INFERRING TARGET CLUSTERS BASED ON SOCIAL CONNECTIONS

• US 20140089400A1
• Filed: 09/24/2012
• Published: 03/27/2014
• Est. Priority Date: 09/24/2012
• Status: Active Grant

• Current Assignee: Meta Platforms, Inc. (f/k/a Facebook, Inc.)
• Original Assignee: Meta Platforms, Inc. (f/k/a Facebook, Inc.)
• Inventors: Yan, Rong, Garcia-Martinez, Antonio Felipe, Zigoris, Philip Anastasios, Singla, Ankush
• Granted Patent: US 9,373,146 B2
• Time in Patent Office: Days
• US Class Current: 709/204
• CPC Class Codes: G06F 16/954 Navigation, e.g. using categorised browsing
• CPC Class Codes: G06Q 30/0251 Targeted advertisements
• CPC Class Codes: G06Q 30/0269 based on user profile or attribute
• CPC Class Codes: G06Q 50/01 Social networking
• CPC Class Codes: H04L 51/52 for supporting social networking services
• CPC Class Codes: H04L 67/306 User profiles
• CPC Class Codes: H04L 67/535 Tracking the activity of the user network monitoring arrangements H04L43/00; recording of computer activity G06F11/34

Abstract

A seed cluster comprising a group of users who share a particular attribute and/or affiliation is determined by a social networking system. For each user of the seed cluster, other users and/or entities connected to the user in the social networking system are retrieved. For each retrieved other user or entity, the social networking system may determine whether the other user or entity exhibits the attribute or affiliation based on a random walk algorithm. A resulting targeting cluster of users and/or entities may be used for targeting advertisements targeting to members. A social networking system may also infer an affiliation for a user based on the user'"'"'s interaction with a page, application, or entity where other users who interacted with the same page, application, or entity have the same affiliation.

Claims

1. A method comprising:

receiving a selection of an attribute shared by a subset of users of a social networking system;

determining a seed cluster that comprises the subset of users sharing the selected attribute;

for each user of one or more of the users in the seed cluster,

retrieving one or more primary connections of the user; and

for each retrieved primary connection of the retrieved one or more primary connections of the user having an unknown value with respect to the selected attribute,

retrieving one or more secondary connections of the retrieved user, where each secondary connection is connected to the retrieved primary connection in the social networking system,

determining that one or more secondary connections exhibit the selected attribute, and

declaring that the retrieved primary connection exhibits the attribute based on the determined one or more secondary connections exhibiting the attribute satisfying a predetermined criteria; and

storing information defining a targeting cluster of users of the social networking system who share the attribute, where the targeting cluster comprises the seed cluster of users and the declared one or more primary connections.

2. The method of claim 1, wherein receiving a selection of an attribute shared by a subset of users of a social networking system further comprises receiving the selection from an advertiser selecting targeting criteria for an ad request.

3. The method of claim 1, wherein receiving a selection of an attribute shared by a subset of users of a social networking system further comprises receiving the selection from a module in the social networking system.

4. The method of claim 1, wherein determining a seed cluster comprises adding users to the seed cluster based on an inference related to the selected attribute.

5. The method of claim 4, wherein adding users to the cluster based on an inference related to the selected attribute comprises adding an inferred user based on retrieved profile information of users connected to the inferred user.

6. The method of claim 1, wherein the subset of users sharing the selected attribute comprises users of the social networking system who have recently used a specified application on the social networking system.

7. The method of claim 1, wherein determining a seed cluster comprises adding users to the seed cluster based on profile information relating to the selected attribute.

8. The method of claim 1, wherein determining a seed cluster comprises adding users to the seed cluster based on content information related to the selected attribute.

9. The method of claim 1, wherein determining that one or more secondary connections exhibit the attribute further comprises:

for each secondary connection in a subset of the one or more secondary connections comprising a subset of users of the social networking system, determining that the secondary connection exhibits the attribute based on the user profile of the secondary connection comprising the attribute.

10. The method of claim 1, wherein declaring that the retrieved primary connection exhibits the attribute based on the determined one or more secondary connections exhibiting the attribute further comprises:

determining a percentage of total secondary connections exhibiting the attribute based on the determined one or more secondary connections compared to the retrieved one or more secondary connections connected to the retrieved primary connection in the social networking system; and

responsive to the determined percentage exceeding a predetermined threshold percentage, declaring that the retrieved primary connection exhibits the attribute.

11. The method of claim 10, wherein the predetermined threshold percentage comprises at least eighty percent.

12. The method of claim 1, wherein declaring that the retrieved primary connection exhibits the attribute based on the determined one or more secondary connections exhibiting the attribute further comprises:

determining a weighted average using a plurality of affinity scores of the retrieved primary connection for the determined one or more secondary connections as weights; and

responsive to the determined weighted average exceeding a predetermined threshold, declaring that the retrieved primary connection exhibits the attribute.

13. The method of claim 1, wherein the predetermined criteria comprises at least a predetermined threshold percentage of one or more secondary connections exhibiting the attribute.

14. A method comprising:

determining a plurality of seed users of a social networking system, where each seed user previously self-declared a particular affiliation in the user'"'"'s profile on the social networking system;

for each seed user,

selecting a plurality of social connections connected to the seed user in the social networking system, and

for each selected social connection of the plurality of social connections connected to the seed user in the social networking system, determining an inference that the social connection has the particular affiliation based on one or more secondary connections of the social connection having the particular affiliation satisfying a predetermined criteria; and

storing information defining a targeting cluster of users in the social networking system, where the targeting cluster comprises the seed cluster of users and the one or more social connections inferred to have the particular affiliation.

15. The method of claim 14, wherein determining a plurality of social connections of the seed user further comprises:

retrieving a listing of the plurality of social connections connected to the seed user from the user profile of the seed user; and

determining the plurality of social connections connected to the seed user based on the retrieved listing.

16. The method of claim 14, wherein determining a plurality of social connections of the seed user further comprises:

retrieving a plurality of edge objects associated the seed user in the social networking system; and

determining the plurality of social connections connected to the seed user based on the retrieved plurality of edge objects.

17. The method of claim 14, wherein determining a plurality of social connections of the seed user further comprises:

retrieving a plurality of content objects associated the seed user in the social networking system; and

determining the plurality of social connections connected to the seed user based on the retrieved plurality of content objects.

18. The method of claim 14, where each retrieved social connection has not previously self-declared the particular affiliation in the social networking system.

19. The method of claim 14, wherein determining an inference that the social connection has the particular affiliation further comprises:

responsive to determining that a predetermined threshold percentage of one or more secondary connections of the social connection that have the particular affiliation, determining the inference that the social connection has the particular affiliation.

20. The method of claim 14, wherein determining an inference that the social connection has the particular affiliation further comprises:

responsive to a score exceeding a predetermined threshold score, the score determined using a scoring model on the one or more secondary connections of the social connection that have the particular affiliation, determining the inference that the social connection has the particular affiliation.

21. The method of claim 14, wherein the predetermined criteria comprises at least a predetermined threshold percentage of one or more secondary connections of the social connection having the particular affiliation.

22. The method of claim 21, wherein the predetermined threshold percentage comprises at least eighty percent.

23. A method comprising:

receiving an indication that a user of a social networking system interacted with an entity of the social networking system;

responsive to retrieving a previously inferred association of a particular attribute for the entity of the social networking system, determining that the user exhibits the particular attribute based on the indication that the user interacted with the entity; and

responsive to not retrieving the previously inferred association of the particular attribute for the entity,

retrieving a plurality of social connections connected to the entity, where each of the plurality of social connections are associated with the particular attribute,

determining a total number of users that have interacted with the entity,

determining a ratio comprising a number of the retrieved plurality of social connections connected to the entity that are associated with the particular attribute over the determined total number of users that have interacted with the entity,

determining an inference that the entity is associated with the particular attribute based on the determined ratio exceeding a predetermined threshold for making the inference,

storing the inference that the entity is associated with the particular attribute in the social networking system, and

determining that the user exhibits the particular attribute based on the indication that the user interacted with the entity.

24. The method of claim 23, wherein the entity comprises a page on the social networking system and the indication that the user interacted with the entity comprises a user interaction with the page.

25. The method of claim 23, wherein the entity comprises an application on the social networking system and the indication that the user interacted with the entity comprises a user installation of the application on the social networking system.

26. The method of claim 23, wherein the entity comprises an application on the social networking system and the indication that the user interacted with the entity comprises a user operating the application on the social networking system.

27. The method of claim 23, wherein the entity comprises an application on an external system connected to the social networking system and the indication that the user interacted with the entity comprises a user operating the application on the external system.