, the frequency is generally low.

In the case of [1~0], articles that are partly similar and partly different from other documents may be determined as'positive' articles or articles that may be determined as'neutral' according to the user's judgment.

However, contrary to the numerical meaning, even if the actual similarity value is low (for example, 0.4), the positive emotion value cannot be considered low, and differences may occur because the composition of terms is different from other articles in the same category. .

Accordingly, in the case of [1 to 0], the verification unit 170 may set an upper or lower limit boundary value, check only samples of articles located within the boundary value, or set a separate reference value.

On the other hand, when the similarity is 0, the verification unit 170 may determine that the similarity value is too low or has a characteristic different from that of other articles, so that it is'neutral' or'unable to judge'. In this case, as in case 1, only a small number of articles may be applicable.

Accordingly, when the similarity accumulated value exists among the three sections as shown in FIG. 6, the verification unit 170 may perform a process of removing specific news articles from the processing target by setting a threshold. .

6 shows a case where the threshold value is set to 0.32, and accordingly, the verification unit 170 removes news articles 7 and 8 documents having 1.28 and 2.17 values lower than 0.32 accordingly.

In addition, only news article numbers 1 to 6 and 9 to 10 are finally left in the positive emotion news article set that has been verified by the verification unit 170, which is transmitted to the processing unit 180 to label the positive emotion information. They can be processed and printed as articles.

On the other hand, the verification unit 170 performs a similarity verification process for a set of news articles having negative sensibility in the same manner, and collects only news articles that are finally determined as having negative sensibility by passing the verification as to whether or not they have negative sensibility. , By passing it to the processing unit 180, the negative emotion information may be processed and output as labeled articles.

Meanwhile, the method according to various embodiments of the present invention described above may be implemented as a program and provided to each server or devices while being stored in various non-transitory computer readable media. Accordingly, the user terminal 100 may access the server or device and download the program.

The non-transitory readable medium refers to a medium that stores data semi-permanently and can be read by a device, rather than a medium that stores data for a short moment, such as a register, a cache, and a memory. Specifically, the above-described various applications or programs may be provided by being stored in a non-transitory readable medium such as a CD, DVD, hard disk, Blu-ray disk, USB, memory card, ROM, or the like.

In addition, although the preferred embodiments of the present invention have been illustrated and described above, the present invention is not limited to the specific embodiments described above, and the technical field to which the present invention belongs without departing from the gist of the present invention claimed in the claims. In addition, various modifications are possible by those of ordinary skill in the art, and these modifications should not be individually understood from the technical spirit or prospect of the present invention.

Claims (19)

Receiving a new news article for labeling emotional information;
Extracting paragraph information of the new news article, performing paragraph indexing, and checking whether the analysis target information is indexed for each of the indexed paragraphs;
Allocates an indicator variable corresponding to the paragraph in which the information to be analyzed is indexed, and sets the current paragraph to which the indicator variable is assigned, the upper one paragraph, the lower two paragraphs, and the title paragraph of the news article document as the target paragraph range. And setting a current paragraph, a lower first paragraph, an upper paragraph, a lower second paragraph, and a title paragraph in order;
Designate the current paragraph as the target paragraph according to the above-set order, and whether to process it into article information for emotional labeling based on the presence and frequency of keywords and sentiment words based on the preset dictionary, whether to move to the next paragraph or to the present Determining a paragraph type by skipping a news article document and indexing an index indicating whether to receive a next article document;
If it is a paragraph to be processed into article information based on the paragraph type, assigning a score for each dictionary registered keyword and sentiment words indexed in the extracted paragraph, and determining the score of the corresponding analyzer based on the sum score Wow;
Determining a positive, negative, or neutral emotional label based on the score of the analyzed article, recording log information on determination of the emotional label of the corresponding paragraph, and tagging the determined emotional label and log information to a target paragraph;
Obtaining a plurality of article documents each including paragraphs to which the emotion information label to be analyzed is first tagged, calculating a verification value according to a similarity comparison operation for each emotion classification of the plurality of article documents, and based on the verification value, Finally determining a document to be processed into article information and an analysis target emotion information label to be tagged to the article information; Including
How to label sentiment information in news articles. The method of claim 1,
The paragraph information extraction refers to a set of sentences that are divided into upper and lower blank lines while the document is divided into one or more blank lines, and includes extracting a single sentence into one paragraph.
How to label sentiment information in news articles. The method of claim 1,
A company name list is set in advance as the information to be analyzed, and the company name in the company name list is indexed in which paragraph in the news document, and if the company name is not indexed in any paragraph in the news document, the news document is ignored, The following news article documents are received
How to label sentiment information in news articles. The method of claim 1,
The dictionary unit,
And a plurality of language data sets built on a learning basis to determine an analysis target emotional information label of a paragraph obtained from the document data,
The language data set,
A keyword set capable of discriminating a noun-type term having a positive or negative meaning corresponding to the economy or credit of an analysis object from the paragraph;
A sentiment word set capable of identifying an adjective-type term having a positive or negative meaning corresponding to the reputation of the analysis target from the paragraph; Including
How to label sentiment information in news articles. The method of claim 1,
Log information for determining the emotion label,
Includes news information log, paragraph information log, and term information log,
News info. is a log record of the news article itself, and is composed of article id and original content.
Paragraph info. is a log record of extracted paragraphs, including the paragraph id and the extracted paragraph content (filtered paragraph), the scored sum obtained through labeling corresponding to the terms that occurred, and Includes a label determined based on this,
The term information log (Lexicon info.) is a log record of terms constituting the extracted paragraph, and the term and type that occurred (terms per type), frequency, score, and counts per type ) Consisting of
How to label sentiment information in news articles. delete delete delete delete delete delete delete delete delete delete delete delete delete delete

Images