Social Behavior Analysis and Inferring Social Networks for a Recommendation System

• US 20090164400A1
• Filed: 12/20/2007
• Published: 06/25/2009
• Est. Priority Date: 12/20/2007
• Status: Active Grant

• Current Assignee: Yahoo Assets LLC
• Original Assignee: Yahoo! Inc. (Apollo Global Management, Inc.)
• Inventors: Pang, Bo, Stoyanovich, Julia, Gabrilovich, Evgeniy, Amer-Yahia, Sihem, Yu, Cong
• Granted Patent: US 8,073,794 B2
• Time in Patent Office: Days
• US Class Current: 706/45
• CPC Class Codes: G06Q 10/00 Administration; Management
• CPC Class Codes: G06Q 30/0631 Item recommendations
• CPC Class Codes: G06Q 50/01 Social networking

Abstract

Systems and methods are provided for determining items or people of potential interest to recommend to users in a computer-based network. Implied social networks may be determined based at least in part on obtained social behavior information. Items or people of potential interest to users may be determined based at least in part on implied social network information. Vocabulary taxonomies may be associated with, or used in determining, implied social networks.

Claims

1. A method for determining items or people of potential interest to recommend to users in a computer-based network, the method comprising:

obtaining information relating to one or more types of computer-based social behavior for multiple users;

determining one or more implied social networks based at least in part on the obtained social behavior information; and

determining one or more items or people of potential interest to recommend to a user, based at least in part on at least one of the one or more implied social networks.

2. The method of claim 1, wherein obtaining information relating to social behavior includes obtaining tagging behavior information.

3. The method of claim 1, wherein obtaining information relating to social behavior includes obtaining bookmarking information.

4. The method of claim 1, wherein obtaining information includes obtaining information relating to social behavior of users of the Internet.

5. The method of claim 1, comprising integrating the one or more implied social networks with one or more explicit social networks.

6. The method of claim 1, wherein determining one or more implied social networks comprises determining commonalities in social behavior between users.

7. The method of claim 6, comprising determining commonalities in social behavior between users based at least in part on one or more vocabulary taxonomies.

8. The method of claim 1, wherein determining items or people of potential interest comprises identifying content.

9. The method of claim 1, comprising recommending the items or people of potential interest.

10. The method of claim 9, wherein recommending includes providing a graphical user interface.

11. The method of claim 1, wherein determining one or more items or people of potential interest comprises analyzing social behavior information using a tag space.

12. A method for determining items or people of potential interest to recommend to users in a computer-based network, the method comprising:

obtaining information relating to a plurality of types of computer-based, word-based social behavior for multiple users;

analyzing the obtained word-based social behavior information using a vocabulary taxonomy to determine at least one implied topic-specific social network including a set of users of the multiple users; and

determining an item or person of potential interest to recommend to a user of the set of users in the topic-specific social network, based at least on information relating to the topic-specific social network.

13. The method of claim 12, wherein the analyzing step includes utilizing a semantically-sensitive vocabulary-based taxonomy developed in connection with the topic-specific social network.

14. The method of claim 13, wherein the determining step includes determining the item of potential interest to the user based at least in part on obtained social behavior information indicating items of interest to one or more other users in the topic-specific implied social network.

15. The method of claim 14, wherein the determining step includes determining the item of potential interest to the user based at least in part on obtained social behavior information indicating popular items of interest among users in the implied topic-specific network.

16. A system for determining items or people of potential interest to recommend to users in a computer-based network, the system comprising;

one or more server computers connected to a network; and

a plurality of user computers connected to the network;

wherein the one or more server computers include a computer-based social behavior analysis program, the program being for;

obtaining information relating to a plurality of types of computer-based, word-based social behavior for multiple users of the plurality of users;

analyzing the obtained word-based social behavior information using a vocabulary taxonomy to determine at least one implied, semantically-sensitive, topic-specific social network including a set of users of the multiple users; and

determining an item or person of potential interest to recommend to a user of the set of users in the topic-specific social network, based at least on information relating to the topic-specific social network.

17. The system of claim 16, comprising a database for storing the information relating to social behavior.

18. The system of claim 16, wherein the network comprises the Internet.

19. The system of claim 16, wherein the social behavior information comprises at least one of tagging behavior or bookmarking behavior.

20. A computer program product, comprising computer-readable medium comprising instructions for causing a processing unit to perform a method for determining items or people of potential interest to recommend to users in a computer-based network, the method comprising:

obtaining information relating to a plurality of types of computer-based, word-based social behavior for multiple users;

analyzing the obtained word-based social behavior information using a vocabulary-based taxonomy to determine at least one implied topic-specific social network including a set of users of the multiple users; and

determining an item or person of potential interest to recommend to a user of the set of users in the topic-specific social network, based at least on information relating to the topic-specific social network.