Determining user content classifications within an online community

• US 9,146,943 B1
• Filed: 02/26/2013
• Issued: 09/29/2015
• Est. Priority Date: 02/26/2013
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google Inc. (Alphabet Inc.)
• Inventors: Thakur, Madhukar Narayan, Kappiah, Nandini, Ye, Guangqi, Mokani, Dharmeshkumar Jayantilal, Lees, Karen, Chernyakhovskiy, Oleg, Granoff, Andrew, Marambio, Luis Alberto Rojas, Llora Fabrega, Francesco Xavier, Conbere, Morgan Avery
• Primary Examiner(s): Dang, Thanh-Ha
• Application Number:
  US13/778,090
• Time in Patent Office: 945 Days
• Field of Search: 707/748, 707/750, 707/754
• US Class Current: 1/1
• CPC Class Codes: G06F 16/20 of structured data, e.g. relational data
• CPC Class Codes: G06F 16/245 Query processing
• CPC Class Codes: G06F 16/24578 using ranking
• CPC Class Codes: G06F 16/8373 Query execution

Abstract

The present disclosure includes systems and methods for classifying user content (e.g., spam) within an online community by determining user specific signals and content specific signals, the systems and methods comprising: a user interface module configured to receive user content from the online community, a social signal processing module configured to determine signals from the user content, a user and content classifying module configured to classify user content and configured to compute a decision on the user content, a user content labeling module configured to label the user content, and an execution module configured to execute the decision.

Claims

1. A method comprising:

receiving, using at least one computing device, user content associated with a user in an online community;

processing, using the at least one computing device, content-specific signals relating to the received user content and user-specific signals relating to a reputation associated with the user to generate processed signals;

defining, using the at least one computing device, a threshold level of score to classify content into a classification;

calculating, using the at least one computing device, a score for the received user content using the processed signals;

classifying using the at least one computing device, the received user content into the classification based on the score and the defined threshold level of score;

computing, using the at least one computing device, a decision to perform an action on the received user content, based on the classification; and

executing, using the at least one computing device, the decision on the received user content.

2. The method according to claim 1, wherein the content-specific signals relate to the frequency of the content and reaction to the content by others and wherein the user-specific signals inform on the user'"'"'s patterns.

3. The method according to claim 1, wherein the classifying further comprises:

testing, using the at least one computing device, the score for the user content to determine if it is less than the defined threshold level of score; and

labeling the user content as valid.

4. The method according to claim 1, wherein the classifying further comprises:

testing, using the at least one computing device, the score for the user content to determine if it is more than the defined threshold level of score; and

labeling the user content as spam.

5. The method according to claim 1, wherein the user-specific signals are continuously processed to update the classification.

6. The method according to claim 1, wherein the content-specific signals are continuously processed to update the classification.

7. The method according to claim 1, wherein the user content includes at least one of a group of users, comments, and posts.

8. A computer program product comprising a non-transitory computer usable medium including a computer readable program, wherein the computer readable program when executed on a computer causes the computer to:

receive user content associated with a user in an online community;

process content-specific signals relating to the received user content and user-specific signals relating to a reputation associated with the user to generate processed signals;

define a threshold level of score to classify content into a classification;

calculate a score for the received user content using the processed signals;

classify the received user content into the classification based on the score and the defined threshold level of score;

compute a decision to perform an action on the received user content, based on the classification; and

execute the decision on the received user content.

9. The computer program product according to claim 8, wherein the content-specific signals relate to the frequency of the content and reaction to the content by others and wherein the user-specific signals inform on the user'"'"'s patterns.

10. The computer program product according to claim 8, wherein to classify further comprises:

testing, using the at least one computing device, the score for the user content to determine if it is less than the defined threshold level of score; and

labeling the user content as valid.

11. The computer program product according to claim 8, wherein to classify further comprises:

testing, using the at least one computing device, the score for the user content to determine if it is more than the threshold level of score; and

labeling the user content as spam.

12. The computer program product according to claim 8, wherein the user-specific signals are continuously processed to update the classification.

13. The computer program product according to claim 8, wherein content-specific signals are continuously processed to update the classification.

14. The computer program product according to claim 8, wherein the user content includes at least one of a group of users, comments, and posts.

15. A system, comprising:

a processor, and;

a memory storing instructions that, when executed, cause the system to;

receive user content associated with a user within an online community;

process content-specific signals relating to the received user content and user-specific signals relating to a reputation associated with the user to generate processed signals;

define a threshold level of score to classify the user content into a classification;

calculate a score for the received user content using the processed signals;

classify the received user content into the classification based on the score and the defined threshold level of score;

compute a decision to perform an action on the received user content, based on the classification; and

execute the decision on the received user content.

16. The system according to claim 15, wherein the memory further stores instructions that, when executed, cause the system to classify by:

testing the score for the user content to determine if it is less than the defined threshold level of score; and

labeling the user content as valid.

17. The system according to claim 15, wherein the memory further stores instructions that, when executed, cause the system to classify by:

testing the score for the user content to determine if it is more than the defined threshold level of score; and

labeling the user content as spam.

18. The system according to claim 15, wherein the user-specific signals are continuously processed to update the classification.

19. The system according to claim 15, wherein the content-specific signals are continuously processed to update the classification.

20. The system according to claim 15, wherein the user content includes at least one from a group of users, comments, and posts.