WO2020098157A1

WO2020098157A1 - Rumor spread risk analysis method and apparatus, and computer-readable storage medium

Info

Publication number: WO2020098157A1
Application number: PCT/CN2019/073548
Authority: WO
Inventors: 黄博; 毕野; 吴振宇; 王建明; 肖京
Original assignee: 平安科技（深圳）有限公司
Priority date: 2018-11-12
Filing date: 2019-01-28
Publication date: 2020-05-22
Also published as: CN109657906B; CN109657906A

Abstract

A rumor spread risk analysis method, comprising: acquiring social data of social network platform users (101); calculating effective distances from each user to all other users on the basis of the social data (102); using the effective distances from each user to all other users to calculate the length of the shortest effective path from each user to all other users (103); and analyzing the spread risk by each user according to the length of the shortest effective path from each user to all other users (104). The present application also relates to a rumor spread risk analysis apparatus, a computer non-volatile storage medium, and a computer device.

Description

Analysis method and device of rumor spreading risk, computer readable storage medium

This application requires the priority of the Chinese patent application submitted to the Chinese Patent Office on November 12, 2018, with the application number 2018113407137 and the application name "Analysis Method and Device for Rumor Propagation Risk, Storage Media, and Computer Equipment". Incorporated by reference in the application.

Technical field

The present application relates to the technical field of social network platforms, and in particular, to a method and device for analyzing the risk of spreading rumors, and a computer-readable storage medium.

Background technique

In recent years, the massive emergence of social platforms and the continuous expansion of network users have created new opportunities for the construction and development of the Internet. Social platforms are an important place for people to share and obtain information, but while providing convenience for people ’s daily lives, It has also become a breeding ground for many Internet rumors. With the help of the large user base of social platforms, the spread and spread of rumors have been increased unprecedentedly, posing a serious threat to social harmony and stability.

At present, only one qualitative measurement method can be given for measuring the risk of spreading rumors in the context of Internet social platforms. For example, accounts with many fans will spread rumors more quickly, or accounts with more information will spread rumors more quickly. . This qualitative measurement method has no accurate scientific basis, and the risk of spreading rumors in social platforms cannot be accurately measured.

Summary of the invention

In view of this, the present application provides a method and device for analyzing the risk of spreading rumors, and a computer-readable storage medium, to achieve quantitative calculation of the risk of spreading rumors.

According to one aspect of the present application, a method for analyzing the risk of spreading rumors is provided, which includes:

Obtain social data of users of social network platforms;

Based on the social data, calculate the effective distance from each user to all other users;

Use the effective distance from each user to all other users to calculate the length of the shortest effective path from each user to all other users, where the shortest effective path from any user to any other user The length is the sum of the effective distance from the any user to the other user or a plurality of effective distances that can connect the any user to the other user;

According to the length of the shortest effective path from each user to all other users, the propagation risk of each user is analyzed.

According to another aspect of the present application, there is provided an apparatus for analyzing the risk of spreading rumors, which includes:

Social data acquisition unit, used to acquire social data of social network platform users;

An effective distance calculation unit, used to calculate the effective distance from each user to all other users according to the social data;

An effective path calculation unit, configured to calculate the length of the shortest effective path from each user to all other users by using the effective distance from each user to all other users, wherein any user to any other user The length of the shortest effective path of a user is the sum of the effective distances from the any user to the other user or the multiple effective distances that can connect the any user to the other user;

The propagation risk analysis unit is configured to analyze the propagation risk of each user according to the length of the shortest effective path from each user to all other users.

According to yet another aspect of the present application, a computer non-volatile readable storage medium is provided, on which computer readable instructions are stored, and when the computer readable instructions are executed by a processor, the following steps are realized:

Obtain social data of users of social network platforms;

According to yet another aspect of the present application, there is provided a computer device, including a memory, a processor, and computer readable instructions stored on the memory and executable on the processor, the processor implementing the computer readable instructions The following steps:

Obtain social data of users of social network platforms;

With the above technical solutions, a method and device for analyzing the spread of rumors and a computer-readable storage medium provided by the present application use the social data of users on the social platform to quantify the effective distance between users to determine the distance between users The shortest length of the effective path is used for quantitative analysis of the propagation risk. In the prior art solution, the user's propagation risk can only be qualitatively determined according to the number of users' fans or the number of messages posted by the user. This solution is based on the user's social data and quantitatively analyzes the user's communication risk, which is more conducive to the subsequent management and control of the user's message transmission on the social platform according to the communication risk.

BRIEF DESCRIPTION

The drawings described herein are used to provide a further understanding of the present application and form a part of the present application. The schematic embodiments and descriptions of the present application are used to explain the present application and do not constitute an undue limitation on the present application. In the drawings:

FIG. 1 shows a schematic flowchart of a method for analyzing a rumor spreading risk provided by an embodiment of the present application;

FIG. 2 shows a schematic flowchart of another method for analyzing a rumor spreading risk provided by an embodiment of the present application;

3 shows a schematic diagram of a message propagation path between users of a social network platform provided by an embodiment of the present application;

4 shows a schematic structural diagram of an apparatus for analyzing a rumor spreading risk provided by an embodiment of the present application;

FIG. 5 shows a schematic structural diagram of another apparatus for analyzing a rumor spreading risk provided by an embodiment of the present application;

FIG. 6 shows a schematic diagram of the physical structure of a computer device provided by an embodiment of the present application.

detailed description

Hereinafter, the present application will be described in detail with reference to the drawings and in conjunction with the embodiments. It should be noted that the embodiments in the present application and the features in the embodiments can be combined with each other if there is no conflict.

In this embodiment, an analysis of the risk of spreading rumors is provided. As shown in FIG. 1, the method includes:

Step 101: Obtain social data of users of a social network platform.

Among them, the social data may mainly include reading data, like data, comment data, etc. of a user's texts, pictures, videos and other messages posted by other users on a social network platform. For example, the social data may record the like data of the articles that user A forwards to user B, and the comment data of user B sharing the video with user C, and so on.

It should be noted that social data has "directivity", and the social data of user A to user B is different from the social data of user B to user A.

Step 102: Based on the social data, calculate the effective distance from each user to all other users.

Specifically, based on data such as reading, likes, and comments between users, the effective distance between users is calculated. The effective distance from one user to another user reflects the influence of one user on another user, or it is a The importance of a user to another user. For example, using the social data of user A to user B to calculate the effective distance from user A to user B, using the effective distance from user A to user B can measure the influence of user A on user B.

Similarly, since the social data of user A to user B is different from the social data of user B to user A, the effective distance from user A to user B is also different from the effective distance from user B to user A.

Step 103: Use the effective distance from each user to all other users to calculate the length of the shortest effective path from each user to all other users, where the length of the shortest effective path from any user to any other user is any user The effective distance to any other user or the sum of multiple effective distances that can connect any user to any other user.

It should be noted that the effective path between users and the effective distance between users are not completely equivalent. The effective path between users represents the entire distance that a user travels to another user after posting, analyzing, or forwarding a message on the social platform. Specifically, suppose there are 4 users on the social platform, which are user A. , B, C, D, the effective path of user A's message to user D can be AD, ACD, or ABD, or ABCD, or ACBD. Therefore, the effective distance between users is used to calculate the length of each effective path, and the length of the shortest effective path between users is obtained.

Step 104: Based on the length of the shortest effective path from each user to all other users, analyze the propagation risk of each user.

The length of the shortest effective path between users reflects the closest propagation path when a user spreads a message to another user, that is, the fastest path for rumors. According to the length of the shortest effective path, the user ’s risk of spreading rumors is evaluated. It helps to further manage and control the spread of user rumors based on the user's communication risk.

By applying the technical solution of this embodiment, the user ’s social data of the social platform is used to quantify the effective distance between users, so as to determine the shortest length of the effective path between users, and perform quantitative analysis of the communication risk. In the solution, the user's communication risk can only be characterized based on the number of users' fans or the number of messages posted by the user. Compared with the existing technology, this solution is based on the user's social data and quantitatively analyzes the user's communication risk. It is beneficial for the subsequent management and control of users' news spreading on social platforms according to the spreading risks.

Further, as a refinement and expansion of the specific implementation of the above embodiment, in order to fully explain the specific implementation process of this embodiment, another method for analyzing the risk of spreading rumors is provided. As shown in FIG. 2, the method includes:

Step 201: Obtain social data of users of a social network platform.

Obtain data such as the number of likes, comments, and readings of all messages posted by other users on each social network platform.

Step 202: Calculate the influence Pmn of user m to user n according to the first influence calculation formula. The first influence calculation formula is:

Among them, social data includes the number of interactions between users, Nmn represents the number of interactions of user m with user n, Nm represents the number of interactions of user m with all users, m is greater than or equal to 1 and less than or equal to the number of users K, n is greater Or equal to 1 and less than or equal to K, m ≠ n.

Specifically, on the social networking platform, the number of interactions Nmn of any user m likes, comments, and readings of messages posted by any other user n, and the likes, comments, and readings of users m to messages posted by all other users, etc. The number of interactions Nm, and the proportion of Nmn to Nm is the influence of user m on user n, and it can also be said that the importance of user m on user n. The greater the influence of user m on user n, it means that if user m is in The rumors published on the social network platform are more likely to affect user n, and the influence Pmn of user m on user n is calculated to provide a data basis for subsequent quantitative analysis of communication risks.

In another embodiment, the influence Pmn of the user m to the user n includes the like influence Pmn1, the reading influence Pmn2, and the comment influence Pmn3. The calculation method of the influence of the user m to the user n Pmn may also be as follows achieve:

According to the fourth influence calculation formula, calculate the influence Pmn of the user m to the user n, and the fourth influence calculation formula is:

Among them, the like influence Pmn1, reading influence Pmn2, and comment influence Pmn3 are the number of likes, readings, and comments that user m publishes to user n. The number of times and the number of comments.

In addition, the ratio of the number of likes, readings, and comments of user m to the message posted by user n to the share of the number of likes, readings, and comments of user m to all users can also be counted to obtain the influence of likes Pmn1 , Reading influence Pmn2 and comment influence Pmn3, so as to obtain the average value as the influence Pmn of user m to user n.

It should be noted that, according to the importance of like influence Pmn1, reading influence Pmn2, and comment influence Pmn3 in influence Pmn, each influence can be weighted to obtain a weighted sum to obtain user m vs user n The influence of Pmn, the specific weighting method is not limited here.

For example, for a social networking platform, reading data has the greatest influence on the spread of messages from user m to user n, and the weight of reading influence is set to 0.5; the influence of comment data on the spread of messages is second, and the weight of comment influence Set to 0.3; the likes data has the least influence on the message spread. Set the weight of likes influence to 0.2, then the formula for calculating the influence Pmn of user m to user n is:

Pmn = 0.2 * Pmn1 + 0.5 * Pmn2 + 0.3 * Pmn3.

In addition, the user's interaction data is not limited to reading data, comment data and like data. Correspondingly, the influence is not limited to reading influence, comment influence and like influence. The interaction data can also be user m's Collection data, that is, the number of times user m has collected messages posted by user n, and the number of times user m has collected messages posted by users across the network, and the interaction data can also be user m's forwarding data, that is, user m's forwarding of messages posted by user n The number of times, and the number of times user m forwards messages posted by users across the network.

The method for calculating the influence Pmn of the user m to the user n may adopt any one of the above or other influence calculation methods.

Step 203: Calculate the effective distance dmn from user m to user n according to the effective distance calculation formula. The effective distance calculation formula is:

dmn = 1-logPmn.

According to the influence Pmn of user m on user n, calculate the effective distance dmn from user m to user n. The shorter the effective distance, the shorter the propagation distance of the message posted on behalf of user m to user n, and it can also reflect the message posted by user m It is easier to spread to user n. If user m publishes rumors, it will easily affect user n.

Step 204: Establish an effective path set Smn from user m to user n, and Smn includes all effective paths from user m to user n.

Specifically, all effective paths from user m to user n are counted to form an effective path set Smn, and the set Smn records all effective paths in which messages are directly or indirectly propagated from user m to user n. Specific examples are as follows:

FIG. 3 shows a schematic diagram of a message propagation path between users of a social network platform provided by an embodiment of the present application. As shown in Figure 3, there are users n1, n2, n3, and n4 in the network platform. If n1 publishes a message, all effective paths propagating to n4 are two, namely: the first, n1-n2-n4; Two, n1-n3-n4.

Step 205: Calculate the length len (Smn) of any effective path from user m to user n in the effective path set Smn to obtain the shortest effective path length Dmn from user m to user n.

Specifically, the length of all effective paths in the effective path set Smn is calculated to obtain the shortest effective path length Dmn of user m and user n, that is, the shortest length of message propagation from user m to user n.

It should be noted that when a user propagates a message to another user, the direct propagation path is not necessarily shorter than the indirect propagation path. For example, as shown in FIG. 3, the propagation path from user n1 to user n2 includes: the first one, n1-n2; the second one, n1-n3-n4-n2. Obviously, in the first path, user n1 directly propagates the message to user n2, while in the second path, user n1 publishes the message, and then propagates to user n2 after passing through user n3 and user n4. The length of the first path is d12, and the length of the second path is d13 + d34 + d42. If d12 = 10, d13 = 1, d34 = 2, and d42 = 3, it is obvious that the length of the first path 10 is greater than the first Two path lengths (1 + 2 + 3) = 6.

In addition, as shown in FIG. 3, there is no effective path from user n2 to user n3, that is, the message posted by user n2 cannot be propagated to user n3. At this time, the shortest effective path length from user n2 to user n3 It is recorded as a preset value. This preset value can take the longest effective path length between all users, or it can directly set a fixed value for subsequent analysis of the influence between users. Because the message posted by user n2 cannot be propagated to user n3, the fixed value here is preferably set to be slightly longer than the longest effective path length between all users. For the preset value here, this application is not limited here.

In step 206, the shortest effective path length Dmn from user m to user n is used to calculate the average value Dm of influence of user m to all other users and the average value D of influence of all users.

In the above embodiment, specifically, according to the second influence calculation formula, the average influence Dm of the user m to all users is calculated, and the second influence calculation formula is:

According to the third influence calculation formula, calculate the average influence D of all users. The third influence calculation formula is:

Specifically, according to the shortest effective path length from user m to any other user, the average value Dm of user m's influence on other users is calculated, and Dm reflects the average influence of user m on users across the network. After obtaining the average influence of each user, the average value of the arithmetic is taken as the average influence of the entire network. By comparing the average influence of each user with the average influence of users across the network, a simple analysis of the user's transmission risk compared to other users can be performed.

For example, the average influence of user m on other users is 9, and the average influence of users across the entire network is 5, indicating that user m ’s influence is larger than the overall influence of users across the entire network. If user m is social Publishing rumors on the online platform may have a greater impact on other users on the social platform. If user m publishes rumors, it is more likely to cause rumors to spread.

Step 207: Analyze the propagation risk of user m according to the average influence Dm of user m to all other users and the average influence D of all users.

In the above embodiment, specifically, the propagation risk score Rm of the user m is calculated according to the propagation risk score calculation formula, and the propagation risk score calculation formula is:

Obviously, through the propagation risk score calculation formula, you can quantitatively analyze the propagation risk of any user based on the average influence of any user and the average influence of all users, give their specific risk scores, and use the user's communication risk Scoring strictly monitors and guards against the spread of news on the online platform by users with higher risks.

Specifically, according to the user's communication risk score and the standard threshold value, the user's rumor transmission risk can be judged, the high-risk users should be focused on prevention, and the release of their messages should be strictly controlled.

For example, after calculating the propagation risk score of user m is 80, and the standard threshold is 60, user m can be classified as a rumor spread risk user, and the social network platform supervision system is controlled to focus on the messages posted by user m on the network platform. Monitor, or interview user m in advance to remind him that he is a user with greater influence, and he should pay attention to the content of his own dissemination message, so as not to cause adverse effects to others.

By applying the technical solution of this embodiment, using the social data of users on the social platform, quantitative analysis of the effective distance of message propagation between users and the shortest effective path length, thereby calculating the influence of each user and the average influence of users, and then analyzing The risk of users' rumors spreading provides a reliable basis for the prevention of rumors spreading on social network platforms.

Further, as a specific implementation of the method of FIG. 1, an embodiment of the present application provides an apparatus for analyzing the risk of spreading rumors. As shown in FIG. 4, the apparatus includes: a social data acquisition unit 41, an effective distance calculation unit 42, and the shortest effective Path acquisition unit 43, propagation risk analysis unit 44.

The social data acquisition unit 41 is used to acquire social data of users of the social network platform;

The effective distance calculation unit 42 is used to calculate the effective distance from each user to all other users according to social data;

The shortest effective path obtaining unit 43 is used to calculate the length of the shortest effective path from each user to all other users by using the effective distance from each user to all other users, wherein the shortest effective path from any user to any other user The length is the effective distance from any user to any other user or the sum of multiple effective distances that can connect any user to any other user;

The propagation risk analysis unit 44 is configured to analyze the propagation risk of each user according to the length of the shortest effective path from each user to all other users.

In a specific application scenario, as shown in FIG. 5, the effective distance calculation unit 42 specifically includes: an influence calculation unit 421 and an effective distance calculation unit 422;

The influence calculation unit 421 is configured to calculate the influence Pmn of the user m to the user n according to the first influence calculation formula, and the first influence calculation formula is:

Among them, the social data includes the number of interactions between users, Nmn represents the number of interactions between user m and user n, Nm represents the number of interactions between user m and all users, m is greater than or equal to 1 and less than or equal to the number of users K, n is greater than Or equal to 1 and less than or equal to K, m ≠ n;

The effective distance calculation unit 422 is used to calculate the effective distance dmn from user m to user n according to the effective distance calculation formula. The effective distance calculation formula is:

dmn = 1-logPmn.

The shortest effective path acquisition unit 43 specifically includes: an effective path set establishment unit 431 and an effective path length calculation unit 432;

The effective path set establishing unit 431 is used to establish an effective path set Smn from user m to user n, and Smn includes all effective paths from user m to user n;

The effective path length calculation unit 432 is configured to separately calculate the length len (Smn) of any effective path from the user m to the user n in the effective path set Smn to obtain the shortest effective path length Dmn from the user m to the user n.

In a specific application scenario, in order to quantitatively analyze the user's communication risk, the communication risk analysis unit 44 specifically includes: an average influence calculation unit 441 and a communication risk analysis sub-unit 442;

The average influence calculation unit 441 is used to calculate the average influence Dm of the user m to all other users and the average influence D of all users by using the shortest effective path length Dmn of the user m to the user n;

The propagation risk analysis sub-unit 442 is used to analyze the propagation risk of user m according to the mean value Dm of influence of user m to all other users and the mean value D of influence of all users.

The average influence calculation unit 441 is specifically used to calculate the average influence Dm of the user m to all users according to the second influence calculation formula, and the second influence calculation formula is:

The propagation risk analysis sub-unit 442 is specifically used to calculate the propagation risk score Rm of the user m according to the propagation risk score calculation formula, and the propagation risk score calculation formula is:

In a specific application scenario, the influence Pmn of the user m to the user n includes the like influence Pmn1, the reading influence Pmn2, and the comment influence Pmn3;

The influence calculation unit 421 is also used to calculate the influence Pmn of the user m to the user n according to the fourth influence calculation formula, and the fourth influence calculation formula is:

Among them, the like influence Pmn1, the reading influence Pmn2 and the comment influence Pmn3 are the number of likes, readings and comments of the user m on the message posted by the user n, respectively , The proportion of readings and comments.

It should be noted that, for other corresponding descriptions of each functional unit involved in an apparatus for analyzing a rumor propagation risk provided by an embodiment of the present application, reference may be made to the corresponding descriptions in FIG. 1 and FIG. 2, and details are not described herein again.

Based on the method shown in FIG. 1 above, correspondingly, an embodiment of the present application also provides a computer non-volatile readable storage medium on which computer readable instructions are stored, and when the program is executed by the processor, the following steps are realized : Obtain the social data of the users of the social network platform; calculate the effective distance from each user to all other users based on the social data; use the effective distance from each user to all other users to calculate the shortest effective path from each user to all other users The length of the shortest effective path from any user to any other user is the effective distance from any user to any other user or the sum of multiple effective distances that can connect any user to any other user; From the length of the shortest effective path of each user to all other users, analyze the propagation risk of each user.

Based on this understanding, the technical solution of the present application can be embodied in the form of a software product, which can be stored in a non-volatile memory (can be a CD-ROM, U disk, mobile hard disk, etc.), including several instructions It is used to enable a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the method described in each implementation scenario of the present application.

Based on the embodiment of the method shown in FIG. 1 and the apparatus for analyzing the risk of spreading rumors shown in FIG. 4, the embodiment of the present application further provides a physical structure diagram of a computer device, as shown in FIG. : Processor 51, memory 52, and computer readable instructions stored on the memory 52 and executable on the processor, wherein the memory 52 and the processor 51 are both set on the bus 53 when the processor 51 executes the program The following steps are implemented: acquiring social data of users of the social networking platform; calculating the effective distance from each user to all other users based on the social data; calculating the effective distance from each user to all other users using the effective distance from each user to all other users The length of the shortest effective path, where the length of the shortest effective path from any user to any other user is the effective distance from any user to any other user or the multi-segment effective distance that can connect any user to any other user And; According to the length of the shortest effective path from each user to all other users, analyze the propagation risk of each user. The computer device also includes a bus 53 configured to couple the processor 51 and the memory 52.

Optionally, the computer device may further include a user interface, a network interface, a camera, a radio frequency (Radio Frequency) circuit, a sensor, an audio circuit, a WI-FI module, and so on. The user interface may include a display (Display), an input unit such as a keyboard, and the like, and the optional user interface may also include a USB interface, a card reader interface, and the like. The network interface may optionally include a standard wired interface, a wireless interface (such as a Bluetooth interface, and a WI-FI interface).

The memory may also include an operating system and a network communication module. An operating system is a program that manages the hardware and software resources of a computer device, and supports the operation of information processing programs and other software and / or programs. The network communication module is used to realize communication between various components inside the memory, and to communicate with other hardware and software in the physical device.

Through the description of the above embodiments, those skilled in the art can clearly understand that the present application can be implemented by means of software plus a necessary general hardware platform, or the technical solution of this embodiment can be implemented by hardware.

Claims

An analysis method for the risk of spreading rumors, which is characterized by:

Obtain social data of users of social network platforms;

Based on the social data, calculate the effective distance from each user to all other users;

Use the effective distance from each user to all other users to calculate the length of the shortest effective path from each user to all other users, where the shortest effective path from any user to any other user The length is the sum of the effective distance from the any user to the other user or a plurality of effective distances that can connect the any user to the other user;

According to the length of the shortest effective path from each user to all other users, the propagation risk of each user is analyzed.
The method according to claim 1, wherein the calculating the effective distance from each user to all other users according to the social data specifically includes:

According to the first influence calculation formula, the influence Pmn of the user m to the user n is calculated, and the first influence calculation formula is:

Wherein, the social data includes the number of interactions between the users, Nmn represents the number of interactions of the user m with the user n, Nm represents the number of interactions of the user m with all the users, m is greater than or equal to 1 and less than or equal to the number of users K, n greater than or equal to 1 and less than or equal to K, m ≠ n;

According to the effective distance calculation formula, calculate the effective distance dmn from the user m to the user n, the effective distance calculation formula is:

dmn = 1-logPmn.
The method according to claim 2, wherein the use of the effective distance from each user to all other users to calculate the length of the shortest effective path from each user to all other users, This includes:

Establish an effective path set Smn from the user m to the user n, and Smn includes all effective paths from the user m to the user n;

The length len (Smn) of any effective path from the user m to the user n in the effective path set Smn is calculated separately to obtain the shortest effective path length Dmn from the user m to the user n.
The method according to claim 3, wherein the analyzing the propagation risk of each user according to the length of the shortest effective path from each user to all other users specifically includes:

Using the shortest effective path length Dmn from the user m to the user n to calculate the average influence Dm of the user m to all other users and the average influence D of all users;

According to the mean value Dm of the influence of the user m to all other users and the mean value D of the influence of all the users, the propagation risk of the user m is analyzed.
The method according to claim 4, characterized in that

According to the second influence calculation formula, the mean value Dm of the influence of the user m to all other users is calculated, and the second influence calculation formula is:

According to the third influence calculation formula, calculate the mean value D of all users' influence, and the third influence calculation formula is:
The method according to claim 5, characterized in that, based on the mean value Dm of the influence of the user m to all other users and the mean value D of the influence of all the users, the propagation risk of the user m is analyzed , Including:

The propagation risk score Rm of the user m is calculated according to the propagation risk score calculation formula, and the propagation risk score calculation formula is:
The method according to any one of claims 2 to 6, wherein the influence Pmn of the user m on the user n includes a like influence Pmn1, a reading influence Pmn2, and a comment influence Pmn3;

The calculation of the influence Pmn of user m on user n specifically includes:

Calculate the influence Pmn of the user m on the user n according to the fourth influence calculation formula, and the fourth influence calculation formula is:

Wherein, the like influence Pmn1, the reading influence Pmn2 and the comment influence Pmn3 are respectively the number of likes, readings and comments of the message posted by the user m to the user n accounting for the user The proportion of the number of likes, readings and comments on messages posted by all the users.
An analysis device for the risk of spreading rumors, characterized by including:

Social data acquisition unit, used to acquire social data of social network platform users;

An effective distance calculation unit, used to calculate the effective distance from each user to all other users according to the social data;

The shortest effective path obtaining unit is used to calculate the length of the shortest effective path from each user to all other users by using the effective distance from each user to all other users, wherein any user to other The length of the shortest effective path of any user is the sum of the effective distance from the any user to the other user or the multiple effective distances that can connect the any user to the other user;

The propagation risk analysis unit is configured to analyze the propagation risk of each user according to the length of the shortest effective path from each user to all other users.
The apparatus according to claim 1, wherein the effective distance calculation unit specifically includes:

An influence calculation unit, configured to calculate the influence Pmn of user m to user n according to a first influence calculation formula, and the first influence calculation formula is:

Wherein, the social data includes the number of interactions between the users, Nmn represents the number of interactions of the user m with the user n, Nm represents the number of interactions of the user m with all the users, m is greater than or equal to 1 and less than or equal to the number of users K, n greater than or equal to 1 and less than or equal to K, m ≠ n;

The effective distance calculation unit is configured to calculate the effective distance dmn from the user m to the user n according to the effective distance calculation formula, and the effective distance calculation formula is:

dmn = 1-logPmn.
The apparatus according to claim 9, wherein the shortest effective path acquisition unit specifically includes:

An effective path set establishing unit, configured to establish an effective path set Smn from the user m to the user n, and Smn includes all effective paths from the user m to the user n;

An effective path length calculation unit, used to calculate the length len (Smn) of any effective path from the user m to the user n in the effective path set Smn to obtain the shortest from the user m to the user n Effective path length Dmn.
The apparatus according to claim 10, wherein the propagation risk analysis unit specifically includes:

An average influence calculation unit, used to calculate the average influence Dm of the user m to all other users and the average influence D of all users by using the shortest effective path length Dmn of the user m to the user n;

The propagation risk analysis subunit is configured to analyze the propagation risk of the user m according to the mean value Dm of the influence of the user m to the all other users and the mean value D of the influence of all the users.
The device according to claim 11, characterized in that

The average influence calculation unit is specifically configured to calculate the average influence Dm of the user m to all other users according to a second influence calculation formula, and the second influence calculation formula is:

According to the third influence calculation formula, calculate the mean value D of all users' influence, and the third influence calculation formula is:
The device according to claim 12, characterized in that

The propagation risk analysis subunit is specifically configured to calculate the propagation risk score Rm of the user m according to a propagation risk score calculation formula, and the propagation risk score calculation formula is:
The device according to any one of claims 9 to 13, wherein the influence Pmn of the user m on the user n includes a like influence Pmn1, a reading influence Pmn2, and a comment influence Pmn3;

The influence calculation unit 421 is further configured to calculate the influence Pmn of the user m to the user n according to a fourth influence calculation formula, and the fourth influence calculation formula is:

Wherein, the like influence Pmn1, the reading influence Pmn2 and the comment influence Pmn3 are respectively the number of likes, readings and comments of the message posted by the user m to the user n accounting for the user The proportion of the number of likes, readings and comments on messages posted by all the users.
A computer non-volatile storage medium having computer readable instructions stored thereon, characterized in that, when the computer readable instructions are executed by a processor, a method for analyzing the risk of spreading rumors is implemented, including:

Obtain social data of users of social network platforms;

Based on the social data, calculate the effective distance from each user to all other users;

Use the effective distance from each user to all other users to calculate the length of the shortest effective path from each user to all other users, where the shortest effective path from any user to any other user The length is the sum of the effective distance from the any user to the other user or a plurality of effective distances that can connect the any user to the other user;

According to the length of the shortest effective path from each user to all other users, the propagation risk of each user is analyzed.
The computer non-volatile storage medium according to claim 15, wherein the computer-readable instructions are executed by the processor to implement the calculation of each user to all other users according to the social data Effective distance, including:

According to the first influence calculation formula, the influence Pmn of the user m to the user n is calculated, and the first influence calculation formula is:

Wherein, the social data includes the number of interactions between the users, Nmn represents the number of interactions of the user m with the user n, Nm represents the number of interactions of the user m with all the users, m is greater than or equal to 1 and less than or equal to the number of users K, n greater than or equal to 1 and less than or equal to K, m ≠ n;

According to the effective distance calculation formula, calculate the effective distance dmn from the user m to the user n, the effective distance calculation formula is:

dmn = 1-logPmn.
The computer non-volatile readable storage medium according to claim 15, wherein when the computer-readable instructions are executed by a processor, the utilization of the effective distance from each user to all other users is realized To calculate the length of the shortest effective path from each user to all other users, specifically including:

Establish an effective path set Smn from the user m to the user n, and Smn includes all effective paths from the user m to the user n;

The length len (Smn) of any effective path from the user m to the user n in the effective path set Smn is calculated separately to obtain the shortest effective path length Dmn from the user m to the user n.
A computer device, including a storage medium, a processor, and a computer program stored on the storage medium and executable on the processor, characterized in that, when the processor executes the program, a method for analyzing a risk of spreading rumors is implemented, including :

Obtain social data of users of social network platforms;

Based on the social data, calculate the effective distance from each user to all other users;

Use the effective distance from each user to all other users to calculate the length of the shortest effective path from each user to all other users, where the shortest effective path from any user to any other user The length is the sum of the effective distance from the any user to the other user or a plurality of effective distances that can connect the any user to the other user;

According to the length of the shortest effective path from each user to all other users, the propagation risk of each user is analyzed.
The computer device according to claim 18, characterized in that, when the processor executes the computer-readable instructions, the calculation of the effective distance from each user to all other users based on the social data is implemented, specifically including:

According to the first influence calculation formula, the influence Pmn of the user m to the user n is calculated, and the first influence calculation formula is:

Wherein, the social data includes the number of interactions between the users, Nmn represents the number of interactions of the user m with the user n, Nm represents the number of interactions of the user m with all the users, m is greater than or equal to 1 and less than or equal to the number of users K, n greater than or equal to 1 and less than or equal to K, m ≠ n;

According to the effective distance calculation formula, calculate the effective distance dmn from the user m to the user n, the effective distance calculation formula is:

dmn = 1-logPmn.
The computer device according to claim 19, characterized in that, when the processor executes the computer-readable instructions, the effective distance between each user and all other users is calculated to calculate the each The length of the shortest effective path from the user to all other users includes:

Establish an effective path set Smn from the user m to the user n, and Smn includes all effective paths from the user m to the user n;

The length len (Smn) of any effective path from the user m to the user n in the effective path set Smn is calculated respectively to obtain the shortest effective path length Dmn from the user m to the user n.