IP Library Granted Patent US 11,258,741
Granted Patent B2
US 11,258,741 · App. 16/541,785 · Granted Feb 22, 2022

Systems and methods for automatically identifying spam in social media comments

Inventors: Vijay Kumar (Karnataka, IN); Rajendran Pichaimurthy (Karnataka, IN); Madhusudhan Srinivasan (Karnataka, IN)
Assignee: Rovi Guides, Inc.
H04L51/12G06Q50/01H04L51/32
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 11,258,741
App. No.
16/541,785
Granted
Feb 22, 2022
Kind
B2
Abstract

Systems and methods are described herein for automatically identifying spam in social media comments based on a comparison of the content of a particular comment on a popular or trending post with content of other comments on the same or other popular or trending posts on the same or other social media platforms. Comments associated with each post are compared to determine whether content of a comment associated with one post is similar to, or matches, content associated with another post of a different trending topic. In response to determining that the content of a comment associated with one post is similar to the content of a comment associated with another post, the two comments are identified as spam, and a notification is generated for display to an administrator of the social media platform identifying the two comments as spam.

Claims (72)

1. A method for detecting spam on a plurality of social media platforms, the method comprising:

determining a plurality of trending topics;

identifying at least one post on each of the plurality of social media platforms related to each topic of the plurality of trending topics;

accessing a plurality of comments associated with each respective identified post corresponding to one of the plurality of social media platforms that the respective identified post was identified on;

generating a plurality of signatures for each of the plurality of comments, wherein each of the plurality of signatures comprises metadata;

comparing metadata of each of the plurality of comments associated with each respective identified post with metadata of each of the plurality of comments of each other respective identified post, wherein the metadata corresponds to each of the plurality of signatures, and wherein the plurality of comments associated with each respective identified post has not previously been identified as spam;

determining, based on the comparing, whether metadata of a first comment associated with a first identified post is similar to metadata of a second comment associated with a second identified post; and

in response to determining that the metadata of the first comment associated with the first identified post is similar to the metadata of the second comment associated with the second identified post:

identifying the first comment and the second comment as spam; and

generating for display, to each respective administrator of each of the plurality of the social media platforms on which the first comment and the second comment identified as spam were accessed, a notification comprising an identifier of the first comment and an identifier of the second comment.

2. The method of claim 1 , wherein the first identified post is located on a first social media platform and the second identified post is located on a second social media platform.

3. The method of claim 1 , wherein determining whether the metadata of the first comment associated with the first identified post is similar to the metadata of the second comment associated with the second identified post comprises:

generating a first signature corresponding to the metadata of the first comment and a second signature corresponding to the metadata of the second comment;

calculating a difference between the first signature and the second signature; and

determining, based on the calculating, whether the difference between the first signature and the second signature is below a threshold difference level.

4. The method of claim 3 , further comprising:

identifying a source of the first comment and a source of the second comment; and

determining whether the source of the first comment is the same as the source of the second comment.

5. The method of claim 1 , wherein determining whether the metadata of the first comment associated with the first identified post is similar to the metadata of the second comment associated with the second identified post comprises:

determining whether a portion of the first comment contains contact information;

in response to determining that the portion of the first comment contains contact information, determining, based on the processing, whether a portion of the second comment contains the contact information; and

in response to determining that the portion of the second comment contains the contact information, determining that the portion of the first comment is similar to the portion of the second comment.

6. The method of claim 1 , further comprising, in response to determining that the metadata of the first comment associated with the first identified post is not similar to the metadata of the second identified post:

identifying contact information in a portion of the first comment;

accessing a plurality of advertisements;

determining whether the contact information appears in an advertisement of the plurality of advertisements; and

in response to determining that the contact information appears in an advertisement of the plurality of advertisements, identifying the first comment as spam.

7. The method of claim 1 , further comprising, further in response to determining that the textual portions of the first comment associated with the first identified post is similar to the textual portions of the second comment associated with the second identified post:

comparing the textual portions of the first comment to an exclusion list having a plurality of entries identifying excluded textual portions;

determining, based on the comparing, whether the textual portions of the first comment matches at least one entry of the plurality of entries; and

in response to determining that the textual portions of the first comment matches at least one entry of the plurality of entries, identifying the first comment as not spam;

wherein identifying the first comment and the second comment as spam is in response to determining that the textual portions of the first comment does not match any entry of the plurality of entries.

8. The method of claim 7 , wherein the plurality of entries identifying excluded textual portions comprises characters representing emotional responses.

9. The method of claim 8 , wherein the characters representing emotional responses are alphanumeric characters.

10. The method of claim 8 , wherein the characters representing emotional responses are graphical icons.

11. A system for detecting spam on a plurality of social media platforms, the system comprising:

transceiver circuitry; and

control circuitry configured to:

determine a plurality of trending topics;

identify at least one post on each of the plurality of social media platforms related to each topic of the plurality of trending topics;

access, using the transceiver circuitry, a plurality of comments associated with each respective identified post corresponding to one of the plurality of social media platforms that the respective identified post was identified on;

generating a plurality of signatures for each of the plurality of comments, wherein each of the plurality of signatures comprises metadata;

compare metadata of each of the plurality of comments associated with each respective identified post with metadata of each of the plurality of comments of each other respective identified post, wherein the metadata corresponds to each of the plurality of signatures, and wherein the plurality comments associated with each respective identified post has not previously been identified as spam;

determine, based on the comparing, whether metadata of a first comment associated with a first identified post is similar to metadata of a second comment associated with a second identified post; and

in response to determining that the metadata of the first comment associated with the first identified post is similar to the metadata of the second comment associated with the second identified post:

identify the first comment and the second comment as spam; and

generate for display, to each respective administrator of each of the plurality of the social media platforms on which the first comment and the second comment identified as spam were accessed, a notification comprising an identifier of the first comment and an identifier of the second comment.

12. The system of claim 11 , wherein the first identified post is located on a first social media platform and the second identified post is located on a second social media platform.

13. The system of claim 11 , wherein the control circuitry configured to determine whether the metadata of the first comment associated with the first identified post is similar to the metadata of the second comment associated with the second identified post is further configured to:

generate a first signature corresponding to the metadata of the first comment and a second signature corresponding to the metadata of the second comment;

calculate a difference between the first signature and the second signature; and

determine, based on the calculating, whether the difference between the first signature and the second signature is below a threshold difference level.

14. The system of claim 13 , wherein the control circuitry is further configured to:

identify a source of the first comment and a source of the second comment; and

determine whether the source of the first comment is the same as the source of the second comment.

15. The system of claim 11 , wherein the control circuitry configured to determine whether the metadata of the first comment associated with the first identified post is similar to the metadata of the second comment associated with the second identified post is further configured to:

determine whether a portion of the first comment contains contact information;

in response to determining that the portion of the first comment contains contact information, determine, based on the processing, whether a portion of the second comment contains the contact information; and

in response to determining that the portion of the second comment contains the contact information, determine that the portion of the first comment is similar to the portion of the second comment.

16. The system of claim 11 , wherein the control circuitry is further configured, in response to determining that the metadata of the first comment associated with the first identified post is not similar to the metadata of the second identified post, to:

identify contact information in a portion of the first comment;

access a plurality of advertisements;

determine whether the contact information appears in an advertisement of the plurality of advertisements; and

in response to determining that the contact information appears in an advertisement of the plurality of advertisements, identify the first comment as spam.

17. The system of claim 11 , wherein the control circuitry is further configured, further in response to determining that the textual portions of the first comment associated with the first identified post is similar to the textual portions of the second comment associated with the second identified post, to:

compare the textual portions of the first comment to an exclusion list having a plurality of entries identifying excluded textual portions;

determine, based on the comparing, whether the textual portions of the first comment matches at least one entry of the plurality of entries; and

in response to determining that the textual portions of the first comment matches at least one entry of the plurality of entries, identify the first comment as not spam;

wherein the control circuitry is further configured to identify the first comment and the second comment as spam is in response to determining that the textual portions of the first comment does not match any entry of the plurality of entries.

18. The system of claim 17 , wherein the plurality of entries identifying excluded textual portions comprises characters representing emotional responses.

19. The system of claim 18 , wherein the characters representing emotional responses are alphanumeric characters.

20. The system of claim 18 , wherein the characters representing emotional responses are graphical icons.

Assignments (7)
CHANGE OF NAME Recorded Oct 3, 2024
From: ROVI GUIDES, INC.
To: ADEIA GUIDES INC.
Reel/Frame 069106/0207 →
RELEASE OF SECURITY INTEREST Recorded Jun 5, 2020
From: MORGAN STANLEY SENIOR FUNDING, INC.
To: ROVI SOLUTIONS CORPORATION; ROVI TECHNOLOGIES CORPORATION; ROVI GUIDES, INC.; TIVO SOLUTIONS, INC.; VEVEO, INC.
Reel/Frame 053481/0790 →
RELEASE OF SECURITY INTEREST Recorded Jun 5, 2020
From: HPS INVESTMENT PARTNERS, LLC
To: ROVI SOLUTIONS CORPORATION; ROVI TECHNOLOGIES CORPORATION; ROVI GUIDES, INC.; TIVO SOLUTIONS, INC.; VEVEO, INC.
Reel/Frame 053458/0749 →
SECURITY INTEREST Recorded Jun 1, 2020
From: ROVI SOLUTIONS CORPORATION; ROVI TECHNOLOGIES CORPORATION; ROVI GUIDES, INC.; TIVO SOLUTIONS INC.; VEVEO, INC.; INVENSAS CORPORATION; INVENSAS BONDING TECHNOLOGIES, INC.; TESSERA, INC.; TESSERA ADVANCED TECHNOLOGIES, INC.; DTS, INC.; PHORUS, INC.; IBIQUITY DIGITAL CORPORATION
To: BANK OF AMERICA, N.A.
Reel/Frame 053468/0001 →
PATENT SECURITY AGREEMENT Recorded Nov 25, 2019
From: ROVI SOLUTIONS CORPORATION; ROVI TECHNOLOGIES CORPORATION; ROVI GUIDES, INC.; TIVO SOLUTIONS, INC.; VEVEO, INC.
To: MORGAN STANLEY SENIOR FUNDING, INC., AS COLLATERAL AGENT
Reel/Frame 051110/0006 →
SECURITY INTEREST Recorded Nov 22, 2019
From: ROVI SOLUTIONS CORPORATION; ROVI TECHNOLOGIES CORPORATION; ROVI GUIDES, INC.; TIVO SOLUTIONS, INC.; VEVEO, INC.
To: HPS INVESTMENT PARTNERS, LLC, AS COLLATERAL AGENT
Reel/Frame 051143/0468 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Oct 23, 2019
From: KUMAR, VIJAY; PICHAIMURTHY, RAJENDRAN; SRINIVASAN, MADHUSUDHAN
To: ROVI GUIDES, INC.
Reel/Frame 050809/0664 →
Continuity (1)
Related Publication 20210051123A1 · Feb 18, 2021