JP7609276B2 - Information quality measuring device, information quality measuring method and program - Google Patents

Description

The present invention relates to an information quality measuring device, an information quality measuring method, and a program.

As a method for measuring the information quality of a certain piece of content, for example, there is a method for measuring quality based on the number of unique users who viewed the content (number of viewing users). There is also a method for measuring quality based on the number of unique users who bookmarked the content (number of bookmarks). Still another method for measuring quality is based on the ratings given to the content (for example, "likes").

Patent No. 5848199

However, the number of views, the number of bookmarks, and the ratings of content can easily be manipulated by the content sender. For example, a content sender can impersonate a large number of individual users to inflate the number of views or bookmarks or to input ratings.

Furthermore, the basic figures used to measure the above quality are highly susceptible to the influence of the number of people who regularly and continuously pay attention to the sender of the content (for example, the number of followers), so there are issues regarding the validity of simply using these figures as a reference method for measuring quality.

The present invention has been made in consideration of the above points and aims to strengthen resistance to tampering in measuring the information quality of content.

In order to solve the above problem, the information quality measuring device has a collection unit that collects a plurality of second contents that cite a first content, and a measurement unit that identifies a third content among the plurality of second contents, in which the evaluation value of the second content is above a threshold, an index value indicating the uniqueness of the users who evaluated the second content is above a threshold, and a ratio of the number of users who evaluated the second content to the estimated number of views of the second content is above a threshold, and the ratio of the third content among the plurality of second contents is a value indicating the information quality of the first content.

Measurement of content information quality can be made more resistant to manipulation.

1 is a diagram illustrating an example of a hardware configuration of an information quality measuring device 10 according to an embodiment of the present invention. 1 is a diagram illustrating an example of a functional configuration of an information quality measuring device 10 according to an embodiment of the present invention. FIG. 2 is a diagram showing an example of the configuration of a post database 14. 10 is a flowchart illustrating an example of a processing procedure executed by an information quality measuring unit 12; FIG. 2 is a diagram showing an example of the configuration of an information quality recording database 15.

An embodiment of the present invention will now be described with reference to the drawings. Figure 1 is a diagram showing an example of the hardware configuration of an information quality measuring device 10 in an embodiment of the present invention. The information quality measuring device 10 in Figure 1 has a drive device 100, an auxiliary storage device 102, a memory device 103, a CPU 104, an interface device 105, etc., which are interconnected by a bus B.

The program that realizes the processing in the information quality measuring device 10 is provided by a recording medium 101 such as a CD-ROM. When the recording medium 101 storing the program is set in the drive device 100, the program is installed from the recording medium 101 via the drive device 100 into the auxiliary storage device 102. However, the program does not necessarily have to be installed from the recording medium 101, but may be downloaded from another computer via a network. The auxiliary storage device 102 stores the installed program as well as necessary files, data, etc.

When an instruction to start a program is received, the memory device 103 reads out and stores the program from the auxiliary storage device 102. The CPU 104 executes functions related to the information quality measuring device 10 in accordance with the program stored in the memory device 103. The interface device 105 is used as an interface for connecting to a network.

Figure 2 is a diagram showing an example of the functional configuration of an information quality measuring device 10 in an embodiment of the present invention. In Figure 2, the information quality measuring device 10 has a post collection unit 11, an information quality measurement unit 12, and an information quality response unit 13. Each of these units is realized by processing in which one or more programs installed in the information quality measuring device 10 are executed by the CPU 104. The information quality measuring device 10 also uses databases (storage units) such as a post database 14 and an information quality record database 15. Each of these databases can be realized, for example, using an auxiliary storage device 102, or a storage device that can be connected to the information quality measuring device 10 via a network.

The post collection unit 11 collects a number of posts (hereinafter referred to as "citing posts") that quote other posts (hereinafter referred to as "cited posts") from among posts published on an online social networking service (SNS), formats the collected results into a format conforming to the post database 14, and records the formatted post content in the post database 14. Fig. 3 is a diagram showing an example of the configuration of the post database 14. Fig. 3 shows the configuration of the post database 14 divided into two tables. The second table is a set of columns that continues from the first table.

As shown in FIG. 3, the post database 14 includes a record for each quoted post. Each record includes a UID, a user name, a quoted URL, the post content, a rating value, the number of favorite users, the number of favorited users, a list of users to whom a rating value has been assigned, and the like.

The UID is the UID (Unique Identifier) of the quoted post. A URI (Uniform Resource Identifier) may be used instead of the UID. The username is the account name of the poster of the quoted post. The quoted URL is the URL of the quoted post that is cited by the quoted post. The quoted URL is included in the quoted post. The post content is the content of the quoted post. The rating value is a numerical value (e.g., the number of "likes") indicating the rating of the quoted post on the Internet. The number of favorite users is the number of other users who are favorited by the poster of the quoted post (e.g., who are followed by the poster). The number of favorited users is the number of other users who like the poster (are interested in the poster (e.g., who follow the poster)). The list of users who assigned a rating value is a list of the usernames of users who assigned a rating value to the quoted post (e.g., who evaluated the quoted post).

As an example, the information quality measurement unit 12 aggregates quoted posts by quoted URL from the post database 14 by performing batch processing once a day (e.g., late at night) and measures the quality (information quality) of the quoted posts related to the quoted URL based on the quoted posts related to the quoted URL. The information quality measurement unit 12 records the measurement results in the information quality recording database 15.

When a user of the information quality measuring device 10 inputs a URL for which the user wants to know the information quality, the information quality response unit 13 outputs a response to the user including the information quality associated with the URL and stored in the information quality recording database 15.

The following describes the processing procedure executed by the information quality measurement unit 12. Figure 4 is a flowchart for explaining an example of the processing procedure executed by the information quality measurement unit 12.

In step S101, the information quality measurement unit 12 classifies all quoted posts stored in the post database 14 into sets (groups) of shared quoted URLs. At this time, normalization of the quoted URLs may be performed. More specifically, one possible method of normalization is to delete the query string in the URL. As a result of the above, a group is generated for each quoted URL.

Next, the information quality measurement unit 12 executes loop processing L1 including steps S102 to S106 for each quoted URL. The quoted URL being processed in loop processing L1 is referred to as the "target quoted URL." In addition, the set of quoted posts classified into the group of the target quoted URL is referred to as the "target quoted post set."

In step S102, the information quality measurement unit 12 assigns flag A to quoted posts from the target quoted post set whose evaluation value is greater than or equal to threshold value α.

Next, the information quality measurement unit 12 compiles the frequency of occurrence (frequency of occurrence in the target quoted post set) of each user name included in the "list of users assigned evaluation values" of each quoted post included in the target quoted post set (S103).

Next, the information quality measurement unit 12 calculates an index value indicating the independence (specificity) of the "user list to which an evaluation value has been assigned" of each quoted post included in the target quoted post set, and assigns a flag B to quoted posts for which the index value is equal to or greater than a threshold value β (S104). The index value for a certain quoted post may be calculated, for example, by subtracting from 1 the proportion of user names with the top n frequency of appearances tallied in step S103 in the "user list to which an evaluation value has been assigned" of the quoted post.

In other words, if we assume the existence of users who are highly likely to rate posts that contain the same quoted URL, it is conceivable that such users rate posts without examining them closely, and thus would end up being among the top n users here. Not including such users in the "list of users who assigned ratings" is thought to contribute to increasing independence (specificity).

Next, the information quality measurement unit 12 calculates the ratio of the list length of the "list of users who have given a rating value" of the quoted post (the number of user names in the list) to the "number of favorited users" of the quoted post for each quoted post included in the target quoted post set, and assigns a flag C to quoted posts for which the ratio is equal to or greater than a threshold m% (S105). In other words, a flag C is assigned to quoted posts for which the ratio of the number of users who have given a rating value to the number of followers of the poster is equal to or greater than a threshold m%. In recent SNS, since there is a function that allows posts to flow on the timelines of favorited users (≒ followers), it is considered that favorited users view the post with a high probability, and the degree of rating (≒ likes) for viewing can be said to be the quality of the information of the post, so the purpose of assigning a flag C to the corresponding quoted post is to. In other words, in this embodiment, the "number of favorited users" of a quoted post is treated as an estimate of the number of views of the quoted post.

Next, the information quality measurement unit 12 calculates the percentage of quoted posts in the target cited post set that are assigned all of the flags A, B, and C, and registers the percentage in the information quality recording database 15 in association with the target cited URL (S106). That is, the percentage is registered in the information quality recording database 15 as a value indicating the information quality of the cited post related to the target cited URL.

Figure 5 is a diagram showing an example of the configuration of the information quality recording database 15. As shown in Figure 5, the information quality recording database 15 stores, for each URL (each quoted URL), the information quality of the post related to that URL.

As described above, according to this embodiment, the information quality of a certain piece of content is evaluated based on the evaluation of other content that quotes the certain piece of content. Here, even if it is easy to tamper with the direct evaluation of the certain piece of content (number of views, number of bookmarks, evaluation value), it is considered difficult to perform similar tampering with a large number of pieces of content that quote the certain piece of content. Therefore, according to this embodiment, it is possible to strengthen the resistance to tampering in the measurement of the information quality of content.

Another feature is that it makes it possible to measure information quality by taking into account how well the content generated discussion.

In this embodiment, an example has been described in which posts on SNS are the subject of information quality measurement, but this embodiment is also effective for any content that is made public via a network such as the Internet and that may be quoted from other content, regardless of whether it is a post on a specific SNS.

In this embodiment, the post collection unit 11 is an example of a collection unit. The information quality measurement unit 12 is an example of a measurement unit. A cited post is an example of a first content. A cited post is an example of a second content.

Although the embodiments of the present invention have been described in detail above, the present invention is not limited to such specific embodiments, and various modifications and variations are possible within the scope of the gist of the present invention as described in the claims.

10 Information quality measurement device 11 Post collection unit 12 Information quality measurement unit 13 Information quality response unit 14 Post database 15 Information quality record database 100 Drive device 101 Recording medium 102 Auxiliary storage device 103 Memory device 104 CPU
105 Interface device B bus

Claims (3)

A collection unit that collects a plurality of second contents that cite the first content;
a measurement unit that identifies a third content among the plurality of second contents, the third content having an evaluation value equal to or greater than a threshold, an index value indicating the uniqueness of the users who have evaluated the second content equal to or greater than a threshold, and a ratio of the number of users who have evaluated the second content to an estimated value of the number of views of the second content equal to or greater than a threshold, and sets the ratio of the third content among the plurality of second contents as a value indicating information quality of the first content;
13. An information quality measuring device comprising: a collection step of collecting a plurality of second contents that cite the first content;
a measurement step of identifying a third content among the plurality of second contents, the third content having an evaluation value equal to or greater than a threshold, an index value indicating the uniqueness of the users who have evaluated the second content equal to or greater than a threshold, and a ratio of the number of users who have evaluated the second content to an estimated value of the number of views of the second content equal to or greater than a threshold, and determining the ratio of the third content among the plurality of second contents as a value indicating the information quality of the first content;
The information quality measurement method is characterized in that the above steps are executed by a computer. 2. A program for causing a computer to function as the information quality measuring device according to claim 1 .

Images