JP6130270B2 - Comment list public server, program and method for sorting and specifying comment sets corresponding to media contents - Google Patents

Description

  The present invention relates to a technique for clearly indicating to a user a media content and a comment set posted on the media content.

  In recent years, various media contents have been released via the Internet. Media content refers to content that can be accessed by an unspecified number of third parties, such as news articles, Web pages, music content, electronic books, and television broadcast content.

  On the other hand, from the unspecified number of users to site servers such as SNS (Social Networking Service), blog (Web log), mini blog (mini Web log) (for example, twitter (registered trademark)) via the Internet A lot of comments have been posted. Such comments are often discussed on common topics. For example, a large number of comments are often posted using the media content as described above as a common topic.

  2. Description of the Related Art Conventionally, there is a technique for collecting comments on a news article published on a site using the title or URL (Uniform Resource Locator) of the news article as a search key and clearly indicating the comment set to the user (see, for example, Non-Patent Document 1) ).

  In addition, there is a technique in which a topic level of a document is set higher as there are more similar documents from a plurality of documents, and a document with a higher topic level is preferentially presented (see, for example, Patent Document 1). According to this technology, it is possible to grasp the topicality of a huge amount of information that changes from day to day, and it can be presented based on two viewpoints: similarity between documents and temporal excitement of the topic. For users who want to acquire the latest topic information from a passive standpoint, information can be acquired efficiently.

JP 2006-120069 A

“Yahoo! News”, [online], [Search August 12, 2013], Internet <URL: headlines.yahoo.co.jp>

  According to the technique described in Non-Patent Document 1, comment sets are basically only displayed in chronological order. The user needs to view and confirm a number of comments in order to find useful comments. Especially for terminals such as smartphones, mobile phones, and tablets, the display size is limited, so it is difficult to find useful comments. Here, it can be considered that a comment with a larger number of citations is more useful. However, the number of citations is often influenced by the degree of recognition of the commenter, and the content of the comment itself is not always useful.

  Further, according to the technique described in Patent Document 1, the usefulness of a document is measured by the similarity between documents. However, when the usefulness of a comment is determined based on only a single index, it may not be optimal for a certain media content for a user or for other media content. On the other hand, the inventors of the present application considered that the index for optimally displaying the comment set for the user may differ depending on the genre of the media content, the distribution source, and the distribution date and time.

  Accordingly, an object of the present invention is to provide a comment list publishing server, a program, and a method for controlling a sorting condition of a comment set related to media contents in accordance with various distribution indexes of the media contents and clearly indicating to the user. To do.

According to the present invention, there is a comment list public server that can communicate with a media server that distributes media content and a comment server that sends text comments between a plurality of contributors.
Weight coefficient storage means for assigning and storing a weight coefficient for each evaluation index element that can be extracted from the content of the comment for each distribution index element in the media content;
A distribution index extracting means for extracting a distribution index element in the media content acquired from the media server;
Comment set search means for searching a comment set related to media content from a comment server;
For each comment in the comment set obtained from the comment server, an evaluation index value extracting means for extracting the value of each evaluation index element from the content;
For each comment in the comment set for the media content, an evaluation index value updating means for multiplying the value of the evaluation index element by a weighting factor based on the distribution index element of the media content ,
And a comment sorting unit that sorts a plurality of comments based on the updated value of the evaluation index element with respect to the comment set for the media content.

According to another embodiment of the comment list public server of the present invention,
The distribution index element is preferably genre information, distribution source information, distribution date and time, or a combination of these elements in the media content.

According to another embodiment of the comment list public server of the present invention,
The evaluation index element includes the excitement element in the comment,
The value of the swell element is preferably the maximum number of the same morphemes among the plurality of morphemes included in the comment.

According to another embodiment of the comment list public server of the present invention,
It further has an emotion expression term registration means for registering in advance the emotion expression terms for each of the positive / negative / emoticons,
The evaluation index element includes an emotion expression element in the comment,
The value of the emotion expression element is preferably the number of appearances of each emotion expression term included in the comment.

According to another embodiment of the comment list public server of the present invention,
The evaluation index element includes the style element in the comment,
The value of the style element is preferably the number of occurrences of each style in the morpheme at the end of the sentence included in the comment.

According to another embodiment of the comment list public server of the present invention,
The evaluation index element includes the attention level element in the comment,
The value of the attention level element is preferably the number of citations of the comment.

According to another embodiment of the comment list public server of the present invention,
One or more characteristic words characterizing the media content are extracted from the comment set in the media content using TF-IDF (Term Frequency-Inverse Document Frequency),
The evaluation index element includes the majority element in the comment,
The value of the majority element is preferably the number of appearances of characteristic words included in the comment.

According to another embodiment of the comment list public server of the present invention,
Regarding the weight coefficient storage means, it is also preferable that the weight coefficient for each evaluation index element for each distribution index element is explicitly set by the user.

According to another embodiment of the comment list public server of the present invention,
Media content is news article content or broadcast content,
The comment is also preferably sent from an SNS (Social Networking Service) server, a blog (Web-log) server, a bulletin board server, or a review site server.

According to the present invention, a program that causes a computer mounted on a server that can communicate with a media server that distributes media content and a comment server that sends text comments between a plurality of contributors,
Weight coefficient storage means for assigning and storing a weight coefficient for each evaluation index element that can be extracted from the content of the comment for each distribution index element in the media content;
A distribution index extracting means for extracting a distribution index element in the media content acquired from the media server;
Comment set search means for searching a comment set related to media content from a comment server;
For each comment in the comment set obtained from the comment server, an evaluation index value extracting means for extracting the value of each evaluation index element from the content;
For each comment in the comment set for the media content, an evaluation index value updating means for multiplying the value of the evaluation index element by a weighting factor based on the distribution index element of the media content ,
The computer is caused to function as comment sorting means for sorting a plurality of comments based on the updated value of the evaluation index element for the comment set for the media content.

According to the present invention, a comment publishing method using a comment list publishing server capable of communicating with a media server that distributes media content and a comment server that sends text comments among a plurality of contributors,
Comment list public server
For each distribution index element in the media content, a weighting coefficient storage unit that allocates and stores a weighting coefficient for each evaluation index element that can be extracted from the content of the comment,
A first step of extracting a distribution index element in the media content acquired from the media server;
A second step of retrieving a comment set related to media content from a comment server;
For each comment of the comment set acquired from the comment server, a third step of extracting the value of each evaluation index element from the content;
A fourth step of multiplying the value of the evaluation index element for each comment of the comment set for the media content by a weighting factor based on the distribution index element of the media content;
And a fifth step of sorting a plurality of comments based on the updated value of the evaluation index element with respect to the comment set for the media content.

  According to the comment list publicizing server, program, and method of the present invention, it is possible to control the sorting condition of the comment set relating to the media content according to various distribution indexes of the media content, and to make it clear to the user.

It is a system configuration diagram in the present invention. It is a function block diagram of the comment list public server in this invention. It is a screen display figure of the terminal browsed by the user. It is a screen display figure showing the sort of the comment set highly weighted to the excitement element. It is a screen display figure showing the sort of the comment set highly weighted by the negative / emotion expression element. It is a screen display figure showing the sort of the comment set highly weighted by the majority element.

  Hereinafter, embodiments of the present invention will be described in detail with reference to the drawings.

  FIG. 1 is a system configuration diagram according to the present invention.

  According to FIG. 1, a media server 2 that distributes media content and a comment server 3 that sends text comments between a plurality of contributors are connected to the Internet. The media contents distributed by the media server 2 are, for example, news articles, web pages, music contents, electronic books, and television broadcast contents, and can be accessed by an unspecified number of users. The comment server 3 may be an SNS server, a blog server, a bulletin board server, or a review site server. The comment released by the comment server 3 is, for example, a tweet released on the twitter (registered trademark) site.

  In the following description, it is assumed that the media server 2 and the comment server 3 are separately installed on the Internet (see FIG. 1). However, a site server in which these functions are integrated may be used. In the case of such a site server, a large number of comments are associated with each media content and released. For example, there is a site server such as YouTube (registered trademark).

  According to FIG. 1, the “comment list public server 1” is further connected to the Internet. The comment list publishing server 1 can acquire media contents from the media server 2 and search for and acquire a comment set from the comment server 3. The comment list publishing server 1 controls the sorting condition of the comment set related to the media content according to various distribution indexes of the media content, and makes it explicit to the user. The function of the comment list public server of the present invention may be incorporated into a site server that integrates the functions of the media server and comment server described above.

  The terminal 4 is, for example, a smartphone, a mobile phone, a tablet terminal, a personal computer, a television, or the like, and can be browsed by the user. By accessing the comment list public server 1, the terminal 4 can view both the media content and the comment list related to the media content.

  FIG. 2 is a functional configuration diagram of the comment list public server according to the present invention.

  According to FIG. 2, the comment list public server 1 includes a weighting factor storage unit 10, a distribution index extraction unit 11, a comment set search unit 12, an evaluation index value extraction unit 13, along with a communication interface connected to the Internet. The evaluation index value update unit 14, the comment sort unit 15, the comment list disclosure unit 16, and the emotion expression element registration unit 17 are included. These functional components are realized by executing a program that causes a computer mounted on the server to function. Moreover, the flow of processing of these functional components can be understood as a comment disclosure method.

[Weight coefficient storage unit 10]
The weighting coefficient storage unit 10 assigns and stores a “weighting coefficient” for each “evaluation index element” that can be extracted from the content of the comment for each “distribution index element” in the media content. That is, the comment list public server 1 of the present invention sorts comment sets from different viewpoints (weighting factors for evaluation index elements) according to the type of media content (distribution index element) and clearly indicates to the user. .

Examples of the “distribution index element” include <genre information A><distribution source information B><delivery date / time C> (a plurality of combinations of these elements) in the media content.
Examples of the “evaluation index element” include <rising element α><emotion expression element β><style element γ><attention level element δ><majority element ε> that can be extracted from the comment.
A specific example of the weighting factor will be described later with reference to FIGS.

[Distribution index extraction unit 11]
The distribution index extraction unit 11 extracts “distribution index elements” in the media content acquired from the media server 2. For example, RSS (Really Simple Syndication / Rich Site
Summary) can be used to collect the latest media content URLs. Then, the distribution index extraction unit 11 extracts “distribution index elements” (genre information A, distribution source information B, distribution date and time C) as well as titles and article texts from the collected media content. The extracted distribution index element is output to the comment set search unit 12.

[Comment set search unit 12]
The comment set search unit 12 searches the comment server 3 for a comment set related to the media content. For example, the search is performed using a search API (Application Programming Interface) published by the comment server 3 using the URL, title, or hash tag of the media content as a search key. For example, when the media content is a news article, a comment set related to the news article can be collected. The retrieved comment set is output to the evaluation index value calculation unit 13.

  As another embodiment, a word may be extracted from text included in media content by morphological analysis. “Morphological analysis” refers to a technique in which sentences are divided into meaningful words and the part of speech and contents are discriminated using a dictionary. The “morpheme” means the smallest unit having meaning among the elements of the sentence. Then, characteristic words are extracted from the words extracted by morphological analysis by TF-IDF (Term Frequency-Inverse Document Frequency). TF-IDF is a technology that weights each word, expresses sentences from a query in a vector space, and ranks them based on the similarity between the sentences and the query. The higher the ranked value, the more important keywords are recognized. Then, it is possible to search from the comment server 3 using this characteristic word as a search key.

[Evaluation index value extraction unit 13]
For each comment of the comment set acquired from the comment server 3, the evaluation index value extraction unit 13 determines each “evaluation index element” (a climax element, an emotion expression element, a style element, a degree-of-interest element, a majority element) from the contents. Extract the value of. Similar to the comment set search unit 12, the evaluation index value extraction unit 13 extracts each evaluation index element included in the comment by executing morphological analysis and TF-IDF processing. The extracted value of each evaluation index element is output to the evaluation index value update unit 14.

[Evaluation index value update unit 14]
The evaluation index value update unit 14 multiplies the value of the evaluation index element by a weighting factor for each comment in the comment set for the media content. The updated evaluation index value is output to the comment sorting unit 15.
A specific example regarding multiplication of the weight coefficient will be described later with reference to FIGS.

[Comment sorting unit 15]
The comment sorter 15 sorts a plurality of comments based on the updated value of the evaluation index element for the comment set for the media content. Specifically, the sum of the updated values of the plurality of evaluation index elements is calculated as the sort priority P. Then, the comments are sorted in order from the comment having the highest sort priority P. The sorted comment set is output to the comment list disclosure unit 16.

[Comment list disclosure unit 16]
The comment list publishing unit 16 transmits the sorted comment set together with the media content to the user terminal 4 as a site page. For example, when the media content is a news article, the user of the terminal 4 can view a comment set of other contributors sorted according to the news article together with the news article.

  FIG. 3 is a screen display diagram of a terminal viewed by the user.

According to FIG. 3, media content distributed from b newspaper company (distribution source information) on August 5, 2013 at 15:30 (distribution date and time) is displayed as news articles (genre information) of mobile phones. .
“Company a has released a cable for charging smartphones from smartphones.
MMM, the entertainer, is printed on the plug of this cable.
The price is 3,150 yen including tax. "
Regarding this media content, comments posted by an unspecified number of users are also displayed.

Hereinafter, a specific weighting method will be described for each evaluation index element.
<Rising element>
The excitement element is “excitement expression” included in the comment. This expression focuses on the continuity of characters, for example. For example, when three or more identical characters appear, it is considered that the part is emphasized in the comment. In other words, the value of the rising element may be the maximum number of the same morphemes among the plurality of morphemes included in the comment. For example, the degree of excitement e can be expressed as follows, for example.
“Hey, ah, ah ah ah ah ah ah ah” (19 characters): e = 19
"Uooooooooooooo" (11 characters): e = 11
"Ooioi wwwwwwwww": e = 14
("Oi" 2 times + "w" 10 times = 14 times)

Here, the sort priority P based on the value of the evaluation index element is expressed as follows.
P = (αA + αB + αC) × e
e: Degree of excitement
αA: Weighting factor of swell expression element for genre information
αB: Weighting factor of swell expression element for distribution source information
αC: Weighting factor of swell expression element for delivery date and time

  FIG. 4 is a screen display diagram showing the sorting of the comment set highly weighted by the swell elements. According to FIG. 4, a comment having a larger number of consecutive identical morphemes is displayed preferentially.

As a specific example, for example, when the genre information is “sports”, a weighted expression αA of “sports” is set high so that the comments that are excited are displayed preferentially. On the other hand, when the genre information is “politics / economy”, it is less necessary to preferentially display the excitement comment, and the weight αA of the excitement expression of “politics / economy” is set low.
For example, when the distribution source information is a “entertainment” company, it is preferable to set the weight αB for the expression of “entertainment” to be high and to display the comment that prevails preferentially.
On the other hand, for example, when the distribution date is “morning”, it is preferable to set the weight αC of the rising expression of “morning” to be low so as not to display the rising comment preferentially.

<Emotion expression element>
The emotion expression element is an “emotional expression” included in the comment. This expression focuses on positive characters / negative characters / emoticons, for example. That is, the value of the emotion expression element is the number of appearances of each “emotional expression term” included in the comment.

For this purpose, the comment list public server 1 further includes an “emotion expression term registration unit 17” in which emotion expression terms of positive characters / negative characters / emoticons are registered in advance. Using the dictionary of the emotion expression term registration unit 17, it is determined whether or not an emotion expression is included in the comment.
Emotional term registration part <-affirmation sp = "happy""congratulations"
Denial sn = "Scared""No"
Emoticon sf ＝ 「(^_^)」 「(； ゜ Д ゜)」 「(； ´Д ｀)」
Comment “It ’s a great news. Congratulations on winning (^ _ ^)”-> 2 affirmations + 1 emoticon “Eh ...... scary ((((； ゜ Д ゜)))))))”-> 1 negative + 1 emoticon “No, this is ... (; ´Д ｀)”-> 1 negative + 1 emoticon

Here, the sort priority P based on the value of the evaluation index element is expressed as follows.
P = (βAp + βBp + βCp) × sp + (βAn + βBn + βCn) × sn
+ (ΒAf + βBf + βCf) × sf
sp: affirmation
sn: negation degree
sf: Emoticon degree
βAp: Weighting factor for positive and emotional expression elements for genre information
βAn: Weight coefficient of negative / emotion expression elements for genre information
βAf: Weight factor of emoticon / emotional expression elements for genre information
βBp: Affirmation / emotion expression element weighting factor for distribution source information
βBn: Weighting factor of negative / emotion expression elements for distribution source information
βBf: Weight coefficient of emoticon / emotion expression element for distribution source information
βCp: Weighting coefficient of affirmative / emotional expression elements for delivery date and time
βCn: Weighting factor of negative / emotion expression element for delivery date and time
βCf: Weight coefficient of emoticon / emotional expression element for delivery date and time

  FIG. 5 is a screen display diagram showing the sorting of the comment set highly weighted by the negative / emotion expression elements. According to FIG. 5, a comment that includes more negative characters and emoticons is preferentially displayed at the top.

As a specific example, for example, when the genre information is “sports”, the weight βAp of the positive / emotion expression element of “sports” is set high in order to preferentially display comments including positive emotional expressions. . On the other hand, when the genre information is “politics / economic”, the weight βAn of the negative / emotional expression element of “politics / economic” is set high in order to preferentially display comments including negative emotional expressions.
Also, for example, when the distribution source information is “entertainment” company, in order to preferentially display comments including negative emotional expression of “entertainment”, the weight βBn of the negative / emotion expression element of “entertainment” is increased. Set.
Furthermore, for example, when the delivery date is “holiday”, it is also preferable to set the emoticon / emotion expression element weight βCf of “holiday” to be high and to display calm comments with many emoticons preferentially.

<Style element>
The stylistic element is a “style expression” included in the comment. This expression can be focused on the adjective forms of “adjectives”, “adjective verbs”, and “verbs” as end sentences analyzed by morphological analysis. Examples of the utilization forms include “instruction form”, “assumed form”, and “unformed form”. That is, the value of the style element is the number of appearances of each style in the morpheme at the end of the sentence included in the comment.
"Wow, don't stop"-> Imperative "If it's a bit cheaper"-> Assumptions "I don't buy this"-> Unfinished

The sort priority P based on the value of the evaluation index element is expressed as follows.
P = (γA + γB + γC) × (w1 + w2 + ... + wn)
γA: Stylistic element weighting factor for genre information
γB: Stylistic element weighting factor for distribution source information
γC: Stylistic element weighting factor for delivery date and time
w1: Presence / absence of command type (0/1)
w2: Presence or absence (0/1)
...
wn: ~ existence of shape (0/1)
As a specific example, for example, when the genre information is “news”, the weight γA of the stylistic element is set high in order to preferentially display comments including a hypothetical stylistic.

<Attention level element>
The attention level element is the number of citations of the comment. For example, in the case of a twitter server, the number of tweets and the number of followers are set as the attention degree f.

The sort priority P based on the value of the evaluation index element is expressed as follows.
P = (δA + δB + δC) × f
δA: Weight factor of attention factor for genre information
δB: Weighting factor of attention factor for distribution source information
δC: Weight coefficient of attention level element with respect to distribution date As a specific example, for example, when the genre information is “news”, the weight δA of the attention level element is increased in order to preferentially display comments with many citations. Set.

<Majority factor>
The value of the majority element is the “number of feature words” included in the comment. The feature word is extracted from the comment set related to the media content using TF-IDF. Then, the comment including the characteristic word is determined as the majority.
Number of comments including feature words-> majority degree m

The sort priority P based on the value of the evaluation index element is expressed as follows.
P = (εA + εB + εC) × m
εA: Weight factor of majority factor for genre information
εB: Weight factor of majority factor for distribution source information
εC: Weight factor of majority factor for delivery date and time

  FIG. 6 is a screen display diagram showing the sorting of comment sets that are heavily weighted by the majority element. According to FIG. 6, the majority comments are displayed with higher priority.

  As a specific example, for example, when the genre information is “news”, the majority element weight εA is set low in order to preferentially display minority comments. TF is the frequency of appearance of each word in the comment regarding the news, and DF is the frequency of occurrence of each word in the comment regarding all news.

Considering all the above-mentioned <rising element><emotion expression element><styleelement><attention level element><majorityelement>, the sort priority can be calculated as follows.
P = (αA + αB + αC) × e
+ (ΒAp + βBp + βCp) × sp + (βAn + βBn + βCn) × sn
+ (ΒAf + βBf + βCf) × sf
+ (ΓA + γB + γC) × (w1 + w2 + ... + wn)
+ (ΔA + δB + δC) × f
+ (ΕA + εB + εC) × m

  As another embodiment, the weighting factor for each evaluation index element for each distribution index element may be fixed in advance or explicitly set by the user. According to FIGS. 3 to 6, buttons of “evaluation index elements” (rising elements, emotional expression elements, style elements, attention degree elements, majority degree elements) are also provided in the upper part of the browser browsed by the user. Yes. The user can sort the currently displayed comment set according to a desired evaluation index. Specifically, when the user clicks the button of the evaluation index element, the weight coefficient based on the evaluation index element in the weight coefficient storage unit 10 is set to be high.

  Further, these weighting factors may be automatically set for each user. For example, it is also preferable to make each index (e, s, w, f, m) a feature by using a classifier such as a neural network, SVM (Support Vector Machine), Naive Bayes, or C4.5. It is also possible to determine the weighting coefficient by letting the classifier learn that a comment viewed (or evaluated) by the user is a “positive example” and a comment that has not been browsed is a “negative example”. Moreover, if each index is included in the browsed comment using the rule base, the weight may be automatically changed.

  As described above in detail, according to the comment list release server, program, and method of the present invention, the user can control the sorting condition of the comment set related to the media content according to various distribution indexes of the media content, and Can be specified.

  Various changes, modifications, and omissions of the above-described various embodiments of the present invention can be easily made by those skilled in the art. The above description is merely an example, and is not intended to be restrictive. The invention is limited only as defined in the following claims and the equivalents thereto.

DESCRIPTION OF SYMBOLS 1 Comment list public server 10 Weight coefficient memory | storage part 11 Distribution index extraction part 12 Comment set search part 13 Evaluation index value extraction part 14 Evaluation index value update part 15 Comment sort part 16 Comment list public part 17 Emotion expression element registration part 2 Media server 3 Comment server 4 Terminal

Claims (11)

A comment list public server that can communicate with a media server that distributes media content and a comment server that sends text comments between multiple contributors,
Weight coefficient storage means for assigning and storing a weight coefficient for each evaluation index element that can be extracted from the content of the comment for each distribution index element in the media content;
Distribution index extraction means for extracting a distribution index element in the media content acquired from the media server;
Comment set search means for searching a comment set related to the media content from the comment server;
For each comment of the comment set acquired from the comment server, an evaluation index value extracting means for extracting the value of each evaluation index element from the content thereof;
For each comment of the comment set for the media content, an evaluation index value update unit that multiplies the value of the evaluation index element by the weight coefficient based on the distribution index element of the media content ;
A comment list publishing server comprising comment sorting means for sorting a plurality of comments on the comment set for the media content based on the updated value of the evaluation index element. The comment list publishing server according to claim 1, wherein the distribution index element is genre information, distribution source information, distribution date and time, or a plurality of combinations of these elements in the media content. The evaluation index element includes a rising element in the comment,
The comment list publishing server according to claim 1, wherein the value of the excitement element is a maximum number of consecutive identical morphemes among a plurality of morphemes included in the comment. It further has an emotion expression term registration means for registering in advance the emotion expression terms for each of the positive / negative / emoticons,
The evaluation index element includes an emotion expression element in the comment,
The comment list public server according to any one of claims 1 to 3, wherein the value of the emotion expression element is the number of appearances of each emotion expression term included in the comment. The evaluation index element includes a stylistic element in the comment,
The comment list publishing server according to any one of claims 1 to 4, wherein the value of the style element is the number of occurrences of each style in the morpheme at the end of the sentence included in the comment. The evaluation index element includes an attention level element in the comment,
6. The comment list public server according to claim 1, wherein the value of the attention level element is the number of citations of the comment. One or more characteristic words characterizing the media content are extracted from the comment set in the media content using TF-IDF (Term Frequency-Inverse Document Frequency),
The evaluation index element includes a majority element in the comment,
The comment list disclosure server according to any one of claims 1 to 6, wherein the value of the majority element is the number of appearances of the characteristic word included in the comment. The comment list according to any one of claims 1 to 7, wherein the weight coefficient for each evaluation index element for each of the distribution index elements is explicitly set by the user in the weight coefficient storage means. Public server. The media content is news article content or broadcast content,
9. The comment according to claim 1, wherein the comment is transmitted from an SNS (Social Networking Service) server, a blog (Web-log) server, a bulletin board server, or a review site server. Public comment list server. A program for functioning a computer mounted on a server that can communicate with a media server that distributes media content and a comment server that sends text comments between multiple contributors,
Weight coefficient storage means for assigning and storing a weight coefficient for each evaluation index element that can be extracted from the content of the comment for each distribution index element in the media content;
Distribution index extraction means for extracting a distribution index element in the media content acquired from the media server;
Comment set search means for searching a comment set related to the media content from the comment server;
For each comment of the comment set acquired from the comment server, an evaluation index value extracting means for extracting the value of each evaluation index element from the content thereof;
For each comment of the comment set for the media content, an evaluation index value update unit that multiplies the value of the evaluation index element by the weight coefficient based on the distribution index element of the media content ;
A program that causes a computer to function as comment sorting means for sorting a plurality of comments based on the updated value of the evaluation index element for the comment set for the media content. A comment publishing method executed by a comment list publishing server that can communicate with a media server that distributes media content and a comment server that sends text comments between a plurality of contributors,
The comment list public server is
For each distribution index element in the media content, a weight coefficient storage unit that allocates and stores a weight coefficient for each evaluation index element that can be extracted from the content of the comment;
A first step of extracting a distribution index element in the media content acquired from the media server;
A second step of retrieving a comment set related to the media content from the comment server;
A third step of extracting the value of each evaluation index element from the content of each comment of the comment set acquired from the comment server;
For each comment in the comment set for the media content, a fourth step of multiplying the value of the evaluation index element by the weighting factor based on the distribution index element of the media content;
Wherein for said comments set for media content, updated comment publishing comments list public server and executes a fifth step of sorting a plurality of comments based on the value of the evaluation index element.

Images