System and method for inferring user interest based on analysis of user-generated metadata

• US 8,707,160 B2
• Filed: 08/10/2006
• Issued: 04/22/2014
• Est. Priority Date: 08/10/2006
• Status: Expired due to Fees

• Current Assignee: R2 Solutions LLC (Acacia Research Corporation)
• Original Assignee: Yahoo! Inc. (Apollo Global Management, Inc.)
• Inventors: Sadagopan, Narayanan, Holmes, Scott
• Primary Examiner(s): Ries, Laurie
• Assistant Examiner(s): AMIN, MUSTAFA A
• Application Number:
  US11/502,869
• Publication Number:
  US 20080040301A1
• Time in Patent Office: 2,812 Days
• Field of Search: 706/16
• US Class Current: 715/234
• CPC Class Codes: G06Q 30/02 Marketing; Price estimation or determination; Fundraising

Abstract

User-generated tags from viewing web-based content are collected over a predetermined period of time. A subset of distinct or unique tags is identified from among the collected tags. A z-score is calculated for each identified distinct tag, where the z-score is a measure of the statistical significance of the tag. The subset of distinct tags is then sorted based on their corresponding z-score. All distinct tags having a corresponding z-score lower than a predetermined threshold are rejected and the remaining distinct tags, having a corresponding z-score higher than the threshold are used to infer a user'"'"'s interest. The ability to infer a user'"'"'s interests from the remaining distinct tags may thus benefit web-based applications by achieving a high degree of accuracy in predicting the interests of users by leveraging on the use of the user generated content tags and keywords.

Claims

1. A method operable on a computer for inferring a user'"'"'s interests from user generated tags, the method comprising:

collecting a plurality of user-generated tags from a given user and one or more users in a social network of the given user over a predetermined period of time;

electronically, calculating, via a processing device, a corresponding z-score for each of the plurality of user-generated tags, where the corresponding z-score is a measure of a statistical significance for a given tag based on an observed frequency of the given tag being selected and a tag selection frequency distribution over the plurality of user-generated tags for the predetermined period of time;

retaining one or more tags from the plurality of user-generated tags where the corresponding z-score of the one or more tags is higher than a threshold determined based on random tag selection by the given user and the one or more users in the social network of the given user based on the tag selection frequency distribution;

comparing the retained one or more tags of the given user with the retained one or more tags of the one or more users in the social network of the given user; and

inferring the given user'"'"'s interest based on the comparison of the retained one or more tags of the given user and the retained one or more tags of the one or more users in the social network of the given user.

2. The method of claim 1, further comprising the step of sorting the plurality of user generated tags based on the plurality of user generated tags'"'"' corresponding z-score.

3. The method of claim 1, wherein the threshold has an associated confidence value that is determined on the basis of a desired statistical confidence for inferring the given user'"'"'s interests.

4. The method of claim 1, wherein the collecting step collects the plurality of user generated tags from one or more web-based content.

5. The method of claim 1, wherein the predetermined time period is a configurable parameter.

6. The method of claim 1, wherein the predetermined time period is a continuous time period.

7. The method of claim 1, wherein the predetermined time period is a non-continuous time period.

8. The method of claim 1, wherein the step of calculating the corresponding z-score for the given tag, z(i), comprises calculating a z-score as:

z(i)=[freq(i)−

μ

]/σ

where freq (i)= a frequency of occurrence of the given tag;

μ

= a mean of the number of occurrences of distinct tags;

σ

= a standard deviation of the number of occurrences of distinct tags.

9. A non-transitory computer-readable medium having computer executable instructions for performing the method of claim 1.

10. A system for inferring a user'"'"'s interests from user generated tags, the system comprising:

a processor;

a memory connected to the processor and storing instructions for operating the processor to perform steps of;

collecting a plurality of user-generated tags from a given user and one or more users in a social network of the given user over a predetermined period of time;

calculating a corresponding z-score for each of the plurality of user-generated tags, where the corresponding z-score is a measure of a statistical significance for a given tag based on an observed frequency of the given tag being selected and a tag selection frequency distribution over the plurality of user-generated tags for the predetermined period of time;

retaining one or more tags from the plurality of user-generated tags where the corresponding z-score of the one or more tags is higher than a threshold determined based on random tag selection by the given user and the one or more users in the social network of the given user based on the tag selection frequency distribution;

comparing the retained one or more tags of the given user with the retained one or more tags of the one or more users in the social network of the given user; and

inferring the given user'"'"'s interest based on the comparison of the retained one or more tags of the given user and the retained one or more tags of the one or more users in the social network of the given user.

11. The system of claim 10, wherein the processor further performs the step of sorting the plurality of user generated tags based on the plurality of user generated tags'"'"' corresponding z-score.

12. The system of claim 10, wherein threshold has an associated confidence value that is determined on the basis of a desired statistical confidence for inferring the given user'"'"'s interests.

13. The system of claim 10, wherein the collecting step collects the plurality of user generated tags from one or more web-based content.

14. The system of claim 10, wherein the predetermined time period is a configurable parameter.

15. The system of claim 10, wherein the predetermined time period is a continuous time period.

16. The system of claim 10, wherein the predetermined time period is a non-continuous time period.

17. A system for inferring a user'"'"'s interests from user generated tags, the system comprising:

means for collecting a plurality of user-generated tags from a given user and one or more users in a social network of the given user over a predetermined period of time;

means for calculating a corresponding z-score for each of the plurality of user-generated tags, where the corresponding z-score is a measure of a statistical significance for a given tag based on an observed frequency of the given tag being selected and a tag selection frequency distribution over the plurality of user-generated tags for the predetermined period of time;

means for retaining one or more tags from the plurality of user-generated tags where the corresponding z-score of the one or more tags is higher than a threshold determined based on random tag selection by the given user and the one or more users in the social network of the given user based on the tag selection frequency distribution;

means for comparing the retained one or more tags of the given user with the retained one or more tags of the one or more users in the social network of the given user;

and means for inferring the given user'"'"'s interest based on the comparison of the retained one or more tags of the given user and the retained one more tags of the one or more users in the social network of the given user.

18. The system of claim 17, further comprising means for sorting the plurality of user generated tags based on the plurality of user generated tags'"'"' corresponding z-score.

19. The system of claim 17, further comprising means for comparing tags from two or more users.

20. A program stored on non-transitory computer readable media for making a computer execute steps of:

collecting a plurality of user-generated tags from a given user and one or more users in a social network of the given user over a predetermined period of time;

calculating a corresponding z-score for each of the plurality of user-generated tags, where the corresponding z-score is a measure of a statistical significance for a given tag based on an observed frequency of the given tag being selected and a tag selection frequency distribution over the plurality of user-generated tags for the predetermined period of time;

retaining one or more tags from the plurality of user-generated tags where the corresponding z-score of the one or more tags is higher than a threshold determined based on random tag selection by the given user and the one or more users in the social network of the given user based on the tag selection frequency distribution;

comparing the retained one or more tags of the given user with the retained one or more tags of the one or more users in the social network of the given user; and

inferring the given user'"'"'s interest based on the comparison of the retained one or more tags of the given user and the retained one or more tags of the one or more users in the social network of the given user.

21. The program of claim 20, wherein the computer further executes the step of sorting the plurality of user generated tags based on the plurality of user generated tags'"'"' corresponding z-score.

22. The program of claim 20, wherein the threshold has an associated confidence value that is determined on the basis of a desired statistical confidence for inferring the given user'"'"'s interests.

23. A non-transitory recording medium recording a program for making a computer execute steps of:

collecting a plurality of user-generated tags from a given user and one or more users in a social network of the given user over a predetermined period of time;

calculating a corresponding z-score for each of the plurality of user-generated tags, where the corresponding z-score is a measure of a statistical significance for a given tag based on an observed frequency of the given tag being selected and a tag selection frequency distribution over the plurality of user-generated tags for the predetermined period of time;

retaining one or more tags from the plurality of user-generated tags where the corresponding z-score of the one or more tags is higher than a threshold determined based on random tag selection by the given user and the one or more users in the social network of the given user based on the tag selection frequency distribution;

comparing the retained one or more tags of the given user with the retained one or more tags of the one or more users in the social network of the given user;

and inferring the given user'"'"'s interest based on the comparison of the retained one or more tags of the given user and the retained one or more tags of the one or more users in the social network of the given user.

24. The non-transitory recording medium of claim 23, wherein the computer further executes the step of sorting the plurality of user generated tags based on the plurality of user generated tags'"'"' corresponding z-score.

25. The non-transitory recording medium of claim 23, wherein the threshold has an associated confidence value that is determined on the basis of a desired statistical confidence for inferring the given user'"'"'s interests.