Information processing apparatus, information processing method, and information processing program

Abstract

To provide an information processing apparatus, an information processing method, and an information processing program that can improve quality of a service related to comments.SOLUTION: An information processing apparatus according to the present application comprises a classification unit and a providing unit. The classification unit classifies comments posted for a predetermined content by a tendency of description of the comments. The providing unit provides the comments in the respective tendencies when a result of classification satisfies a predetermined condition.SELECTED DRAWING: Figure 3

Description

Technical Field

[0001] The present invention relates to an information processing apparatus, an information processing method, and an information processing program.

Background Art

[0002] Conventionally, there has been a service that provides comments posted by a user on a news article to other users who have viewed the news article (see, for example, Patent Document 1).

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] However, in the prior art, there has been room for further improvement in improving the quality of services related to comments.

[0005] 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 capable of improving the quality of services related to comments.

Means for Solving the Problems

[0006] The information processing apparatus according to the present application includes a classification unit and a provision unit. The classification unit classifies each comment posted on a predetermined content according to the tendency of the comment content. The provision unit provides the comments of each tendency when the classification result satisfies a predetermined condition.

Effects of the Invention

[0007] According to one aspect of the embodiment, there is an effect that the quality of services related to comments can be improved.

Brief Description of the Drawings

[0008]

Figure 1A

Figure 1B

Figure 1C

Figure 1D

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

Figure 8

Figure 9

Figure 10

Figure 11

Modes for Carrying Out the Invention

[0009] Hereinafter, embodiments for implementing the information processing apparatus, information processing method, and information processing program according to the present application (hereinafter referred to as "embodiments") will be described in detail with reference to the drawings. Note that the information processing apparatus, information processing method, and information processing program according to the present application are not limited by this embodiment. Also, in each of the following embodiments, the same parts are denoted by the same reference numerals, and redundant descriptions are omitted.

[0010] (Embodiment) First, with reference to FIGS. 1A to 1D, the processing executed by the information processing apparatus according to the embodiment will be described. FIGS. 1A to 1D are diagrams showing Process 1 to Process 4 executed by the information processing apparatus according to the embodiment. Note that FIGS. 1A to 1D show an operation example of the information processing system S including the information processing apparatus 1 according to the embodiment.

[0011] As shown in FIGS. 1A to 1D, the information processing system S according to the embodiment includes an information processing apparatus 1, a plurality of user terminals 100, and a request source terminal 200. Note that in FIGS. 1B to 1D, the request source terminal 200 is omitted for convenience of explanation.

[0012] In the information processing system S according to the embodiment, various processes are performed based on comments posted by users on predetermined content, thereby improving the quality of services related to the comments.

[0013] First, Process 1 shown in FIG. 1A will be described. Specifically, the information processing apparatus 1 first receives a request for content distribution from a requesting user via the request source terminal 200 (step S1).

[0014] The content is, for example, information on news articles in a news distribution service, information on products sold in a shopping service, or the like. In other words, the content is content that can receive comments from the distributing user. The comment is, in the case of a news article, a comment on the news article, and in the case of a product, a review of the product or a review of the store selling the product.

[0015] Subsequently, the information processing apparatus 1 distributes the received content to the user via the user terminal 100 (step S2). Specifically, when the information processing apparatus 1 receives a content distribution request from the user terminal 100, the information processing apparatus 1 distributes the specified content to the user terminal 100.

[0016] Subsequently, the information processing apparatus 1 receives comments on the content from the user who has received the content distribution (step S3). The comment is, for example, information in text format, but is not limited to this, and may be information in audio format or image format. Note that the reception of the comment may accept a comment that the user is in the process of inputting, or may accept the comment after the user presses a button (posting button) to request posting after input.

[0017] Subsequently, the information processing apparatus 1 analyzes the received comment and identifies the tendency of the comment content (step S4). The tendency includes, for example, whether the comment content is favorable or negative with respect to the entire content or a part of the content, or whether the content supplements the content of the entire content or a part of the content. The tendency may be preset or may be automatically generated based on the comment content.

[0018] To identify the tendency, for example, a classification model in machine learning can be used. Specifically, the information processing apparatus 1 inputs the comment into a classification model that has learned the comment content and the tendency as a dataset, thereby identifying the tendency of the comment.

[0019] Subsequently, the information processing apparatus 1 classifies each comment according to the identified tendency (step S5). Specifically, the information processing apparatus 1 sorts each comment according to the identified tendency.

[0020] For example, when the number of comments has reached or exceeded a predetermined number, the information processing apparatus 1 stops sorting comments for such a trend after the timing when the number has reached or exceeded the predetermined number. Further, when a trend in which a predetermined number or more of comments are classified in a short period (predetermined period), the information processing apparatus 1 performs a process of thinning out unnecessary comments (for example, random extraction) from among such a predetermined number or more of comments. That is, when a predetermined number or more of comments are classified for a specific trend, the information processing apparatus 1 regards such a predetermined number or more of comments as inappropriate comments (spam comments, abusive comments) and prevents them from increasing any further.

[0021] Subsequently, the information processing apparatus 1 performs various notifications to the user based on the trend of the comment content (step S6). Specifically, when the identified trend is similar (including the same) to the trend of the already-posted comments for which a predetermined number or more have already been posted, the information processing apparatus 1 issues a non-posting notification indicating that the comment cannot be posted. The non-posting notification may be notified, for example, by making the post button displayed on the user terminal 100 non-displayed when the user is in the middle of inputting a comment, or by notifying a text message indicating that the post cannot be accepted after the user has pressed the post button. That is, the information processing apparatus 1 performs control to avoid accepting the posting of comments. Thereby, for example, it is possible to avoid a decrease in the diversity of comments due to only a large number of comments of the same trend being posted. That is, according to the information processing apparatus 1 according to the embodiment, since the diversity of comments can be increased, the quality of the service regarding comments can be improved.

[0022] In addition, the information processing apparatus 1 compares the comment status for each classified trend and proposes comment contributions for other trends based on the comparison result. Specifically, the information processing apparatus 1 compares the number of comments for each trend and proposes comment contributions for trends where the number of comments is less than a predetermined number. Specifically, when a predetermined number or more of comments have already been collected for the trend of the posted comments, the information processing apparatus 1 proposes the posting of comments regarding trends where the number of comments is less than the predetermined number. As a result, the diversity of comments can be increased, and thus the quality of the service related to comments can be improved.

[0023] Subsequently, the information processing apparatus 1 determines whether the classification result by the process of step S5 satisfies a predetermined condition (step S7). Specifically, the information processing apparatus 1 determines whether comments for a predetermined number or more of the plurality of preset trends have been posted (classified).

[0024] Subsequently, when the classification result satisfies a predetermined condition, specifically, when comments for a predetermined number or more of the plurality of preset trends have been posted, the information processing apparatus 1 collectively provides the posted comments for each trend (step S8-1). That is, instead of immediately providing the posted comments, the comments are collectively provided at the timing when comments for various trends have been posted. As a result, it is possible to prevent only comments with a biased trend from being provided, and since comments for various trends can be collectively provided, the diversity of comments can be increased. That is, according to the information processing apparatus 1 according to the embodiment, the quality of the service related to comments can be improved.

[0025] In addition, the information processing apparatus 1 provides comments with a tendency different from that of the comments posted by the user who posted the comment (step S8-2). For example, the information processing apparatus 1 collectively provides comments with a tendency excluding the tendency of the comments posted by the user among the comments of each tendency. In this way, the posting user can view comments with a tendency other than the tendency of the comments posted by the posting user. That is, according to the information processing apparatus 1 according to the embodiment, the quality of the service related to the comments can be improved.

[0026] Next, the second part of the process shown in FIG. 1B will be described. In FIG. 1B, for the processes that overlap with the processes shown in FIG. 1A, the description may be omitted for convenience of explanation.

[0027] In the second part of the process shown in FIG. 1B, the information processing apparatus 1 collects (acquires) evaluation information indicating the evaluation of each comment posted on the content (step S31). The evaluation information includes whether the evaluation of the comment is a favorable evaluation (agreeing with the comment) or a negative evaluation (not agreeing with the comment).

[0028] Subsequently, the information processing apparatus 1 determines the diversity of the evaluations based on the acquired evaluation information (step S32). For example, when the evaluation of the comment is only a favorable evaluation (or only a negative evaluation), the information processing apparatus 1 determines that there is no diversity in the evaluations. In other words, when the number of evaluations (number of users) of each of the favorable evaluation and the negative evaluation is balanced (when the difference in the number of evaluations is less than a predetermined value), the information processing apparatus 1 determines that there is diversity in the evaluations.

[0029] In addition, the information processing apparatus 1 determines the diversity of evaluations included in a set for each combination of a plurality of comments. Specifically, the information processing apparatus 1 determines whether there is diversity in the evaluations of the comments included in the set. For example, when user A evaluates comment A and comment B, if user A gives a favorable evaluation to comment A and a negative evaluation to comment B, the information processing apparatus 1 determines that there is diversity in the evaluations of the set of comment A and comment B. Note that in the above description, the diversity is determined based on the evaluation of user A, but the diversity may also be determined based on the evaluations of a group including a plurality of users with similar user information. Note that the number of comments included in the set may be three or more.

[0030] In addition, the information processing apparatus 1 determines that there is diversity in the evaluations for a set including only favorable evaluation comments and only negative evaluation comments. That is, when the information processing apparatus 1 views the evaluations in terms of sets, if the favorable evaluations and the negative evaluations are balanced, the information processing apparatus 1 determines that there is diversity in the evaluations.

[0031] Subsequently, the information processing apparatus 1 determines whether to display the comment (whether to make it a display target) based on the determination result (step S33). For example, the information processing apparatus 1 determines that the comments for which diversity in evaluations is determined are display targets. In addition, the information processing apparatus 1 determines that the comments of the set for which diversity in evaluations is determined are display targets.

[0032] Subsequently, the information processing apparatus 1 displays the comments (sets of comments) determined to be display targets on the user terminal 100 (step S34). As described above, according to the information processing apparatus 1 according to the embodiment, by providing comments with diversity in evaluations, the quality of the service related to the comments can be improved.

[0033] Next, the third part of the process shown in FIG. 1C will be described. Note that in FIG. 1C, descriptions of processes overlapping with those shown in FIGS. 1A and 1B may be omitted for convenience of explanation.

[0034] In Process 3 shown in FIG. 1C, the information processing apparatus 1 collects each comment on the content (step S51).

[0035] Subsequently, the information processing apparatus 1 extracts comments whose comment content satisfies a predetermined content condition (step S52). For example, the information processing apparatus 1 uses a model learned with a dataset of feature information extracted from the comment content and a score indicating the degree of inappropriateness of the comment content, and extracts comments whose comment content is inappropriate (score is equal to or higher than a predetermined value).

[0036] Subsequently, the information processing apparatus 1 identifies users who agreed with the extracted comments (step S53). Specifically, the information processing apparatus 1 identifies users who gave a favorable evaluation to the extracted comments.

[0037] Subsequently, the information processing apparatus 1 detects other comments whose comment content satisfies a predetermined condition based on the agreement status of the identified users (specific users) with other comments (step S54). For example, the information processing apparatus 1 detects other comments for which the number of specific users who agreed with the other comments is equal to or more than a predetermined number as other comments that satisfy the predetermined condition. In other words, the information processing apparatus 1 detects, as comments with inappropriate content, other comments with a large number of specific users for other comments determined not to have inappropriate comment content in step S52. Thereby, since inappropriate other comments can be found from the agreement status of users who agreed with inappropriate comments with other comments, the quality of the service regarding comments can be improved.

[0038] Subsequently, the information processing apparatus 1 displays, on the user terminal 100, comments excluding the other comments detected in step S54 and the comments extracted in step S52 from the display targets (step S55).

[0039] Next, the fourth process shown in FIG. 1D will be described. In FIG. 1D, for processes that overlap with those shown in FIGS. 1A to 1C, the description may be omitted for convenience of explanation.

[0040] In the fourth process shown in FIG. 1D, the information processing apparatus 1 distributes content to the user terminal 100 (step S71). Subsequently, the information processing apparatus 1 receives a user's comment on the content (step S72).

[0041] Subsequently, the information processing apparatus 1 classifies each received comment according to the tendency of the comment content or according to the user information of the posting user (step S73).

[0042] Subsequently, the information processing apparatus 1 identifies the user information corresponding to the comment viewed by the browsing user or the tendency of the comment (step S74). Specifically, the information processing apparatus 1 identifies the user information or tendency into which the comments viewed by the browsing user in the past are classified.

[0043] Subsequently, the information processing apparatus 1 extracts comments corresponding to user information different from the identified user information or comments having a tendency different from the identified tendency (step S75).

[0044] Subsequently, the information processing apparatus 1 provides the extracted comments to the user terminal 100 of the browsing user (step S76).

[0045] Thereby, since comments with tendencies and user information different from those of the comments viewed by the browsing user can be provided, the quality of the service regarding comments can be improved.

[0046] Next, with reference to FIG. 2, a configuration example of the information processing system S according to the embodiment will be described. FIG. 2 is a block diagram showing a configuration example of the information processing system S according to the embodiment. As shown in FIG. 2, in the information processing system S according to the embodiment, an information processing apparatus 1, a plurality of user terminals 100, and a plurality of request source terminals 200 are connected to a network N by wire or wirelessly. The network N is, for example, a network such as the Internet, a WAN (Wide Area Network), or a LAN (Local Area Network).

[0047] The information processing apparatus 1 is a server apparatus that executes the information processing method according to the embodiment. The information processing apparatus 1 executes Process 1 to Process 4 described above using FIGS. 1A to 1D.

[0048] In addition, the information processing apparatus 1 is an information processing apparatus that cooperates with a plurality of user terminals 100 and a plurality of request source terminals 200 and provides API (Application Programming Interface) services and various data for each user terminal 100 and each request source terminal 200 with respect to various applications (hereinafter referred to as apps), etc., and is realized by a server apparatus, a cloud system, or the like.

[0049] Further, the information processing apparatus 1 may be an information processing apparatus that provides some kind of Web service online for each user terminal 100 and each request source terminal 200. For example, as a Web service, the information processing apparatus 1 may provide services such as Internet connection, search service, SNS (Social Networking Service), electronic commerce (EC: Electronic Commerce), electronic payment, online game, online banking, online trading, accommodation / ticket reservation, video / music distribution, news, map, route search, route guidance, route information, operation information, weather forecast, etc. Actually, the information processing apparatus 1 may cooperate with various servers that provide the above Web services and mediate the Web services or be in charge of the processing of the Web services.

[0050] The user terminal 100 is a terminal device held by a user who views content, comments, evaluations of comments, etc. The user terminal 100 can use any type of terminal device such as a smartphone, desktop PC, notebook PC, tablet PC, etc. The user terminal 100 transmits various information to the information processing device 1, etc., and receives information provided from the information processing device 1, etc.

[0051] The requesting source terminal 200 is a terminal device held by a requesting user who requests the distribution of content. The requesting source terminal 200 can use any type of terminal device such as a smartphone, desktop PC, notebook PC, tablet PC, etc. The requesting source terminal 200 transmits various information to the information processing device 1, etc., and receives information provided from the information processing device 1, etc.

[0052] Next, with reference to FIG. 3, a configuration example of the information processing device 1 will be described.

[0053] FIG. 3 is a diagram showing a configuration example of the information processing device 1 according to the embodiment. As shown in FIG. 3, the information processing device 1 includes a communication unit 2, a control unit 3, and a storage unit 4. The control unit 3 includes a distribution unit 31, an acquisition unit 32, a specifying unit 33, a classification unit 34, a determination unit 35, a decision unit 36, a detection unit 37, a reception control unit 38, a proposal unit 39, and a provision unit 40. The storage unit 4 stores user information 41, content information 42, and comment information 43.

[0054] The communication unit 2 is realized by, for example, a NIC (Network Interface Card) or the like. The communication unit 2 is connected to a network via wire or wirelessly.

[0055] The control unit 3 is a controller, which is realized, for example, by a processor such as a CPU (Central Processing Unit) or an MPU (Micro Processing Unit), when various programs (corresponding to an example of information processing programs) stored in a storage device inside the information processing apparatus 1 are executed with a RAM or the like as a work area. Further, the control unit 3 is a controller and may be realized by an integrated circuit such as an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array), or a GPGPU (General Purpose Graphic Processing Unit).

[0056] The storage unit 4 is realized, for example, by a semiconductor memory element such as a RAM (Random Access Memory) or a flash memory, or a storage device such as a hard disk or an optical disk.

[0057] The user information 41 is information about the user. FIG. 4 is a diagram showing an example of the user information 41. As shown in FIG. 4, the user information 41 includes items such as "user ID" and "user information".

[0058] The "user ID" is identification information for identifying the user. The "user information" is information about the user. The "user information" includes, for example, attribute information regarding the attributes of the user and behavior information. The attribute information includes psychographic attributes, demographic attributes, and the like. The behavior information includes the user's behavior on the network (search behavior, purchase behavior, comment posting behavior, evaluation posting behavior, etc.).

[0059] Next, the content information 42 is information about the content. FIG. 5 is a diagram showing an example of the content information 42. As shown in FIG. 5, the content information 42 includes items such as "content ID", "type", "content information", and "comment information".

[0060] The "Content ID" is identification information for identifying content. The "Type" is information indicating the type of content. The "Content Information" is information indicating the content of the content and includes text information, image information, etc. The "Comment Information" is information on comments posted on the content, and the "Comment ID" of the comment information 43 described later is input.

[0061] Next, the comment information 43 is information regarding comments posted on the content. FIG. 6 is a diagram showing an example of the comment information 43. As shown in FIG. 6, the comment information 43 includes items such as "Comment ID", "Trend", "Content Information", and "Evaluation Information".

[0062] The "Comment ID" is identification information for identifying a comment. The "Trend" is information indicating the trend of the comment content. The "Content Information" is information indicating the comment content and includes text information. The "Evaluation Information" is information regarding the evaluation made by the user on the comment and includes, for example, information on the number of users who made a favorable evaluation and the number of users who made a negative evaluation.

[0063] Next, each function (distribution unit 31, acquisition unit 32, specification unit 33, classification unit 34, determination unit 35, decision unit 36, detection unit 37, reception control unit 38, proposal unit 39, and provision unit 40) of the control unit 3 of the information processing apparatus 1 will be described.

[0064] The distribution unit 31 distributes content to the user terminal 100. The distribution unit 31 acquires the content to be distributed from the requesting user via the source terminal 200 and stores it in the content information 42. Then, when the distribution unit 31 receives a content distribution request from the user via the user terminal 100, it distributes the target content to the user terminal 100.

[0065] In addition, the distribution unit 31 distributes together with the content the comments posted by other users who viewed the content and the evaluations posted by other users on the comments.

[0066] The acquisition unit 32 acquires comments on the content from the users who have distributed the content. The timing of acquiring comments by the acquisition unit 32 is arbitrary. For example, when the acquisition unit 32 satisfies a predetermined condition during the input of comments (the number of characters is equal to or more than a predetermined number, the elapsed time of input is equal to or more than a predetermined time, etc.), the acquisition unit 32 acquires the comments being input. Also, the acquisition unit 32 acquires the comments when the above-described posting button is pressed after the comments are input. Further, the acquisition unit 32 acquires evaluation information indicating an evaluation of the comments.

[0067] The specifying unit 33 specifies the trend of the comment content based on the comment content. For specifying the trend, for example, a classification model in machine learning can be used. Specifically, the specifying unit 33 inputs the comment into a classification model that has learned the comment content and the trend as a dataset, thereby specifying the trend of the comment.

[0068] Also, the specifying unit 33 specifies the user information of the posting user who has posted the comments. The user information to be specified is, for example, attribute information such as gender, location, occupation, etc., and behavior information such as search behavior and purchase behavior.

[0069] Also, the specifying unit 33 specifies the users who have agreed to the comments determined by the determination unit 35 described later to satisfy a predetermined content condition. For example, the specifying unit 33 specifies the users who have given a favorable evaluation to the comments that satisfy the predetermined content condition.

[0070] Also, the specifying unit 33 specifies the trend corresponding to the posting user based on the action history regarding the comments of the posting user who has posted the comments. The action history regarding the comments is, for example, the posting history of past comments, the evaluation history of the comments posted by other posting users, etc.

[0071] For example, the specifying unit 33 specifies the tendency corresponding to the posting user based on the tendency of the comments posted by the posting user in the past. Specifically, the specifying unit 33 aggregates the tendencies of the comments posted in the past, and specifies the tendency with the largest number of comments as the tendency corresponding to the posting user. Further, the specifying unit 33 may specify a plurality of tendencies with the number of comments equal to or more than a predetermined number as the tendency (plurality) corresponding to the posting user based on the above aggregation result.

[0072] In addition, the specifying unit 33 specifies the tendency corresponding to the posting user based on the content of the evaluation history for the comments posted by other posting users. Specifically, when the posting user gives a favorable evaluation to the comments posted by other posting users, the specifying unit 33 specifies the tendency of the evaluated comments as the tendency corresponding to the posting user.

[0073] In addition, when the posting user gives a negative evaluation to the comments posted by other posting users, the specifying unit 33 specifies a tendency different from the tendency of the evaluated comments as the tendency corresponding to the posting user.

[0074] Note that as a method for selecting a tendency different from the tendency of the evaluated comments, it can be selected based on the distance between tendencies in the dispersion representation space. That is, the specifying unit 33 specifies, in the dispersion representation space, a tendency that is separated from the tendency of the evaluated comments by a predetermined distance or more as the tendency corresponding to the posting user.

[0075] The classification unit 34 classifies each comment for each specified tendency or for each specified user information. Specifically, the classification unit 34 sorts each comment for each specified tendency or for each specified user information. More specifically, the classification unit 34 classifies the tendency of the specified comment into any one of a plurality of preset tendencies. Such classification can be performed by inputting the specified tendency into a model that has learned, as a data set, the specified tendency and the tendency to which the specified tendency belongs among the plurality of preset tendencies.

[0076] For example, when the number of comments reaches a predetermined number or more, or for user information, the classification unit 34 stops classifying such trends or sorting comments to user information after the timing when the number reaches a predetermined number or more. Also, for trends or user information for which a predetermined number or more of comments have been classified in a short period (predetermined period), the classification unit 34 performs a process of thinning out unnecessary comments (for example, random extraction) from among such a predetermined number or more of comments. That is, when a predetermined number or more of comments are classified into a specific trend or user information, the classification unit 34 regards such a predetermined number or more of comments as inappropriate comments (spam comments, abusive comments) so that they do not increase any further.

[0077] Further, the classification unit 34 may re-set a plurality of trends to be classified based on the classification results. Specifically, when the number of comments classified into a specific trend is extremely large, in other words, when the number of comments classified into a specific trend is a predetermined number or more and the number of comments classified into other trends is less than the predetermined number, the classification unit 34 may analyze the comment contents of the classified comments and subdivide the specific trend into a plurality of trends. Alternatively, the classification unit 34 may reduce the number of other trends by combining other trends with less than a predetermined number of comments.

[0078] Such a method for reconstructing trends can be realized, for example, by converting each comment into a distributed representation based on the comment content and automatically generating an axis for delimiting areas in the distributed representation space as a trend.

[0079] The determination unit 35 performs various determination processes. For example, the determination unit 35 determines whether the trend of the identified comment satisfies the conditions based on the trends of the already-posted comments. Specifically, the determination unit 35 determines that the above conditions are satisfied when the trend of the identified comment is similar to the trend in which a predetermined number of already-posted comments are classified.

[0080] Further, the determination unit 35 calculates the ratio of the number of posted comments for each tendency to the number of posted comments for all tendencies, and determines that the above conditions are satisfied when the tendency in which such ratio is equal to or greater than a predetermined value is similar to the tendency of the identified comment.

[0081] Further, the determination unit 35 may determine whether or not the above conditions are satisfied in consideration of the relationship between the posting user and the tendency of the comments posted by the posting user in the past. Specifically, the determination unit 35 first estimates a risk indicating the ease of posting for each tendency according to the number of comments for each tendency posted by the posting user in the past. The risk is set higher for a tendency with a larger number of comments. Then, the determination unit 35 calculates a score indicating the degree of similarity between the tendency of the identified comment and the tendency to which a predetermined number of posted comments are classified, and determines whether or not the above conditions are satisfied based on such score and the above risk.

[0082] Further, the determination unit 35 determines the diversity of evaluations based on the evaluation information acquired by the acquisition unit 32. For example, the determination unit 35 determines that there is no diversity in evaluations when the evaluations for the comments are only favorable evaluations (or only negative evaluations). That is, in other words, the determination unit 35 determines that there is diversity in evaluations when the number of evaluations (number of users) for each of the favorable evaluations and negative evaluations is balanced (when the difference in the number of evaluations is less than a predetermined value).

[0083] Further, the determination unit 35 may determine the diversity of evaluations in a plurality of comments. For example, the determination unit 35 determines the diversity of evaluations included in a set for each combination of a plurality of comments. Specifically, the determination unit 35 determines whether there is diversity in the evaluations of the comments included in the set. For example, when user A evaluates comment A and comment B, if a favorable evaluation is given for comment A and a negative evaluation is given for comment B, the determination unit 35 determines that there is diversity in the evaluations of the set of comment A and comment B. Note that in the above description, the diversity is determined based on the evaluation of user A, but the diversity may also be determined based on the evaluations of a group including a plurality of users with similar user information. Note that the number of comments included in the set may be three or more.

[0084] In addition, the determination unit 35 determines that there is diversity in the evaluations for a set including comments with only favorable evaluations and comments with only negative evaluations. That is, when the determination unit 35 views the evaluations in units of sets, if the favorable evaluations and the negative evaluations are balanced, the determination unit 35 determines that there is diversity in the evaluations.

[0085] Further, the determination unit 35 may determine the diversity of the users who have made evaluations. For example, when the attribute information of each user who has given a favorable evaluation (or a negative evaluation) to a comment is not similar, that is, when users with various attributes have given favorable evaluations, the determination unit 35 determines that there is diversity in the evaluations.

[0086] On the other hand, when the attribute information of each user who has given a favorable evaluation (or a negative evaluation) to a comment is similar, that is, when users with the same type of attributes have given favorable evaluations, the determination unit 35 determines that there is no diversity in the evaluations.

[0087] In addition, the determination unit 35 may group users based on user information and determine the diversity of evaluations in group units. For example, when the information of the groups (for example, the attribute information of the groups) that have given favorable evaluations (or negative evaluations) to the comments is not similar, that is, when groups of various attributes have given favorable evaluations, the determination unit 35 determines that there is diversity in the evaluations.

[0088] On the other hand, when the information of each group that has given a favorable evaluation (or a negative evaluation) to the comment is similar, that is, when groups of the same attributes have given favorable evaluations, the determination unit 35 determines that there is no diversity in the evaluations.

[0089] In addition, the determination unit 35 determines whether the comment content satisfies a predetermined content condition. Specifically, the determination unit 35 inputs the comment into a model learned with the feature information extracted from the comment content and the score indicating the degree of inappropriateness of the comment content as a data set, and determines that the content condition is satisfied when the score output from the model is equal to or higher than a predetermined value. That is, the content condition is a condition for determining whether the comment content is inappropriate (violent expressions, obscene expressions, slanderous expressions, etc.). In addition, the feature information includes articles of violent expressions, obscene expressions, slanderous expressions included in the comment content, the presence or absence of words related to these expressions, and the number of the articles and the words. Note that the determination unit 35 may correct the above model based on other comments that satisfy (are inappropriate) the predetermined conditions detected by the detection unit 37 described later.

[0090] The decision-making unit 36 decides whether to display the comment based on the determination result of the determination unit 35. Specifically, the decision-making unit 36 decides whether to display the comment based on the determination result of the diversity of the evaluations. Specifically, the decision-making unit 36 decides the comment for which the diversity of the evaluations is determined as the display target. In addition, the decision-making unit 36 decides the set of comments for which the diversity of the evaluations is determined as the display target.

[0091] Further, the determination unit 36 determines the display order of comments based on the determination result of the diversity of evaluations. For example, the determination unit 36 displays at the top the comments for which the diversity of evaluations is determined to be present, among a plurality of comments for which a large number of users have made favorable (or negative) evaluations of the comments.

[0092] The detection unit 37 detects other comments whose comment contents satisfy a predetermined condition, based on the consent status of the other comments of the user specified by the specifying unit 33 (the user who agreed to the comment satisfying the content condition). Specifically, the detection unit 37 detects, as other comments satisfying the predetermined condition, other comments for which the number of users who agreed to other comments among the specified users is equal to or greater than a predetermined number. Alternatively, the detection unit 37 may detect, as other comments satisfying the predetermined condition, other comments for which the ratio of the number of users specified by the specifying unit 33 to the total number of users who agreed to other comments is equal to or greater than a predetermined value. In other words, the detection unit 37 detects, as comments with inappropriate content, other comments to which the majority of the specified users agreed, among other comments determined by the determination unit 35 not to have inappropriate comment content. Note that the other comments may be comments posted for the same content (for example, the same news article) that satisfies a predetermined content condition, or may be comments posted for other content of the same type (for example, other news articles). Further, the detection unit 37 may detect appropriate comments from among the comments determined to have inappropriate comment content, based on the consent status of the other comments of the specified users. Further, the other comments detected by the detection unit 37 may be, in addition to comments with inappropriate content, comments seeking empathy from other users, comments posted by the parties involved in the content, and the like.

[0093] Further, the detection unit 37 may detect other comments that satisfy a predetermined condition in consideration of the context information of the identified user. For example, when the context information of the user when agreeing to an inappropriate comment is similar to the context information of the user when agreeing to other comments, the detection unit 37 detects the other comments as other comments that satisfy a predetermined condition. That is, the detection unit 37 estimates from the context information of the user whether or not the user is in a mood (contrary mood) to agree to an inappropriate comment, and detects other comments agreed to when in the mood to agree to an inappropriate comment as other comments that satisfy (inappropriate) a predetermined condition. Note that the context information includes context related to search such as a search query and context related to the user's emotion. The context related to the user's emotion can be inferred from, for example, the text expression of an email, the conversation expression of a voice conversation, or the like.

[0094] Based on the determination result of the determination unit 35, the reception control unit 38 performs control to avoid receiving a comment post. Specifically, when the identified tendency is similar (including the same) to the tendency of the posted comments that have already been posted a predetermined number or more times, the reception control unit 38 issues a post-not-allowed notification indicating that the comment cannot be posted. The post-not-allowed notification may be notified, for example, by making the post button displayed on the user terminal 100 non-displayed when the user is in the middle of inputting a comment, or by notifying a text message indicating that the post cannot be accepted after the user presses the post button.

[0095] Further, the reception control unit 38 may make a proposal to change the tendency of the input comment as control to avoid receiving a comment post. In such a case, the reception control unit 38 proposes a change to a tendency in which the number of classified comments is less than a predetermined number based on the classification result of the classification unit 34.

[0096] The proposal unit 39 compares the comment status for each tendency classified by the classification unit 34, and proposes a comment post based on the comparison result. The proposal of the comment post may be made, for example, when browsing the content or when inputting a comment.

[0097] For example, the proposal unit 39 compares the number of comments for each trend and proposes a comment post for a trend with the number of comments less than a predetermined number. Further, the proposal unit 39 compares the ratio of the number of comments for each trend to the total number of comments obtained by summing the number of comments for each trend, and proposes a comment post for a trend with a ratio less than a predetermined value. Alternatively, the proposal unit 39 proposes a comment post for a trend with a low ratio when the difference between the above ratios between trends is equal to or greater than a predetermined value.

[0098] In addition, when the number of trends is less than a predetermined number, the proposal unit 39 proposes a comment post for a new trend. Also, when the proposal unit 39 proposes a comment post for a specific trend, it proposes auxiliary information for assisting the comment post for the specific trend based on the already-posted comments for the specific trend. The auxiliary information is, for example, summary data of the already-posted comments or list data obtained by extracting and listing words related to a specific trend from the already-posted comments.

[0099] In addition, when the number of comments for each trend is balanced and there is a trend in which the number of comments whose comment content satisfies a predetermined content condition is equal to or greater than a predetermined number, the proposal unit 39 proposes a comment post for that trend. That is, when the number of comments for each trend can ensure a certain number, but there are many comments with inappropriate comment content for a specific trend, the proposal unit 39 proposes a comment post for the specific trend. Specifically, when a predetermined number or more of comments have already been collected for the trend of the posted comments, the proposal unit 39 proposes a comment post for a trend with the number of comments less than a predetermined number.

[0100] The providing unit 40 provides various types of information to the user. For example, when the classification result by the classification unit 34 satisfies a predetermined condition, the providing unit 40 provides comments on each tendency. Specifically, the providing unit 40 assumes that when the tendency in which the comments are classified among a plurality of preset tendencies is equal to or more than a predetermined number, it satisfies the predetermined condition, and provides the posted comments of each tendency collectively. Also, after the providing unit 40 collectively provides the comments, it resets the classification result, re-classifies the newly posted comments, and when the above-mentioned predetermined condition is satisfied, provides the comments of each newly posted tendency collectively. That is, the providing unit 40 collectively provides the comments of each tendency each time the classification result satisfies a predetermined condition.

[0101] The comments to be provided may be all the comments of each tendency, or for a tendency in which there are a predetermined number or more of comments, one or more representative comments may be selected from among the predetermined number or more of comments. The providing unit 40 may select, for example, based on the posting history of the posting user such as giving priority to the comments of the posting user with a large number of past comment postings, or may simply select randomly.

[0102] Also, the providing unit 40 may select representative comments based on the similarity of the attribute information between the posting user and the browsing user. Specifically, the providing unit 40 selects the comments posted by the posting user with a high similarity to the attribute information of the browsing user as the representative comments.

[0103] Also, the providing unit 40 provides comments of a tendency different from the said tendency to the browsing user who has browsed the comments of any tendency classified by the classification unit 34. Also, the providing unit 40 provides comments corresponding to user information different from the said user information to the browsing user who has browsed the comments corresponding to any user information classified by the classification unit 34.

[0104] For example, the providing unit 40 converts each tendency (or each user information) into a distributed representation, and in the distributed representation space, provides a comment with a tendency (or user information) that is farthest from the tendency (or user information) of the comment viewed by the browsing user. Further, the providing unit 40 may provide comments with a plurality of tendencies (or user information) that are separated from the tendency (or user information) of the comment viewed by the browsing user by a predetermined distance or more. Further, when the number of comments with the tendency to be provided is equal to or greater than a predetermined number, the providing unit 40 may select representative comments by the above method.

[0105] Further, the providing unit 40 provides a comment with a tendency different from the tendency of the comment posted by the posting user to the posting user. That is, the providing unit 40 provides a comment with a tendency different from the tendency corresponding to the posting user specified by the specifying unit 33 based on the action history of the posting user to the posting user.

[0106] For example, the providing unit 40 makes the comment with the tendency corresponding to the posting user non-displayed and displays a comment with a tendency different from the tendency. Further, the providing unit 40 places the display order of the comment with a tendency different from the tendency higher than that of the comment with the tendency corresponding to the posting user.

[0107] Further, the providing unit 40 displays the comment with the tendency corresponding to the posting user and the comment with a tendency different from the tendency in different display modes. The display mode is, for example, the background color, the character color, the character underline, the character font, the character size, etc.

[0108] Further, the providing unit 40 provides information on other comments that satisfy (are inappropriate) a predetermined condition detected by the detecting unit 37 to, for example, an administrator who manages the content (or comment).

[0109] Next, with reference to FIGS. 7 to 10, the processing procedures of Processing 1 to Processing 4 executed by the information processing apparatus 1 according to the embodiment will be described. FIGS. 7 to 10 are flowcharts showing the processing procedures of Processing 1 to Processing 4 executed by the information processing apparatus 1 according to the embodiment.

[0110] First, with reference to FIG. 7, Process 1 will be described. As shown in FIG. 7, the control unit 3 first distributes content to the user terminal 100 (step S101).

[0111] Subsequently, the control unit 3 receives the user's comments on the distributed content (step S102).

[0112] Subsequently, the control unit 3 identifies the trend of the comment content (step S103).

[0113] Subsequently, the control unit 3 classifies the comments according to the identified trends (step S104).

[0114] Subsequently, the control unit 3 determines whether the identified trend is similar to the trend of the posted comments in which the number of posts of the identified trend is equal to or greater than a predetermined number (step S105).

[0115] If the identified trend is not similar to the trend of the posted comments in which the number of posts of the identified trend is equal to or greater than a predetermined number (step S105: No), the control unit 3 determines whether the classification result satisfies a predetermined condition (step S106).

[0116] If the classification result satisfies a predetermined condition (step S106: Yes), the control unit 3 summarizes the comments of each trend and provides them to the user (step S107), and ends the process.

[0117] On the other hand, if the classification result does not satisfy a predetermined condition (step S106: No), the control unit 3 ends the process without providing the comments.

[0118] Also, in step S105, if the identified trend is similar to the trend of the posted comments in which the number of posts of the identified trend is equal to or greater than a predetermined number (step S105: Yes), the control unit 3 notifies the user that comment posting is not allowed, or proposes posting comments of other trends (step S108), and ends the process.

[0119] Next, with reference to FIG. 8, Process 2 will be described. As shown in FIG. 8, the control unit 3 collects evaluation information indicating the evaluation of the comment (step S201).

[0120] Subsequently, the control unit 3 determines the diversity of the evaluation based on the collected evaluation information (step S202).

[0121] Subsequently, the control unit 3 determines the comment to be displayed based on the determination result (step S203).

[0122] Subsequently, the control unit 3 provides the determined comment to the user (step S204) and ends the process.

[0123] Next, with reference to FIG. 9, Process 3 will be described. As shown in FIG. 9, the control unit 3 collects each comment of the user on the content (step S301).

[0124] Subsequently, the control unit 3 extracts comments whose comment content satisfies a predetermined content condition (step S302).

[0125] Subsequently, the control unit 3 identifies the users who agreed with the extracted comments (step S303).

[0126] Subsequently, the control unit 3 detects other comments based on the agreement status of the identified users with other comments (step S304) and ends the process.

[0127] Next, with reference to FIG. 10, Process 4 will be described. As shown in FIG. 10, the control unit 3 classifies each comment according to the tendency of the comment content (or user information) (step S401).

[0128] Subsequently, the control unit 3 identifies the tendency (user information) of the comments viewed by the browsing user (step S402).

[0129] Subsequently, the control unit 3 extracts comments on a tendency (or user information) different from the specified tendency (or user information) (step S403).

[0130] Subsequently, the control unit 3 provides the extracted comments to the user (step S404) and ends the process.

[0131] 〔Others〕 Also, among the processes described in the above embodiment, some of the processes described as being automatically performed can be manually performed. Alternatively, all or part of the processes described as being manually performed can be automatically performed by a known method. In addition, regarding the process procedures, specific names, and information including various data and parameters shown in the above documents and drawings, they can be arbitrarily changed unless otherwise specified. For example, the various information shown in each figure is not limited to the illustrated information.

[0132] Also, each component of each device shown in the drawings is a functional concept and does not necessarily have to be physically configured as shown in the drawings. That is, the specific form of the distribution and integration of each device is not limited to that shown in the drawings, and all or part of it can be functionally or physically distributed and integrated in any unit according to various loads, usage situations, etc.

[0133] For example, part or all of the storage unit 4 shown in FIG. 3 may be held not by each device but by a storage server or the like. In this case, each device acquires various information by accessing the storage server.

[0134] 〔Hardware Configuration〕 Further, the information processing apparatus 1 according to the above-described embodiment is realized by a computer 1000 configured as shown in FIG. 11, for example. FIG. 11 is a diagram showing an example of a hardware configuration. The computer 1000 is connected to an output device 1010 and an input device 1020, and has a configuration in which an arithmetic unit 1030, a primary storage device 1040, a secondary storage device 1050, an output IF (Interface) 1060, an input IF 1070, and a network IF 1080 are connected by a bus 1090.

[0135] The arithmetic unit 1030 operates based on programs stored in the primary storage device 1040 and the secondary storage device 1050, programs read from the input device 1020, etc., and executes various processes. The primary storage device 1040 is a memory device that temporarily stores data used by the arithmetic unit 1030 for various operations, such as a RAM. Further, the secondary storage device 1050 is a storage device in which data used by the arithmetic unit 1030 for various operations and various databases are registered, and is realized by a ROM (Read Only Memory), an HDD (Hard Disk Drive), a flash memory, etc.

[0136] The output IF 1060 is an interface for transmitting information to be output to an output device 1010 that outputs various types of information, such as a monitor and a printer, and is realized by a connector of a standard such as USB (Universal Serial Bus), DVI (Digital Visual Interface), HDMI (registered trademark) (High Definition Multimedia Interface). Further, the input IF 1070 is an interface for receiving information from various input devices 1020, such as a mouse, a keyboard, and a scanner, and is realized by, for example, USB or the like.

[0137] Note that the input device 1020 may be a device that reads information from, for example, an optical recording medium such as a CD (Compact Disc), 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. Further, the input device 1020 may be an external storage medium such as a USB memory.

[0138] The network IF 1080 receives data from other devices via the network N and sends it to the arithmetic unit 1030, and also sends the data generated by the arithmetic unit 1030 via the network N to other devices.

[0139] The arithmetic unit 1030 controls the output device 1010 and the input device 1020 via the output IF 1060 and the input IF 1070. For example, the arithmetic unit 1030 loads a program from the input device 1020 or the secondary storage device 1050 onto the primary storage device 1040 and executes the loaded program.

[0140] For example, when the computer 1000 functions as the information processing apparatus 1, the arithmetic unit 1030 of the computer 1000 realizes the function of the control unit 3 by executing the program loaded onto the primary storage device 1040.

[0141] 〔Effect〕 As described above, the information processing apparatus 1 according to the embodiment includes a classification unit 34 and a providing unit 40. The classification unit 34 classifies each comment posted for a predetermined content according to the tendency of the comment content. The providing unit 40 provides the comments of each tendency when the classification result satisfies a predetermined condition.

[0142] Further, the information processing apparatus 1 according to the embodiment includes a specifying unit 33, a determining unit 35, and a reception control unit 38. The specifying unit 33 specifies a tendency of comment contents in a comment posted for a predetermined content and input by a user. The determining unit 35 determines whether or not the tendency of the specified comment satisfies a condition based on the tendency of already-posted comments. The reception control unit 38 performs control to avoid reception of the comment based on the determination result.

[0143] Further, the information processing apparatus 1 according to the embodiment includes an acquisition unit 32, a determining unit 35, and a decision unit 36. The acquisition unit 32 acquires evaluation information indicating an evaluation of a comment posted for a predetermined content. The determining unit 35 determines the diversity of the evaluation based on the acquired evaluation information. The decision unit 36 determines whether or not to display the comment based on the determination result.

[0144] Further, the information processing apparatus 1 according to the embodiment includes a classification unit 34 and a providing unit 40. The classification unit 34 classifies each comment posted for a predetermined content according to the tendency of the comment content. The providing unit 40 provides a comment having a tendency different from the tendency of the comment browsed by a browsing user who has browsed a comment having any of the classified tendencies.

[0145] Further, the information processing apparatus 1 according to the embodiment includes a classification unit 34 and a providing unit 40. The classification unit 34 classifies each comment posted by a posting user for a predetermined content according to the user information of the posting user. The providing unit 40 provides a comment corresponding to user information different from the user information to a browsing user who has browsed a comment corresponding to any of the classified user information.

[0146] Further, the information processing apparatus 1 according to the embodiment includes a classification unit 34, a specifying unit 33, and a providing unit 40. The classification unit 34 classifies each comment posted for a predetermined content according to the tendency of the comment content. The specifying unit 33 specifies the tendency corresponding to the user among the classified tendencies based on the user's behavior history regarding the comment. The providing unit 40 provides the user with comments having a tendency different from the specified tendency.

[0147] Also, the information processing apparatus 1 according to the embodiment includes a specifying unit 33 and a detecting unit 37. The specifying unit 33 specifies a user who has agreed to a comment whose comment content satisfies a predetermined content condition. The detecting unit 37 detects other comments whose comment content satisfies a predetermined condition based on the consent status of the specified user to other comments.

[0148] Further, the information processing apparatus 1 according to the embodiment includes a classification unit 34 and a proposing unit 39. The classification unit 34 classifies each comment posted for a predetermined content according to the tendency of the comment content. The proposing unit 39 compares the comment status for each classified tendency and proposes posting of a comment based on the comparison result.

[0149] According to the information processing apparatus 1 according to each of the above-described embodiments, the quality of the service related to comments can be improved.

[0150] As described above, some of the embodiments of the present application have been described in detail based on the drawings. However, these are examples, and the present invention can be implemented in other forms obtained by making various modifications and improvements based on the knowledge of those skilled in the art, including the aspects described in the column of the disclosure of the invention.

[0151] 〔Others〕 In addition, among the processes described in the above embodiments, all or part of the processes described as being automatically performed can be manually performed, or all or part of the processes described as being manually performed 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 above documents and drawings can be arbitrarily changed unless otherwise specified. For example, the various information shown in each figure is not limited to the illustrated information.

[0152] In addition, each component of each device shown in the drawings is conceptually functional and does not necessarily have to be physically configured as shown in the drawings. That is, the specific form of the distribution and integration of each device is not limited to that shown in the drawings, and all or part of it can be functionally or physically distributed and integrated in any unit according to various loads, usage situations, etc.

[0153] In addition, the processes described in the above-described embodiments can be appropriately combined as long as the processing contents do not conflict.

[0154] In addition, the above-mentioned "section, module, unit" can be read as "means", "circuit", etc. For example, the control unit 3 can be read as a control means or a control circuit.

Explanation of Reference Numerals

[0155] 1 Information processing apparatus 2 Communication unit 3 Control unit 4 Storage unit 31 Distribution unit 32 Acquisition unit 33 Identification unit 34 Classification unit 35 Judgment unit 36 Decision unit 37 Detection unit 38 Reception control unit 39 Proposal unit 40 Provision unit 41 User information 42 Content information 43 Comment information 100 User terminal 200 Requesting source terminal S Information processing system

Claims

1. A classification unit that classifies each comment posted for a given content according to the tendency of the comment content, A providing unit that provides the comments of each tendency when the classification result satisfies a predetermined condition, A proposing unit that proposes posting of the comments related to the tendency with less than a predetermined number of comments when a predetermined number or more of the comments have already been collected for the tendency of the posted comments An information processing apparatus comprising the same.

2. The classification unit classifies each comment into any one of a plurality of preset tendencies, The providing unit collects and provides the comments of each tendency on the assumption that the tendency into which the comment is classified satisfies a predetermined condition when the number of such tendencies is a predetermined number or more among the plurality of tendencies The information processing apparatus according to Claim 1.

3. The providing unit provides the comments of each tendency each time the classification result satisfies a predetermined condition The information processing apparatus according to Claim 1.

4. The classification unit re-sets the plurality of preset tendencies based on the classification result The information processing apparatus according to Claim 2.

5. The classification unit sub-divides a specific tendency among the plurality of tendencies based on the comments when the number of comments classified into the specific tendency is a predetermined value or more The information processing apparatus according to Claim 4.

6. The providing unit selects and provides a representative comment for each tendency for each of the comments to be provided The information processing apparatus according to Claim 1.

7. The providing unit selects the representative comment based on the posting history of the posting user who posted the comment The information processing apparatus according to Claim 6.

8. The providing unit selects the representative comment based on the attribute information of the posting user who posted the comment and the browsing user who browses the comment The information processing apparatus according to Claim 6.

9. An information processing method executed by a computer, comprising: a classification step of classifying each comment posted for a given content according to the tendency of the comment content; a providing step of providing the comments of each tendency when the classification result satisfies a predetermined condition; a proposing step of proposing posting of the comments related to the tendency with less than a predetermined number of comments when a predetermined number or more of the comments have already been collected for the tendency of the posted comments An information processing method including the same.

10. A classification procedure for classifying each comment posted for a given content according to the tendency of the comment content, and A provision procedure for providing the comments of each tendency when the classification result satisfies a predetermined condition, and A proposal procedure for proposing to post comments regarding a tendency with a comment count less than a predetermined number when a predetermined number or more of the comments have already been collected for the tendency of the posted comments An information processing program for causing a computer to execute.

Images