Systems and methods for keyword selection in a web-based social network

• US 20090049036A1
• Filed: 08/16/2007
• Published: 02/19/2009
• Est. Priority Date: 08/16/2007
• Status: Active Grant

• Current Assignee: Meta Platforms, Inc. (f/k/a Facebook, Inc.)
• Original Assignee: Meta Platforms, Inc. (f/k/a Facebook, Inc.)
• Inventors: Juan, Yun-Fang, Jin, Kang-Xing
• Granted Patent: US 8,027,943 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G06Q 10/10 Office automation; Time management
• CPC Class Codes: G06Q 30/0201 Market modelling; Market analysis; Collecting market data
• CPC Class Codes: G06Q 30/0269 based on user profile or attribute
• CPC Class Codes: G06Q 50/01 Social networking
• CPC Class Codes: H04L 67/306 User profiles

Abstract

A system and method for selecting a subset of keywords from a set of master keywords found in user profiles in a social network is disclosed. The method includes selecting a first and second group of user profiles including one or more keywords and computing the number of occurrences of each of the master keywords in the first and second group of profiles. A value may be computed for each of the master keywords based on a comparison of the number of occurrences in the first group of profiles and the number of occurrences in the second group of profiles. The computed value may be used for selecting the subset of keywords from the master keywords and/or ranking the master keywords.

Claims

1. A method for selecting a subset of keywords from a set of master keywords in user profiles of social network users, comprising:

computing a first histogram of each keyword in the master keywords based on the occurrence of the keywords in a first group of user profiles;

computing a second histogram of each keyword in the master keywords based on the occurrence of the keywords in a second group of user profiles;

computing a score based on a comparison of the first histogram and the second histogram for each keyword in the master keywords;

ranking the master keywords based on the score of the keywords; and

selecting a subset of keywords from the master keywords based on the ranking.

2. The method of claim 1, wherein the master keywords include all the keywords occurring in the user profiles of all the social network users.

3. The method of claim 1, wherein the first group of user profiles includes profiles of social network users who respond positively to an invitation.

4. The method of claim 3, wherein the second group of user profiles includes profiles of social network users who respond negatively to the invitation.

5. The method of claim 3, wherein the second group of user profiles includes profiles selected randomly from all social network users.

6. The method of claim 1, wherein the first group of user profiles includes profiles of users selected from the social network users based on a calculated probability that each social network user will respond to an invitation.

7. The method of claim 6, wherein the calculated probability of each user responding to the invitation is determined using a probability function having as input keywords in the profile of the user.

8. The method of claim 6, wherein the second group of user profiles includes profiles of users selected randomly from the social network users.

9. The method of claim 6, wherein the second group of user profiles includes profiles of users selected from the social network users based on a calculated probability that each social network user will respond to the invitation.

10. The method of claim 1, wherein computing a score for each keyword comprises computing a difference between an entry in the first histogram corresponding to the keyword and an entry in the second histogram corresponding to each keyword.

11. The method of claim 1, wherein computing a score for each keyword comprises computing a ratio between an entry in the first histogram corresponding to the keyword and an entry in the second histogram corresponding to each keyword.

12. The method of claim 1, wherein computing a score for each keyword comprises computing a difference between an information gain for an entry in the first histogram corresponding to the keyword and an information gain for an entry in the second histogram corresponding to each keyword.

13. A method for selecting a subset of keywords from a set of master keywords found in user profiles of social network users, comprising:

selecting a first group of user profiles including one or more keywords;

selecting a second group of user profiles including one or more keywords;

computing the number of occurrences of each of the master keywords in the first group of profiles;

computing the number of occurrences of each of the master keywords in the second group of profiles;

computing a value for each of the master keywords based on a comparison of the number of occurrences in the first group of profiles and the number of occurrences in the second group of profiles;

ranking the master keywords based on the computed value; and

selecting a subset of keywords from the master keywords based on the ranking.

14. The method of claim 13, wherein the master keywords include all the keywords occurring in the profiles of all the social network users.

15. The method of claim 13, wherein the first group of user profiles includes profiles of social network users who respond positively to an invitation.

16. The method of claim 15, wherein the second group of user profiles includes profiles of social network users who respond negatively to the invitation.

17. The method of claim 15, wherein the second group of user profiles includes profiles of users selected randomly from the social network users.

18. The method of claim 13, wherein the first group of user profiles is selected from profiles of social network users based on a calculated probability that each social network user will respond to an invitation.

19. The method of claim 18, wherein the calculated probability of each user responding to the invitation is determined using a probability function having as input keywords in the profile of the user.

20. The method of claim 18, wherein the second group of user profiles includes profiles of users selected randomly from the social network users.

21. The method of claim 18, wherein the second group of user profiles includes profiles of users selected from the social network users based on a calculated probability that each social network user will respond to the invitation.

22. The method of claim 13, further comprising determining for each keyword of the master keywords a first percentage of the profiles of first group of users including at least one occurrence of the keyword and a second percentage of the profiles of second group of users including at least one occurrence of the keyword.

23. The method of claim 22, wherein computing a value for each of the master keywords comprises computing a difference between the first percentage and the second percentage.

24. The method of claim 22, wherein computing a value for each of the master keywords comprises computing a ratio of the first percentage divided by the second percentage.

25. The method of claim 22, wherein computing a value for each of the master keywords comprises computing a difference between an information gain for the first percentage and an information gain for the second percentage.

26. The method of claim 22, wherein computing a value for each of the master keywords comprises computing an odds ratio of the first percentage and the second percentage.

27. The method of claim 22, wherein computing a value for each of the master keywords comprises computing a relevancy score for the first percentage and the second percentage.

28. A method for selecting a subset of keywords from a set of master keywords in user profiles of social network users, comprising:

computing a first histogram of the master keywords based on the number of occurrence of each keyword in a first group of user profiles;

computing a second histogram of the master keywords based on the number of occurrence of each keyword in a second group of user profiles;

computing a score based on a comparison of the first histogram and the second histogram for each keyword in the master keywords; and

selecting the subset of keywords from the master keywords based on a comparison of the score for each keyword in the master keywords with a threshold value.