Detection of manipulation of social media content

• US 10,237,226 B2
• Filed: 11/30/2015
• Issued: 03/19/2019
• Est. Priority Date: 11/30/2015
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Ganci, Jr., John M., Rakshit, Sarbajit K., Sahota, Neil, Trim, Craig M.
• Primary Examiner(s): Wang, Liang Che A
• Assistant Examiner(s): Woldemariam, Ayele F
• Application Number:
  US14/953,777
• Publication Number:
  US 20170155613A1
• Time in Patent Office: 1,205 Days
• CPC Class Codes: G06Q 10/10 Office automation; Time management
• CPC Class Codes: G06Q 30/0241 Advertisements
• CPC Class Codes: G06Q 50/01 Social networking
• CPC Class Codes: H04L 51/212 using filtering or selective blocking
• CPC Class Codes: H04L 51/52 for supporting social networking services
• CPC Class Codes: H04L 67/306 User profiles

Abstract

A method for filtering content of a social network comprising a plurality of users. The method includes the steps of: identifying one or more relationships among the plurality of users of the social network; determining a strength of each of the identified one or more relationships among the plurality of users of the social network; determining, based at least in part on a determined strength, a reputation value for one or more of the plurality of users of the social network; detecting manipulated social media content using at least one of the identified relationships, determined strengths, and reputation values; categorizing the detected manipulated social media content into one or more categories, wherein the categorization is based at least in part on a confidence level of the detected manipulation; and filtering, based at least in part on said categorization, the detected manipulated social media content.

Claims

1. A method for filtering content of a social network comprising a plurality of users and a plurality of social media content associated with the plurality of users, the method comprising the steps of:

identifying, by a processor in communication with the social network, one or more relationships among the plurality of users of the social network;

determining, by the processor, a strength of each of the identified one or more relationships among the plurality of users of the social network;

determining, by the processor and based at least in part on a determined strength, a reputation value for one or more of the plurality of users of the social network;

detecting, by the processor, manipulated social media content using at least one of the identified relationships, determined strengths, and reputation values;

determining, by the processor, a confidence level of manipulation of a manipulated social media content detected by the processor, wherein the confidence level is determined at least in part on a comparison of the manipulated social media content detected by the processor to information about one or more of the plurality of users, wherein the processor is configured to assign a high confidence level when the information about the one or more of the plurality of users contradicts the social media content, and is further configured to assign a low confidence level when the processor is unable to determine, based on a comparison to the information about the one or more of the plurality of users, a likelihood of manipulation of the social media content;

categorizing, by the processor, the detected manipulated social media content into one or more categories, wherein the categorization is based at least in part on the determined confidence level; and

filtering, by the processor and based at least in part on said categorization, the detected manipulated social media content,

wherein said determining a reputation value step comprises the steps of;

identifying two or more users participating in one of the identified relationships;

analyzing one or more interactions between the two or more users;

identifying and analyzing one or more interactions between one of the two or more users and a user of the social network other than the users participating in the identified relationship; and

comparing the analysis of the one or more interactions between the two or more users to the analysis of one or more interactions between one of the two or more users and a user of the social network other than the users participating in the identified relationship.

2. The method of claim 1, wherein the one or more relationships are defined based at least in part on one or more interactions between the plurality of users of the social network.

3. The method of claim 2, wherein said strength is determined at least in part by semantic analysis of the one or more interactions.

4. The method of claim 1, further comprising the step of storing the one or more relationships, determined relationship strengths, and/or categorized manipulated social media content in a database.

5. The method of claim 1, wherein said filtering step comprises removing a category of detected manipulated social media content.

6. The method of claim 1, wherein said filtering step comprises removing all detected manipulated social media content.

7. A system for filtering content of a social network comprising a plurality of users, the system comprising:

a processor in communication with a social network comprising a plurality of users and further comprising a plurality of social media content items;

wherein the processor is configured to;

identify one or more relationships among the plurality of users of the social network;

determine a strength of each of the identified one or more relationships among the plurality of users of the social network;

determine, based at least in part on a determined strength, a reputation value for one or more of the plurality of users of the social network;

detect manipulated social media content using at least one of the identified relationships, determined strengths, and reputation values;

determine a confidence level of manipulation of a manipulated social media content detected by the processor, wherein the confidence level is determined at least in part on a comparison of the manipulated social media content detected by the processor to information about one or more of the plurality of users, wherein the processor is configured to assign a high confidence level when the information about the one or more of the plurality of users contradicts the social media content, and is further configured to assign a low confidence level when the processor is unable to determine, based on a comparison to the information about the one or more of the plurality of users, a likelihood of manipulation of the social media;

categorize the detected manipulated social media content into one or more categories, wherein the categorization is based at least in part on the determined confidence level filter, based at least in part on said categorization, the detected manipulated social media content, wherein the processor is configured to determine the reputation value through the steps of;

identifying two or more users participating in one of the identified relationships;

analyzing one or more interactions between the two or more users;

identifying and analyzing one or more interactions between one of the two or more users and a user of the social network other than the users participating in the identified relationship; and

comparing the analysis of the one or more interactions between the two or more users to the analysis of one or more interactions between one of the two or more users and a user of the social network other than the users participating in the identified relationship.

8. The system of claim 7, wherein the one or more relationships are defined based at least in part on one or more interactions between the plurality of users of the social network.

9. The system of claim 8, wherein said strength is determined at least in part by semantic analysis of the one or more interactions.

10. The system of claim 7, wherein the system further comprises a database, the database configured to store one or more of the relationships, determine relationship strengths, and/or categorized manipulated social media content in a database.

11. The system of claim 7, wherein the processor is configured to filter the social media content by removing a category of detected manipulated social media content.

12. The system of claim 7, wherein the processor is configured to remove all detected manipulated social media content.

13. A computer program product for characterizing content of a social network, the computer program product comprising a computer readable storage medium having program instructions embodied therewith, wherein the computer readable storage medium is not a transitory signal per se, the program instructions readable by a computer to cause the computer to perform a method comprising:

identifying one or more relationships among the plurality of users of the social network;

determining a strength of each of the identified one or more relationships among the plurality of users of the social network;

determining, based at least in part on a determined strength, a reputation value for one or more of the plurality of users of the social network;

detecting manipulated social media content using at least one of the identified relationships, determined strengths, and reputation values;

determining, by the processor, a confidence level of manipulation of a manipulated social media content detected by the processor, wherein the confidence level is determined at least in part on a comparison of the manipulated social media content detected by the processor to information about one or more of the plurality of users, wherein the processor is configured to assign a high confidence level when the information about the one or more of the plurality of users contradicts the social media content, and is further configured to assign a low confidence level when the processor is unable to determine, based on a comparison to the information about the one or more of the plurality of users, a likelihood of manipulation of the social media content;

categorizing the detected manipulated social media content into one or more categories, wherein the categorization is based at least in part on the determined confidence level; and

filtering, based at least in part on said categorization, the detected manipulated social media content, wherein said determining a reputation value step comprises the steps of;

identifying two or more users participating in one of the identified relationships;

analyzing one or more interactions between the two or more users;

identifying and analyzing one or more interactions between one of the two or more users and a user of the social network other than the users participating in the identified relationship; and

comparing the analysis of the one or more interactions between the two or more users to the analysis of one or more interactions between one of the two or more users and a user of the social network other than the users participating in the identified relationship.

14. The computer program product of claim 13, wherein the one or more relationships are defined based at least in part on one or more interactions between the plurality of users of the social network.

15. The computer program product of claim 14, wherein said strength is determined at least in part by semantic analysis of the one or more interactions.

16. The computer program product of claim 13, further comprising the step of storing the one or more relationships, determine relationship strengths, and/or categorized manipulated social media content in a database.

17. The computer program product of claim 13, wherein said filtering step comprises removing a category of detected manipulated social media content.