JP6675868B2 - Information processing apparatus, information processing method, and program - Google Patents

Description

  The present invention relates to a technique for extracting a post from a microblog such as Twitter.

  Since microblogging such as Twitter can be written by anyone at any time, it can be regarded as a place where the voice of the world gathers as text data in real time, though it is partial. In recent years, there are many users and companies that use microblogging as an information source with high speed reporting.

  However, there is a limit to the amount of posts that can be manually checked, and it is difficult to check all posts that increase daily. Therefore, as shown in Non-Patent Document 1, some mechanical Research to extract the reputation and topics by performing processing and overlooking the whole is being actively conducted.

  For example, as shown in FIG. 1, by extracting a post including a specific product name and visualizing the time-series transition of the number of posts, it is possible to grasp the timing at which any event has occurred for the product. Also, as shown in FIG. 2, by referring to statistical information such as the frequency of each word included in the post, it is possible to roughly understand what topics are occurring without reading all the posts. it can.

  By combining the above-described techniques, it is possible to confirm a period in which the topic has increased sharply and visualize the topic in the corresponding period. However, the task of manually investigating all periods during which the number of posts has surged is extremely time-consuming. Also, during the period in which the event occurs, there is a tendency that diffused posts and words related to the event tend to appear frequently, making it difficult to grasp topics and evaluations not related to the event.

  As a technique for making it easy to understand the cause analysis of the sudden increase / decrease of the graph, Japanese Patent Application Laid-Open Publication No. 2003-216400 specifies from a post including words (eg, “release”, “announcement”, “holding”, “discovery”) and time expressions indicating the occurrence of an event. There has been proposed a method of automatically extracting schedule information of an event that has occurred in a target and annotating the schedule information on a time-series graph.

WO2009 / 101954

Okumura Manabu, "Text Mining for Social Media" IEICE Fundamental and Boundary Society Fundamental Review Vol.6 No.4 pp.285-293, 2013. Takashi Inui, et al., "Research Trends in Analysis of Evaluation Information for Text", Natural Language Processing, Japan Society for Language Processing, July 2006, Vol. 13, No. 3, pp. 201-241

  According to the technology disclosed in Patent Document 1, it is possible to present a part of an event occurring in each period on a time-series graph. I can't show you what it is. In other words, since topics other than the event presented may have contributed to the sudden increase in the number of posts, users of the system can determine whether more detailed analysis is necessary based only on the annotated information. It cannot be said that it is enough from the viewpoint of reducing labor for analyzing the cause of the sudden increase in the number of posts.

  The present invention has been made in view of the above-described problems, and provides a system user with information for determining whether or not a post requires a more detailed analysis work, thereby reducing the workload of the system user. The purpose is to reduce the amount.

According to a first aspect of the present invention, there is provided an extracting unit for extracting one or more posts related to a specific object, a totaling unit for totalizing the extracted posts for each type of post, and a totaling unit for each type of post. and a display means for displaying the summary information, wherein the post type, at least, include a post for the purpose of diffusion of posts, and a post intended to introduce the articles on a particular subject An information processing apparatus characterized by the following.
According to the first aspect, the extracted posts are totaled for each type of post, and displayed as total information for each type of post. As a result, it is possible to grasp the totaling result for each type of post, so that it is possible to provide the system user with information on whether or not the post requires more detailed analysis work, and to provide the system user with Work burden can be reduced. Further, the extracted posts, it is possible to analyze and classify the post and for the purpose of introducing the articles on posts with a particular subject for the purpose of diffusion of posts.

In the first invention, it is preferable that the display unit displays the number of posts for each type of post in a time-series graph. At this time, it is preferable that the time-series graph further includes an annotation means for giving an annotation relating to the post. This makes it easy to grasp the composition (type) of the post on the annotated time-series graph, and to reduce the time for determining whether or not it is necessary to perform more detailed analysis. it can. Further, it is preferable that the contents of the annotation are topics extracted for each type of post and the number of cases for each topic, and are displayed in the order of the type of post having a large number of posts. This makes it easy to analyze the cause of the increase in the number of posts by annotating the main topic and the number of posts for each topic together on the time-series graph.

  According to a second aspect of the present invention, there is provided an extracting unit that extracts one or more posts related to a specific target, a totaling unit that totals each extracted post for each type of post, and a time series graph of the number of posts for each type of post. Display means for displaying, and an annotation means for giving an annotation on a post to the time-series graph, wherein the contents of the annotation show topics extracted for each type of post and the number of cases for each topic. An information processing apparatus characterized in that:
  According to the second invention, the extracted posts are totaled for each type of post, the number of posts for each type of post is displayed in a time-series graph, and an annotation regarding the post is given to the time-series graph. It is assumed that the contents of the annotation display the topics extracted for each type of post and the number of cases for each topic. This makes it easy to grasp the type of post on the annotated time-series graph, and it is possible to reduce the time for determining whether or not it is necessary to perform more detailed analysis. Also, by annotating the main topic and the number of posts for each topic together on the time-series graph, it is easy to analyze the cause of the increase in the number of posts.
  In addition, it is desirable that the contents of the annotation are displayed in such a manner that topics extracted for each type of post and the number of cases for each topic are displayed in the order of the type of post having a large number of posts.

Further, in the first and second inventions, further comprising an event acquiring means for acquiring an event occurrence period based on the number of posts, wherein the annotating means comprises an annotation on the time-series graph corresponding to the event occurrence period. Is desirably provided. This makes it possible to easily grasp the configuration (type) of the post during the event occurrence period in which the number of posts increases.

According to a third aspect , an extraction step of the information processing device extracts one or more posts related to a specific target, and a tallying unit of the information processing device counts each of the extracted posts for each type of post. And a display step in which the display means of the information processing apparatus displays the total information for each type of post that has been totaled. When an information processing method which comprises a post intended to introduce the articles on a particular subject.
A fourth invention is a step in which the extracting means of the information processing device extracts one or more posts related to a specific object, and the step in which the counting means of the information processing device counts each extracted post for each type of post. A step of displaying the number of posts for each type of post in a time-series graph, and a step of annotating the information processing apparatus annotating the time-series graph with a post-related annotation. , And the content of the annotation is a display of a topic extracted for each type of post and the number of cases for each topic.

According to a fifth aspect of the present invention, the computer displays an extracting unit for extracting one or more posts related to a specific target, a totaling unit for totalizing each extracted post for each type of post, and displaying totaling information for each type of post. display means for, in a program for functioning in, wherein the post type, at least, a post for the purpose of diffusion of posts, the posts for the purpose of introducing the articles on a particular subject The program is characterized by including:
According to a sixth aspect of the present invention, there is provided a computer, comprising: an extracting unit that extracts one or more posts related to a specific target; a counting unit that counts each extracted post for each type of post; A program for functioning as display means for displaying in a series graph, and annotation means for giving an annotation about a post to the time series graph, wherein the contents of the annotation are extracted for each type of post. The program is characterized by displaying topics and the number of cases for each topic.

  ADVANTAGE OF THE INVENTION According to this invention, it becomes possible to provide the system user with information for determining whether or not it is necessary to perform more detailed analysis on a post.

Diagram showing visualization example of time-series transition of the number of posts Diagram showing the frequency of each word included in the post Diagram showing the functional configuration of the microblog analysis system 100 FIG. 2 is a block diagram illustrating an example of a hardware configuration of the information processing apparatus 101. Diagram showing an example of post data 120 The figure which shows an example of the contribution total data 130 Flowchart of post acquisition process Flowchart of post totaling process The figure which shows an example of the number-of-posts daily change graph which the post visualization part 113 generated. The figure which shows an example of the time series graph which the post visualization part 113 produced | generated. Diagram showing the entire contents of the annotation in FIG.

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

FIG. 4 is a block diagram illustrating an example of a hardware configuration of the information processing apparatus 101 according to the embodiment of the present invention.
In FIG. 4, reference numeral 201 denotes a CPU, which comprehensively controls each device and controller connected to the system bus 204. Also, the ROM 203 or the external memory 211 is required to implement a function executed by each server or each PC, such as a basic input / output system (BIOS) or an operating system program (hereinafter, OS), which is a control program of the CPU 201. Various programs and the like are stored.

  Reference numeral 202 denotes a RAM, which functions as a main memory, a work area, and the like for the CPU 201. The CPU 201 implements various operations by loading programs and the like necessary for executing processing from the ROM 203 or the external memory 211 into the RAM 202 and executing the loaded programs.

  An input controller 205 controls input from the input device 209 or the like. A video controller 206 controls display on a display device 210 such as a liquid crystal display. The display device is not limited to a liquid crystal display, but may be a CRT display or the like. These are used by the client as needed.

A memory controller 207 is connected to a hard disk (HD) for storing a boot program, various applications, font data, user files, edit files, various data, and the like, a flexible disk (FD), or a PCMCIA card slot via an adapter. Access to an external memory 211 such as a compact flash (registered trademark) memory.
The external memory 211 stores a program for causing the CPU 201 to execute each function of the microblog analysis system 100 described later. By installing this program on a general-purpose computer, the information processing apparatus 101 according to the present invention can be obtained.

  A communication I / F controller 208 connects and communicates with an external device via a network (for example, the LAN 400 shown in FIG. 1), and executes communication control processing on the network. For example, communication using TCP / IP is possible.

Note that the CPU 201 enables display on the display device 210 by executing, for example, a process of developing (rasterizing) an outline font in a display information area in the RAM 202. Further, the CPU 201 enables a user instruction with a mouse cursor (not shown) on the display device 210.
Various programs operating on the hardware are recorded in the external memory 211 and are executed by the CPU 201 by being loaded into the RAM 202 as needed.
Note that not all devices have these components, and only need to have necessary components.

  According to the present invention, when the number of posts on a microblog increases rapidly (when an event occurs), it is highly likely that the URL of a Web page related to the event information is included in the post, and the microblog user's interest has been attracted. Topics are extracted and visualized using the characteristics of microblogging, such as the fact that posts are easily quoted and spread. Hereinafter, embodiments of the present invention will be described in detail with reference to the drawings.

FIG. 3 is a diagram illustrating a functional configuration of the microblog analysis system 100 according to the embodiment of the present invention.
The microblog analysis system 100 includes a post acquisition unit 111, a post totaling unit 112, a post visualizing unit 113, post data 120, and post total data 130.

  The post acquisition unit 111 acquires a post related to a specific target from the microblog and stores the post in the post data 120. The post acquisition process in the post acquisition unit 111 will be described later in detail using an example.

  The post totaling unit 112 refers to the post stored in the post data 120, performs various types of total processing required to generate a time-series graph of the post data, and stores the total result in the post total data 130. The tallying process in the posting tallying unit 112 will be described later in detail using an example.

  The post visualization unit 113 generates a time-series graph of the post data with reference to the post total data 130. The method of generating the time series graph will be described in detail later using an example.

  FIG. 5 is an example of the post data 120. In addition to a post ID for uniquely identifying a post, a post date and time, and a post, an article title separately given by the post acquisition unit 111 and a diffusion target ID are provided for each post. Hold. The article title and the diffusion target ID will be described in detail later in the description of the post acquisition process.

  FIG. 6 is an example of the post totaling data 130. The post total data 130 includes total post total data 131, article post total data 132, spread post total data 133, and opinion post total data 134. Details of each data will be described in detail in the description of the post totaling process.

  Next, the post acquisition process in the post acquisition unit 111, the tallying process in the post tallying unit 112, and the method of generating the time series graph in the post visualization unit 113 will be described in order using examples.

  First, the post acquisition process in the post acquisition unit 111 will be described with reference to FIGS. FIG. 7 is a flowchart of the post acquisition process according to the embodiment of the present invention. Hereinafter, an example in which a post about “product A” is acquired from a microblog according to the processing of FIG. 7 will be described.

In step S101, the CPU 201 (post acquisition unit 111) of the information processing apparatus 101 acquires, from the microblog, a post including “product A” to be analyzed in the posted text. In order to explain the subsequent processing, it is assumed here that a set of posts including the five posts (post A to post E) shown in the following table has been acquired.
Note that step S101 constitutes an example of “extraction means for extracting one or more posts related to a specific subject from a microblog” of the present invention.

  For each post acquired in step S101, the CPU 201 (post acquisition unit 111) repeatedly executes the processes of steps S102 to S107. The processing of steps S102 to S107 is processing of acquiring additional information for a URL included in a post or a post citing another post, and storing the additional information in the post data 120.

  First, in step S103, the CPU 201 (post acquisition unit 111) determines whether a URL is included in the posted text. CPU201 (post acquisition part 111) shifts processing to Step S104, when URL is contained in a contribution text. For example, since the post A includes the URL in the post, the CPU 201 (post acquisition unit 111) executes the process of step S104.

  In step S104, the CPU 201 (post acquisition unit 111) acquires the title of the Web page indicated by the URL via the Internet. Here, the acquired title is called an “article title”. When a posted sentence includes a plurality of URLs, the CPU 201 (post acquisition unit 111) acquires article titles for all URLs. For example, in the post A, the article title “Product A will be released this winter” for the URL “http://zsha.example.com/news/1001.html” and the URL “http://zsha.example.com/ news / 1002.html "for each article title" Product A performance table ".

  Next, in step S105, the CPU 201 (post acquisition unit 111) determines whether or not the post refers to another post. If the post cites another post, the CPU 201 (post acquisition unit 111) shifts the processing to step S106. For example, since the post C is a post citing the post B, the process of step S106 is executed. Here, in order to simplify the explanation, the posts quoted by each post will be described as information that can be obtained at the time of obtaining the post from the microblog.

  In step S106, the CPU 201 (post acquisition unit 111) acquires the post ID of the quoted post. The post ID acquired here is called “spread target ID”.

  Next, in step 107, the CPU 201 (post acquisition unit 111) stores the post ID, the post date and time, the posted text, the article title acquired in step 104, and the diffusion target ID acquired in step 106 in the post data. Add to 120. Here, a post having an article title is referred to as an "article post" (a post intended to introduce an article on the Web), and a post having a target ID is referred to as a "diffused post" (a purpose of post diffusion). Posts), and posts that do not exist are called "opinion posts." For example, the post A and the post B are article posts, the post C is an article post and diffuse post, the post D is an opinion post, and the post E is a diffuse post.

  The post acquisition process in the post acquisition unit 111 has been described using examples. Note that, for simplification of the description, the post cited by each post has been described as information that can be obtained at the time of obtaining the post from the microblog in step S105. It is possible to mechanically acquire a post to be quoted depending on the context of the content and the posting date and time.

  Next, the post totaling process in the post totalizing section 112 will be described with reference to FIGS. 5, 6, and 8. FIG. FIG. 8 is a flowchart of the post totaling process in the embodiment of the present invention. Hereinafter, an example in which the postings of “October 4, 2015” regarding “Product A” are totaled according to the processing of FIG.

  First, in step S201, the CPU 201 (post counting unit 112) of the information processing apparatus 101 acquires a post posted during the counting target period from the posting data. For example, when the totaling period is one day of October 4, 2015, the posting data 120 in FIG. 5 indicates that posting A, posting B, posting C, and posting D are to be obtained, and posting E is not to be obtained. is there.

  Next, for each post acquired in step S201, the CPU 201 (post totaling unit 112) repeatedly executes the processes of steps S202 to S209. The process of steps S202 to S209 is a process of updating the posted total data 130.

  First, in step S203, the CPU 201 (post totaling unit 112) determines whether or not an article title exists in the post data. If the article title is included in the posted data, the CPU 201 (post counting unit 112) shifts the processing to step S204.

  In step S204, the CPU 201 (the post totaling unit 112) updates the post totaling data 132. The article posting total data 132 includes a totaling period, an article title, and the number of posts. Here, the number of posts is the number of posts including each article title in each counting period. The CPU 201 (post counting unit 112) refers to the article posting count data 132, and if there is a record having the same counting target period / article title as the posting data, adds 1 to the number of posts of the corresponding record, and If the record does not exist, a new record with one post is registered.

  Next, in step S205, the CPU 201 (post totalizing unit 112) determines whether or not the post data has a diffusion target ID. If the post data includes the diffusion target ID, the CPU 201 (post totaling unit 112) shifts the processing to step S206.

  In step S206, the CPU 201 (the post totaling unit 112) updates the diffused post total data 133. The spread posting total data 133 includes a totaling period, a spreading target ID, and the number of posts. Here, the number of posts is the number of posts including each diffusion target ID in each aggregation period. The CPU 201 (post totalizing unit 112) refers to the diffusion totaling data 133, and if there is a record having the same totaling period and diffusion ID as the posting data, adds 1 to the number of postings of the corresponding record, and If there is no record to be registered, a new record with one post is registered.

  Next, in step S207, the CPU 201 (post totalizing unit 112) determines whether or not the post data is an opinion post (no article title or diffusion target ID exists). If the posting data is an opinion posting, the CPU 201 (post summarizing unit 112) shifts the processing to step S208.

  In step S208, the CPU 201 (post totalizing unit 112) updates the opinion totaling data 134. The opinion posting total data 134 includes a totaling period, opinions, and the number of posts. Here, the “opinion” is a character string extracted from a posted sentence using natural language processing. In order to simplify the explanation, adjectives and verbs included in the posted sentence are treated as opinions of the posted data here (extraction of adjectives and verbs is possible by a known technique). For example, adjectives such as "want" and "great" are extracted from the posted sentence of the post D in the posted data 120 in FIG. The CPU 201 (post totalizing unit 112) refers to the opinion totaling data 134, and if there is a record in the same totaling period for each extracted opinion, adds 1 to the number of posts of the corresponding record, and If there is no record to be registered, a new record with one post is registered.

  Next, in step S209, the CPU 201 (post totalizing unit 112) updates the total post totaling data 131. The total post total data 131 includes the number of posts, the number of article posts, the number of diffused posts, and the number of opinion posts. The post totaling unit 112 refers to the total post total data 131, adds 1 to the number of posts in the corresponding record if there is a record of the same totaling target period, and adds the number of posts if there is no corresponding record. Is registered as a new record. If the post data is an article post, 1 is added to the number of article posts, if it is a diffuse post, 1 is added to the diffuse post, and if it is an opinion post, 1 is added to the number of opinion posts.

The posting tallying process performed by the posting tallying unit 112 has been described above using examples. For the sake of simplicity, in step S208, a method of treating the prototypes of adjectives and verbs as opinions of the posted data has been described. However, the output result of the evaluation information extraction technology as introduced in Non-Patent Document 2 is described. May be used.
Note that, according to steps S102 to S107 in FIG. 7 (post acquisition processing) and steps S201 to S209 in FIG. 8 (post summarization processing), each extracted post of the present invention is classified and classified according to the type of post. Tallying means "An example of" the tallying means categorizes and counts the extracted posts into at least a post for the purpose of spreading the posts and a post for the purpose of introducing an article on the Web " Is configured. The types of posts include diffuse posts and article posts, article posts excluding diffuse posts, diffuse posts excluding article posts, and opinion posts.

Next, a method of visualizing post data in post visualization section 113 will be described with reference to FIGS. 1, 6, 9, and 10. FIG. FIG. 9 and FIG. 10 are time-series graphs generated by the post visualization unit 113 with reference to the post totaling data 130. The system user can browse and operate the graphs through a Web browser or the like. FIG. 11 is a diagram showing the entire contents of the annotation of FIG.
Hereinafter, the configuration of the time series graph will be described.

The CPU 201 (post visualization unit 113) of the information processing apparatus 101 refers to the total post total data 131, and visualizes the number of posts for each total period by a stacked bar graph. FIG. 9 is a transition graph of the number of posts in October 2015 for the product A generated by the post visualization unit 113. The post visualization unit 113 visualizes the number of posts of article posts excluding diffuse posts, the number of posts of article posts and diffuse posts, the number of posts of diffuse posts excluding article posts, and the number of opinion posts in different colors. This constitutes an example of “display means for displaying total information for each type of post” of the present invention, and “the display means displays the number of posts for each type of post in a time-series graph”.
The number of posts can be calculated by the following formula using the value held by the total post total data 131.

(Equation 1)
α = number of article posts and diffused posts = (number of article posts + number of diffused posts + number of opinion posts)-number of posts Number of article posts excluding diffused posts = number of article posts-α
Number of diffused posts except article posts = Number of diffused posts-α
Number of opinion posts = Number of opinion posts

Further, the CPU 201 (post visualization unit 113) refers to the post totaling data 130, and gives an annotation to be developed by a click operation by the user of the system on the time-series graph. FIG. 10 shows a time-series graph after the user of the system clicks on the bar graphs of “October 4”, “October 10”, and “October 20” and expands respective annotations. I have. This constitutes an example of the "annotation means for giving an annotation relating to a post to the time-series graph" of the present invention.
Hereinafter, a method of acquiring the content described in the annotation in the post visualization unit 113 will be described.

An annotation is given to a place where an event is considered to have occurred (event occurrence period).
The event occurrence period can be specifically obtained by the following method.

  First, the CPU 201 (post visible unit 113) sorts the number of posts per unit period in the analysis period in descending order, and obtains the average value of the number of posts in the lower half (normal average value). Then, the CPU 201 (post visible unit 113) determines that the position where the number of posts is N or more and M times or more the average value in normal times is the event occurrence period. This constitutes an example of the “event acquisition unit that acquires an event occurrence period based on the number of posts” of the present invention.

The CPU 201 (post visualization unit 113) extracts characteristic topics for each type of post during each event occurrence period, and extracts the topics extracted in the order of the type of post with the largest number of posts on the time-series graph with the number of cases for each topic. Annotate. By this, according to the present invention, "the annotation means assigns an annotation on the time-series graph corresponding to the event occurrence period""The content of the annotation is a topic extracted in the order of the number of posts with the largest number of posts. And the number of cases for each topic ".
Hereinafter, a topic extraction method will be described in the order of article posting, diffusion posting, and opinion posting.

  First, a method of extracting a topic in article posting will be described. The CPU 201 (post visualization unit 113) refers to the article posting total data 132 and extracts, as a topic, the top L items of the number of posts among the article titles in the totaling period. (L is a natural number)

  Next, a method of extracting a topic in a diffusion posting will be described. The CPU 201 (post visualization unit 113) refers to the diffusion posting total data 133, extracts the top M posts with the number of posts from among the diffusion target IDs in the counting target period, and extracts the post corresponding to each diffusion target ID as a topic. I do. (M is a natural number)

  Next, a method of extracting a topic in opinion posting will be described. The CPU 201 (post visualization unit 113) refers to the opinion post total data 134 and extracts, from the opinions in the total period, the top N articles with the number of posts as topics. (N is a natural number)

  By referring to the annotated time-series graph output by the post visualization unit 113 described above, it becomes easy for the user of the system to grasp the composition of the post in the aggregation target period on the time-series graph. In addition, it is possible to reduce the time for determining whether more detailed analysis needs to be performed. For example, from FIG. 10, “The cause of the sudden increase in the number of posts on October 10 is that only the posts of the user who lost the product A are diffused, and no problem has occurred with the product A itself”. Therefore, it is possible to determine to omit the analysis for the period. Also, by consolidating topics for each type of post, it is possible to analyze only opinion posts, and it is possible to analyze evaluations (reputations at normal times) that are not related to events.

  In addition, since it is understood that “the ratio of the number of opinion postings increases on October 4 and October 20”, it is possible to determine that the analysis should be performed with more focus on the period. .

  As described above, the embodiment has been described in detail. However, the present invention can take an embodiment as, for example, a system, an apparatus, a method, a program, a storage medium, or the like. The system may be applied to a system including a single device, or may be applied to an apparatus including one device.

  The configurations and contents of the various data described above are not limited to those described above, and it goes without saying that the various data are configured according to applications and purposes.

  Needless to say, the present invention can be applied to a case where the present invention is achieved by supplying a program to a system or an apparatus. In this case, by reading a recording medium storing a program represented by software for achieving the present invention into the system or the apparatus, the system or the apparatus can enjoy the effects of the present invention.

  Further, by downloading and reading out a program represented by software for achieving the present invention from a server, a database, or the like by a communication program on a network, the system or apparatus can enjoy the effects of the present invention. It becomes possible.

  It should be noted that the present invention includes all configurations obtained by combining the above-described embodiments and their modifications.

100 Microblog analysis system 101 Information processing device 111 Post acquisition unit 112 Post totaling unit 113 Post visualization unit 120 Post data 130 … Post total data 131… Total post total data 132… Article post total data 133… Diffusion post total data 134… Opinion post total data 201… CPU
202 ...... RAM
203 ...... ROM
204 system bus 209 input device 210 display device 211 external memory

Claims (11)

Extraction means for extracting one or more posts about a particular subject;
A counting means for counting each extracted post for each type of post;
Display means for displaying total information for each type of post;
With
Wherein the post type, at least, a post for the purpose of diffusion of posts, the information processing apparatus according to claim <br/> include a post intended to introduce the articles on a particular subject. The information processing apparatus according to claim 1, wherein the display unit displays the number of posts for each type of post in a time-series graph. The information processing apparatus according to claim 2, further comprising: an annotation providing unit configured to add an annotation related to a post to the time-series graph. 4. The information processing according to claim 3 , wherein the contents of the annotation are topics extracted for each type of post and the number of cases for each topic, and are displayed in the order of types of posts having a large number of posts. apparatus. Extraction means for extracting one or more posts about a particular subject;
  A counting means for counting each extracted post for each type of post;
  Display means for displaying the number of posts for each type of post in a time-series graph;
  Annotating means for giving an annotation on a post to the time-series graph,
  With
  The content of the annotation is a display of topics extracted for each type of post and the number of cases for each topic.
  An information processing apparatus characterized by the above-mentioned. The contents of the annotation are the topics extracted for each type of post and the number of cases for each topic are displayed in the order of the type of post with the largest number of posts.
  The information processing apparatus according to claim 5, wherein: Further comprising an event acquisition unit for acquiring an event occurrence period based on the number of posts,
The information processing apparatus according to any one of claims 3 to 6, wherein the annotation providing unit adds an annotation on the time-series graph corresponding to the event occurrence period. An extracting step of extracting one or more posts related to a specific object, by an extracting unit of the information processing device;
A totaling unit of the information processing apparatus, a totalizing step of totalizing each extracted post for each type of post;
A display unit of the information processing device, a display step of displaying total information for each type of post that has been totalized,
Including
Wherein the post type, at least, a post for the purpose of diffusion of posts, the information processing method comprising <br/> include a post intended to introduce the articles on a particular subject. Computer
Extraction means for extracting one or more posts about a particular subject;
A counting means for counting each extracted post for each type of post;
Display means for displaying total information for each type of post;
A program to function as
Wherein the post type, at least, a post for the purpose of diffusion of posts, program characterized <br/> include a post intended to introduce the articles on a particular subject. Extracting means of the information processing apparatus for extracting one or more posts related to a specific object;
  A step in which the counting means of the information processing device counts each extracted post for each type of post;
  A display unit of the information processing apparatus, a step of displaying the number of posts for each type of post in a time-series graph,
  Annotating means of the information processing device, annotating the time-series graph, annotating a post,
  Including
  The content of the annotation is a display of topics extracted for each type of post and the number of cases for each topic.
An information processing method, comprising:   Computer
  Extraction means for extracting one or more posts about a particular subject;
  A counting means for counting each extracted post for each type of post;
  Display means for displaying the number of posts for each type of post in a time-series graph;
  Annotating means for giving an annotation on a post to the time-series graph,
  A program to function as
  The contents of the annotation indicate topics extracted for each type of post and the number of cases for each topic.
A program characterized by that:

Images