Information processing device, information processing method, and information processing program

Abstract

To provide information that is useful for evaluating content. [Solution] The information processing device comprises a content selection unit, a comment collection unit, a persona generation unit, and an information output unit. The content selection unit selects target content from among multiple contents published on the internet. The comment collection unit collects one or more comments posted by one or more viewers for the selected target content. The persona generation unit generates one or more personas representing the one or more viewers who posted the one or more target comments based on the collected one or more target comments, and obtains one or more persona information, which is information indicating the one or more generated personas. The information output unit outputs the obtained one or more persona information.

Description

Technical Field

[0007] , , , ,

[0004] ,

[0006] , , , , , ,

[0005] , , ,

[0003] , , , , , , ,

[0001] This disclosure relates to an information processing apparatus.

Background Art

[0002] Patent Document 1 describes a comment evaluation system that collects comments on video content distributed by a video distribution server, aggregates positive comments and negative comments respectively, and determines an evaluation of the video content based on the aggregation results.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In content published for promoting the sale of a product or service, there is a problem that it may be difficult to evaluate whether the content was effective in promoting sales based solely on an evaluation of whether the comments are positive or not.

[0005] An object of this disclosure is to provide information effective for evaluating content.

Means for Solving the Problems

[0006] One aspect of this disclosure is an information processing apparatus including a content selection unit, a comment collection unit, a persona image generation unit, and an information output unit. The content selection unit is configured to select target content, which is the target content among a plurality of contents published on the Internet.

[0007] The comment collection unit is configured to collect one or more comments posted by one or more viewers for the target content selected by the content selection unit. The persona generation unit is configured to generate one or more personas representing one or more viewers who posted one or more target comments, based on one or more comments collected by the comment collection unit, and to acquire one or more persona information, which is information indicating the generated one or more personas.

[0008] The information output unit is configured to output one or more persona image information acquired by the persona image generation unit. The information processing device of this disclosure, configured in this manner, can provide its users with persona information that shows the persona of viewers who post comments on the target content. This allows the information processing device to enable its users to evaluate, based on the persona, whether the target content is being viewed by the customers the user is targeting. Therefore, the information processing device of this disclosure can provide information that is effective for evaluating content.

[0009] In one aspect of this disclosure, a comment classification unit may be configured to classify one or more target comments collected by a comment collection unit into at least several groups, including an affirmative group that is positive towards the target content and a negative group that is negative towards the target content, using a sentiment analyzer. In one aspect of this disclosure, a persona generation unit may be configured to cause artificial intelligence to generate one or more personas as one or more affirmative personas based on one or more target comments classified into the affirmative group, and to cause artificial intelligence to generate one or more personas as one or more negative personas based on one or more target comments classified into the negative group.

[0010] As a result, the information processing device disclosed herein can provide users of the information processing device with personas of viewers who post positive comments on the target content and personas of viewers who post negative comments on the target content.

[0011] In one aspect of this disclosure, the comment classification unit may be configured to use a sentiment analyzer to calculate a positive confidence score indicating the probability that a target comment is positive for each of the one or more target comments classified in the positive group, and to calculate a negative confidence score indicating the probability that a target comment is negative for each of the one or more target comments classified in the negative group. In one aspect of this disclosure, the comment display unit may be configured to display one or more positive comments in association with the corresponding one or more positive confidence scores, and to display one or more negative comments in association with the corresponding one or more negative confidence scores.

[0012] As a result, the information processing device of this disclosure can provide the user of the information processing device with the content and confidence level of positive comments used to generate a positive persona image, and the content and confidence level of negative comments used to generate a negative persona image. Therefore, the user of the information processing device can evaluate the confidence level of the positive persona image and the negative persona image generated by artificial intelligence based on the content and confidence level of positive comments and the content and confidence level of negative comments used to generate a negative persona image.

[0013] In one aspect of this disclosure, the system may include a comment generation unit configured to cause artificial intelligence to generate persona comments, which are comments posted by viewers corresponding to a persona to the target content, for at least one persona generated by artificial intelligence.

[0014] As a result, the information processing device disclosed herein can provide its users with persona comments, which are comments posted by viewers corresponding to a persona to the target content. Therefore, the users of the information processing device can further evaluate, based on the persona comments, whether or not the customers targeted by the user are viewing the target content.

[0015] Another aspect of this disclosure is an information processing method performed by an information processing device. In the information processing method of this disclosure, the information processing device selects target content from among multiple contents published on the internet, collects one or more comments posted by one or more viewers to the selected target content, has artificial intelligence generate one or more persona images representing one or more viewers who posted one or more target comments based on the collected one or more comments, obtains one or more persona image information which is information indicating the generated one or more persona images, and outputs the obtained one or more persona image information.

[0016] The information processing method disclosed herein is a method executed by the information processing device disclosed herein, and by executing this method, the same effects as those of the information processing device disclosed herein can be obtained. Another aspect of this disclosure is an information processing program for causing a computer to function as a content selection unit, a comment collection unit, a persona image generation unit, and an information output unit.

[0017] A computer of an information processing device controlled by the information processing program of this disclosure can constitute a part of the information processing device of this disclosure and can achieve the same effects as the information processing device of this disclosure. [Brief explanation of the drawing]

[0018] [Figure 1] This is a block diagram showing the configuration of the comment analysis system. [Figure 2] It is a flowchart showing the comment analysis process of the first embodiment. [Figure 3] It is a diagram showing an example of a comment group of the first embodiment. [Figure 4] It is a diagram showing a specific example of a prompt. [Figure 5] It is a diagram showing a specific example of a persona image answer in the first embodiment. [Figure 6] It is a diagram showing a specific example of result display in the first embodiment. [Figure 7] It is a flowchart showing the comment analysis process of the second embodiment. [Figure 8] It is a diagram showing an example of a comment group of the second embodiment. [Figure 9] It is a diagram showing a first specific example of a classification result in the second embodiment. [Figure 10] It is a diagram showing a second specific example of a classification result in the second embodiment. [Figure 11] It is a diagram showing a first specific example of a persona image answer in the second embodiment. [Figure 12] It is a diagram showing a second specific example of a persona image answer in the second embodiment. [Figure 13] It is a diagram showing a first specific example of result display in the second embodiment. [Figure 14] It is a diagram showing a second specific example of result display in the second embodiment.

Mode for Carrying Out the Invention

[0019] [1. First Embodiment] The first embodiment of the present disclosure will be described below with reference to the drawings. [1-1. Configuration] As shown in FIG. 1, the comment analysis system 1 of the present embodiment includes an information processing device 2, a video distribution server 3, and an AI server 4. AI is an abbreviation for Artificial Intelligence.

[0020] The information processing device 2 comprises a control unit 21, a communication unit 22, a storage unit 23, a display unit 24, and an operation input unit 25. The control unit 21 is an electronic control unit centered around a microcomputer equipped with a CPU 211, ROM 212, RAM 213, etc. The various functions of the microcomputer are realized by the CPU 211 executing a program stored in a non-transitional physical recording medium. In this example, ROM 212 corresponds to the non-transitional physical recording medium that stores the program. Furthermore, the execution of this program executes the method corresponding to the program. Note that some or all of the functions performed by the CPU 211 may be configured hardware-wise by one or more ICs, etc. Also, the number of microcomputers constituting the control unit 21 may be one or more.

[0021] The communications unit 22 performs data communication with the video distribution server 3 and the AI ​​server 4 via the wide-area communication network NW. The memory unit 23 is a storage device for storing various types of data. The memory unit 23 stores a comment analysis program 231 for executing the comment analysis process described later.

[0022] The display unit 24 is a display device that displays various images on the display screen. The operation input unit 25 is equipped with a keyboard and a mouse. The operation input unit 25 outputs input operation information to identify the input operations performed by the user via the keyboard and mouse.

[0023] Video distribution server 3 is a server for providing video distribution services that deliver video content over the internet. An example of such a service is YouTube. YouTube is a registered trademark.

[0024] Users of the video streaming service can post video content by accessing the video streaming server 3 using their information terminal and uploading the video content they have created to the video streaming server 3.

[0025] The video distribution server 3 stores the uploaded video content in a database located within the video distribution server 3, associating it with video identification information used to identify the video content. Video distribution server 3 publishes multiple video content uploaded to video distribution server 3 to the internet.

[0026] Users of the video streaming service can access the video streaming server 3 using their information terminal and select video content from the many video contents made available by the video streaming server 3, thereby viewing their desired video content in streaming format.

[0027] Users of video streaming services can post comments on the video content they are watching using their personal devices. The video distribution server 3 can display submitted comments, along with user identification information that identifies the user who submitted the comment, within a comment display area located on the web page displaying the corresponding video content. In other words, the video distribution server 3 stores one or more comments on video content in a database provided within the video distribution server 3, associating them with the video identification information of the corresponding video content.

[0028] AI Server 4 is equipped with artificial intelligence 41. Artificial intelligence 41 is a generative AI that uses a large-scale language model. Examples of generative AIs include ChatGPT and Gemini. The large-scale language model has the ability to understand and generate text by learning from a large amount of text data using deep learning technology.

[0029] Therefore, the artificial intelligence 41 is configured to generate and output a text response in text format when a prompt representing specific instructions in text format is input.

[0030] [1-2. Processing] Next, the procedure for the comment analysis process performed by the information processing device 2 will be explained. The comment analysis process is performed by activating the comment analysis program 231 based on input from the user of the information processing device 2.

[0031] When the comment analysis process is executed, the CPU 211 of the control unit 21 determines in S10, as shown in Figure 2, whether or not video identification information for identifying the video content to be collected from comments has been input to the control unit 21 via the operation input unit 25.

[0032] If video identification information is not entered, the process in S10 is repeated until video identification information is entered. Once video identification information is entered, CPU 211 collects all comments posted to the video content identified by the video identification information entered in S10 from video distribution server 3 in S20. For example, if the video distribution service provided by video distribution server 3 is YouTube, CPU 211 can obtain comments posted to a specific video content from video distribution server 3 by sending an API request using a programming language such as Python with the YouTube Data API. API stands for Application Programming Interface.

[0033] Figure 3 shows an example of a group of comments collected from the video distribution server 3 by processing in S20. Figure 3 shows multiple viewer comments on video content created through a collaboration between an influencer named "NNNNN" and a company called "BBBB".

[0034] Once processing in S20 is complete, CPU 211, as shown in Figure 2, creates a prompt in S30 (hereinafter referred to as the persona generation prompt) that instructs the system to generate persona profiles of viewers who posted comments based on the comments collected in S20, and sends the created persona generation prompt to AI server 4.

[0035] In this embodiment, the persona refers to a typical user who uses the product or service. As shown in Figure 4, the persona generation prompt in this embodiment is written in English using a programming language such as Python.

[0036] The role of the generated AI is described by the instruction C1 that follows "role": "system", "content": written within the rectangle R1 indicated by the dashed line. The instructions C2-C4 following "role: "user", "content": f""" written within the dashed rectangle R2, and the instructions C5-C10 following "role: "user", "content":" written within the dashed rectangle R3, describe specific instructions for the generated AI.

[0037] Instruction C2 states, "The following text and keywords reflect consumer comments on a collaboration video created by an influencer and featuring {client}." {client} in instruction C2 should be replaced with the company name corresponding to "NNNNN" above.

[0038] Instruction C3 states, "Summarize your impression of the PR product based on these comments." Instruction C4 states, "Furthermore, create three personas with different personalities, and based on the information from the comments, generate each persona's impression of {client} after watching the collaboration video." {client} in instruction C4 is set to the company name corresponding to "NNNNN" mentioned above.

[0039] Instruction C5 states, "There is a topic that contains the following document {''.join(text)} which is a comment posted by a video viewer." {''.join(text)} in instruction C5 is a function that concatenates strings defined by text. In this embodiment, text represents the group of comments collected from the video distribution server 3 by the processing in S20.

[0040] Instruction C6 states, "Please answer in Japanese." Instruction C7 states, "Based on the keywords in the comments, estimate the age, gender, and personality of the video viewers in order to generate three personas."

[0041] Instruction C8 states, "If there are few comments, and it is difficult to generate a persona and impression, output 'Results cannot be generated due to insufficient comments.'"

[0042] Instruction C9 states, "Generate user impressions of the PR product in the form of comments based on a persona." Instruction C10 states, "Please generate an answer based on the following example sentences. The following sentences are merely examples, and the content will be generated solely from comments posted by video viewers."

[0043] The text within rectangle R4, indicated by the dashed line, specifies the output format for the summary of the impression of the PR product and the three persona profiles. Once the processing in S30 is complete, the CPU 211 retrieves the response output from the artificial intelligence 41 of the AI ​​server 4 (hereinafter referred to as the persona response) in S40, as shown in Figure 2.

[0044] Figure 5 shows an example of a persona profile response output by artificial intelligence 41. In the persona responses shown in Figure 5, along with a description of the "overview of the PR product," age, gender, personality, and user feedback are included for each of the first, second, and third personas.

[0045] Once the processing in S40 is complete, the CPU 211 displays the persona profile responses obtained in S40 on the display screen of the display unit 24 in S50, as shown in Figure 2, and then terminates the comment analysis process.

[0046] Figure 6 shows an example of the display of the response output by the artificial intelligence 41. Figure 6 shows the state in which the thumbnail of the video content identified by the video identification information input in S10, along with the age, gender, personality, and user voice of the first, second, and third persona profiles, are displayed on the display screen of the display unit 24.

[0047] [1-3. Effects] According to the embodiments described above, the following effects can be obtained. (1a) The information processing device 2 configured in this way can provide its users with persona information that shows the persona of a viewer who posts comments on a video content selected from among multiple video contents published on the internet (hereinafter referred to as the target content). This allows the information processing device 2 to enable its users to evaluate, based on the persona, whether or not the target content is being viewed by the customers targeted by the information processing device 2. Therefore, the information processing device 2 can provide information that is effective for evaluating the content.

[0048] (1b) The information processing device 2 can provide users of the information processing device 2 with comments posted by viewers corresponding to the persona profile on the target content (hereinafter referred to as persona profile comments). Therefore, users of the information processing device 2 can further evaluate, based on the persona profile comments, whether or not the target content is being viewed by customers targeted by the user of the information processing device 2.

[0049] [1-4. Correspondence of Terms] In the embodiments described above, S10 corresponds to processing as a content selection unit, S20 corresponds to processing as a comment collection unit, S30 and S40 correspond to processing as a persona image generation unit and a comment generation unit, and S50 corresponds to processing as an information output unit.

[0050] Furthermore, video content corresponds to content, the display example shown in Figure 6 corresponds to persona profile information, user voices correspond to persona profile comments, and the comment analysis program 231 corresponds to an information processing program.

[0051] [2. Second Embodiment] A second embodiment of this disclosure is described below with reference to the drawings. Note that the second embodiment will describe parts that differ from the first embodiment. Common components will be denoted by the same reference numerals.

[0052] The comment analysis system 1 of the second embodiment differs from the first embodiment in that the comment analysis process has been modified. [2-1. Processing] Next, the procedure for the comment analysis process in the second embodiment will be described.

[0053] When the comment analysis process of the second embodiment is executed, the CPU 211 of the control unit 21 determines in S110, as shown in Figure 7, whether or not video identification information for identifying the video content to be collected for comment analysis has been input to the control unit 21 via the operation input unit 25.

[0054] If no video identification information is entered, the process in S110 is repeated until the video identification information is entered. Once the video identification information is entered, the CPU 211, in S120, collects all comments posted to the video content identified by the video identification information entered in S110 from the video distribution server 3.

[0055] Figure 8 shows an example of a group of comments collected from the video distribution server 3 by the processing in S120. Figure 8 shows multiple viewer comments on video content created through a collaboration between a group called "KKK," which includes several influencers, and a service provided by a company called "JJJJ."

[0056] Once processing in S120 is complete, CPU 211, in S130 as shown in Figure 7, classifies the comments collected in S120 into positive, negative, or neutral categories for the video content using a Japanese sentiment analyzer. The Japanese sentiment analyzer is a machine learning model that extracts and analyzes emotions from text data and is installed in the information processing device 2.

[0057] Figure 9 shows the results of classifying positive comments on video content. For each of the multiple positive comments, Figure 9 associates the comment content with a "label," "score," and "ID."

[0058] The "label" can be set to either "positive," "negative," or "neutral." As all the comments shown in Figure 9 are positive, the "label" is set to "positive" for all of them.

[0059] The "Score" indicates the confidence level (hereinafter referred to as "positive confidence") of the Japanese sentiment analyzer's determination that a comment is positive. The positive confidence level indicates the probability that the corresponding comment is positive. The positive confidence level can be set to a value from 0 to 1. 0 is the lowest confidence level, and 1 is the highest confidence level.

[0060] "Id" is the video identification information for the target video content. Figure 10 shows the results of classifying negative comments on video content. For each of the multiple negative comments in Figure 10, the content of the comment, the "label," the "score," and the "Id" are associated.

[0061] As shown in Figure 10, all comments are negative, and therefore the "label" is set to "negative" for all of them. The "Score" indicates the confidence level (hereinafter referred to as "negative confidence") of the Japanese sentiment analyzer's determination that a comment is negative. Negative confidence indicates the probability that the corresponding comment is negative. Negative confidence can be set to a value from 0 to 1. 0 is the lowest confidence level, and 1 is the highest confidence level.

[0062] Once processing in S130 is complete, CPU 211, as shown in Figure 7, creates a persona generation prompt in S140 that instructs the system to generate persona profiles of viewers who posted comments based on each group of comments classified as "positive" or "negative" in S130, and sends the created persona generation prompt to AI server 4.

[0063] CPU211 retrieves the persona image response output by AI Server 4's artificial intelligence 41 in S150. Figure 11 shows an example of a persona response output by artificial intelligence 41 based on a group of comments classified as "positive." In the persona response shown in Figure 11, along with a description of the "overview of the PR product," age, gender, personality, and user feedback are included for each of the first, second, and third personas.

[0064] Figure 12 shows an example of a persona profile response output by artificial intelligence 41 based on a group of comments classified as "negative." In the response shown in Figure 12, along with a description of the "overview of the PR product," the age, gender, personality, and user comments are included for each of the first, second, and third personas.

[0065] When the processing in S150 is completed, the CPU 211 displays the classification results classified in S130 and the persona image responses obtained in S160 on the display screen of the display unit 24, as shown in Figure 7, and then terminates the comment analysis process.

[0066] Figure 13 shows an example of a persona display generated based on a group of comments classified as "positive." Figure 13 shows the thumbnail image of the video content identified by the video identification information input in S110, the notation "positive" indicating that the comment is positive, and the age, gender, personality, and user voice of the first, second, and third personas, respectively, displayed on the display screen of the display unit 24.

[0067] Figure 14 shows an example of how comments are categorized as "positive," "negative," and "neutral." Figure 14 shows a state that includes a first display area D1 containing video identification information, video title and thumbnail image, a second display area D2 showing the ratio of "positive" and "negative" comments, a third display area D3 illustrating positive comments, a fourth display area D4 illustrating neutral comments, and a fifth display area D5 illustrating negative comments.

[0068] [2-2. Effects] According to the embodiments described above, the following effects can be obtained. (2a) The information processing device 2 configured in this way can provide users of the information processing device 2 with a persona of a viewer who posts positive comments on the target content (hereinafter referred to as the positive persona) and a persona of a viewer who posts negative comments on the target content (hereinafter referred to as the negative persona).

[0069] (2b) The information processing device 2 can provide the user of the information processing device 2 with the content and confidence level of positive comments used to generate a positive persona image, and the content and confidence level of negative comments used to generate a negative persona image. Therefore, the user of the information processing device 2 can evaluate the confidence level of the positive persona image and the negative persona image generated by the artificial intelligence 41 based on the content and confidence level of positive comments and the content and confidence level of negative comments used to generate a negative persona image.

[0070] [2-3. Correspondence of Terms] In the embodiments described above, S110 corresponds to processing as a content selection unit, S120 corresponds to processing as a comment collection unit, S140 and S150 correspond to processing as a persona image generation unit, and S160 corresponds to processing as an information output unit.

[0071] Furthermore, S130 corresponds to processing as a comment classification unit, the group of comments shown in Figure 9 corresponds to the positive group, the group of comments shown in Figure 10 corresponds to the negative group, and S160 corresponds to processing as a comment display unit.

[0072] [3. Other Embodiments] Although one embodiment of the present disclosure has been described above, the present disclosure is not limited to the above embodiment and can be implemented in various modified forms.

[0073] (3a) The above embodiment shows a method for generating a persona based on comments posted to video content. However, the target content is not limited to video content, but can include at least one of text, still images, and videos. Examples of platforms on which content including at least one of text, still images, and videos can be published on the internet include Instagram, LINE, Facebook, and X (formerly Twitter). Instagram is a registered trademark. LINE is a registered trademark. Facebook is a registered trademark. Twitter is a registered trademark.

[0074] (3b) In the above embodiment, the artificial intelligence 41 installed on the AI ​​server 4 is shown to generate the persona image. However, the artificial intelligence for generating the persona image may be installed on the information processing device 2.

[0075] The control unit 21 and its method described herein may be implemented by a dedicated computer provided by configuring a processor and memory programmed to perform one or more functions embodied by a computer program. Alternatively, the control unit 21 and its method described herein may be implemented by a dedicated computer provided by configuring a processor by one or more dedicated hardware logic circuits. Alternatively, the control unit 21 and its method described herein may be implemented by one or more dedicated computers configured by a combination of a processor and memory programmed to perform one or more functions and a processor configured by one or more hardware logic circuits. Furthermore, the computer program may be stored as instructions executed by the computer on a computer-readable non-transitional tangible recording medium. The method for implementing the functions of each part included in the control unit 21 does not necessarily need to include software, and all of its functions may be implemented using one or more hardware components.

[0076] Multiple functions of one component in the above embodiment may be realized by multiple components, or one function of one component may be realized by multiple components. Furthermore, multiple functions of multiple components may be realized by one component, or one function realized by multiple components may be realized by one component. Also, some parts of the configuration of the above embodiment may be omitted. Furthermore, at least some parts of the configuration of the above embodiment may be added to or replaced with the configuration of other above embodiments.

[0077] In addition to the information processing device 2 described above, this disclosure can also be realized in various forms, such as a system comprising the information processing device 2, a program for causing a computer to function as the information processing device 2, a non-transitional physical recording medium such as a semiconductor memory on which this program is recorded, and an information processing method. [Explanation of Symbols]

[0078] 2... Information processing device, 41... Artificial intelligence, 231... Comment analysis program

Claims

1. A content selection unit configured to select the target content from among multiple pieces of content publicly available on the internet, A comment collection unit configured to collect one or more comments posted by one or more viewers for the target content selected by the content selection unit, A persona generation unit is configured to generate one or more persona images representing one or more viewers who posted one or more of the target comments collected by the comment collection unit, based on one or more of the target comments, and to acquire one or more persona image information which is information indicating the generated one or more persona images. An information output unit configured to output one or more pieces of persona information acquired by the persona image generation unit, The system includes a comment classification unit configured to classify one or more of the target comments collected by the comment collection unit into at least a number of groups, including an affirmative group that is positive towards the target content and a negative group that is negative towards the target content, using a sentiment analyzer. The persona image generation unit is configured to cause the artificial intelligence to generate one or more persona images as one or more positive persona images based on one or more target comments classified into the positive group, and to cause the artificial intelligence to generate one or more persona images as one or more negative persona images based on one or more target comments classified into the negative group.

2. An information processing device according to Claim 1, The comment classification unit is configured to use the sentiment analyzer to calculate a positive confidence score indicating the probability that the target comment is positive for each of the one or more target comments classified in the positive group, and to calculate a negative confidence score indicating the probability that the target comment is negative for each of the one or more target comments classified in the negative group. An information processing apparatus comprising a comment display unit configured to display one or more of the aforementioned positive comments in association with one or more of the aforementioned positive confidence levels, and to display one or more of the aforementioned negative comments in association with one or more of the aforementioned negative confidence levels.

3. A content selection unit configured to select a target content from among multiple contents published on the internet, A comment collection unit configured to collect one or more comments posted by one or more viewers for the target content selected by the content selection unit, A persona generation unit is configured to generate one or more persona images representing one or more viewers who posted one or more of the target comments collected by the comment collection unit, based on one or more of the target comments, and to acquire one or more persona image information which is information indicating the generated one or more persona images. An information output unit configured to output one or more pieces of persona information acquired by the persona image generation unit, An information processing apparatus comprising: a comment generation unit configured to cause the artificial intelligence to generate persona comments, which are comments posted by viewers corresponding to the persona image to the target content, for at least one persona image generated by the artificial intelligence.

4. An information processing method performed by an information processing device, From among multiple pieces of content publicly available on the internet, select the target content, Collect one or more comments posted by one or more viewers on the selected target content, Based on the collected one or more comments, which are one or more target comments, the artificial intelligence generates one or more persona images representing one or more viewers who posted the one or more target comments, and obtains one or more persona image information, which is information indicating the one or more generated persona images. Output one or more of the acquired persona profile information, Using a sentiment analyzer, one or more of the collected target comments are classified into multiple groups, including at least an affirmative group that is positive towards the target content and a negative group that is negative towards the target content. An information processing method that causes the artificial intelligence to generate one or more personas as one or more positive personas based on one or more target comments classified into the positive group, and causes the artificial intelligence to generate one or more personas as one or more negative personas based on one or more target comments classified into the negative group.

5. An information processing method performed by an information processing device, From among multiple pieces of content publicly available on the internet, select the target content, Collect one or more comments posted by one or more viewers on the selected target content, Based on the collected one or more comments, which are one or more target comments, the artificial intelligence generates one or more persona images representing one or more viewers who posted the one or more target comments, and obtains one or more persona image information, which is information indicating the one or more generated persona images. Output one or more of the acquired persona profile information, An information processing method that causes the artificial intelligence to generate a persona comment, which is a comment posted by the viewer corresponding to the persona to the target content, for at least one persona generated by the artificial intelligence.

6. Computers, A content selection unit configured to select the target content from among multiple pieces of content publicly available on the internet. A comment collection unit configured to collect one or more comments posted by one or more viewers for the target content selected by the content selection unit, A persona generation unit is configured to generate one or more persona images representing one or more viewers who posted one or more of the target comments collected by the comment collection unit, based on one or more of the target comments, and to acquire one or more persona image information which is information indicating the one or more persona images generated. An information output unit configured to output one or more pieces of persona information acquired by the persona image generation unit, and A comment classification unit is configured to classify one or more of the target comments collected by the comment collection unit into multiple groups, including at least an affirmative group that is positive towards the target content and a negative group that is negative towards the target content, using a sentiment analyzer. To make it function as, The persona image generation unit is an information processing program configured to cause the artificial intelligence to generate one or more persona images as one or more positive persona images based on one or more target comments classified into the positive group, and to cause the artificial intelligence to generate one or more persona images as one or more negative persona images based on one or more target comments classified into the negative group.

7. A computer, A content selection unit configured to select the target content from among multiple pieces of content publicly available on the internet. A comment collection unit configured to collect one or more comments posted by one or more viewers for the target content selected by the content selection unit, A persona generation unit is configured to generate one or more persona images representing one or more viewers who posted one or more of the target comments collected by the comment collection unit, based on one or more of the target comments, and to acquire one or more persona image information which is information indicating the one or more persona images generated. An information output unit configured to output one or more pieces of persona information acquired by the persona image generation unit, and A comment generation unit is configured to cause the artificial intelligence to generate persona comments, which are comments posted by viewers corresponding to the persona image to the target content, for at least one persona image generated by the artificial intelligence. An information processing program designed to function as such.

Images