Identifying posts in a social networking system for presentation to one or more user demographic groups

• US 10,373,270 B2
• Filed: 10/14/2013
• Issued: 08/06/2019
• Est. Priority Date: 10/14/2013
• Status: Active Grant

• Current Assignee: Meta Platforms, Inc. (f/k/a Facebook, Inc.)
• Original Assignee: Meta Platforms, Inc. (f/k/a Facebook, Inc.)
• Inventors: Guo, Dong, Wong, Mark Kar Hong, Anand, Abheek
• Primary Examiner(s): Brown, Luis A
• Assistant Examiner(s): Johnson, Robert C
• Application Number:
  US14/053,567
• Publication Number:
  US 20150106192A1
• Time in Patent Office: 2,122 Days
• Field of Search: 705 1449
• CPC Class Codes: G06Q 30/0246 Traffic
• CPC Class Codes: G06Q 30/0269 based on user profile or attribute
• CPC Class Codes: G06Q 50/01 Social networking

Abstract

To promote an object maintained by a social networking system, an advertiser identifies the object to the social networking system. Based on the user interaction with one or more posts associated with the object, the social networking system selects one or more candidate posts from the one or more posts. Promotion efficacies of each candidate post for a group of users having one or more common demographic characteristics are determined and a candidate post is selected based at least in part on the promotion efficacies. The selected candidate post may be identified to the advertiser or presented to additional users having the common demographic characteristic by the social networking system.

Claims

1. A method comprising:

receiving from a content provider at a social networking system an indication of a page in the social networking system to be promoted;

selecting a set of candidate posts from a plurality of posts associated with the page based on the candidate posts having more than a threshold amount of interaction by users with the candidate posts indicating popularity of the candidate posts;

identifying, by a processor, for each candidate post, demographic characteristics of the users who interacted with the candidate posts;

defining, by a processor, for each candidate post, a plurality of user demographic groups into which the users are grouped based on the demographic characteristics of the users who interacted with the candidate posts, wherein the identified demographic characteristics associated with each user demographic group for the candidate post are demographic characteristics identified as being common to at least a threshold number of users who performed the threshold amount of interaction with the candidate post;

measuring, by the processor, a promotion efficacy of each candidate post for each of the plurality of user demographic groups defined for the candidate post by;

presenting the candidate post to a test set of users in one of the user demographic groups that have not previously interacted with the page in the social networking system; and

computing a measure of user interaction with the candidate posts by users in the test set of users that have not previously interacted with the page in the social networking system;

identifying one or more additional users in each of the plurality of user demographic groups;

selecting a candidate post from the set of candidate posts for presentation to the one or more additional users in each of the user demographic groups based at least in part on the measured promotion efficacy of the candidate posts for the test set of users from a same demographic group; and

providing, for display by the processor, a user interface for each of the one or more additional users, the user interface comprising a newsfeed including the selected candidate post amongst a plurality of stories describing actions performed by other users connected to the additional user.

2. The method of claim 1, wherein measuring promotion efficacy of each candidate post for each of the plurality of user demographic groups comprises:

computing a total number of users in the test set of users in the user demographic group presented with the candidate post;

computing a measure of user interaction based on a number of users in the test set of users that interacted with the page within a specified time interval after being presented with the candidate post; and

determining a measure of promotion efficacy of the candidate post for the user demographic group based at least in part on the total number of users in the test set of users and the measure of user interaction.

3. The method of claim 1, wherein measuring promotion efficacy of each candidate post for each of the plurality of user demographic groups comprises:

determining a statistical likelihood of each user in the user demographic group performing a conversion event after being presented with the candidate post based at least in part on characteristics of each user in the user demographic group.

4. The method of claim 1, wherein the demographic characteristics associated with the user demographic group are selected from a group consisting of:

an age distribution, one or more interests, a gender distribution, one or more locations, an ethnicity, one or more languages, or any combination thereof.

5. The method of claim 1, wherein the one or more additional users in each of the user demographic groups comprise users in each of the user demographic groups who have not directly interacted with the page.

6. The method of claim 1, further comprising:

identifying the selected candidate post and each of the user demographic groups to the content provider.

7. The method of claim 6, wherein identifying the selected candidate post and each of the user demographic groups further comprises

identifying one or more demographic characteristics associated with each of the user demographic groups to the content provider.

8. The method of claim 1, further comprising:

presenting the selected candidate post to one or more additional users in each of the user demographic groups.

9. The method of claim 8, further comprising:

receiving a target amount of user interaction with the selected candidate post from the content provider;

measuring an amount of user interaction by the one or more additional users in the user demographic group after being presented with the selected candidate post; and

modifying presentation of the selected candidate post to the one or more additional users in the user demographic group based at least in part on a comparison between the target amount of user interaction and the measured amount of user interaction by the one or more additional users in the user demographic group.

10. The method of claim 1, wherein selecting the candidate post from the set of candidate posts for presentation to the one or more additional users in each of the user demographic groups based at least in part on measured promotion efficacy of the candidate posts for the test set of users from a same demographic group comprises:

selecting a candidate post having a highest measured promotion efficacy for the user demographic group.

11. The method of claim 1, wherein selecting the set of candidate posts from a plurality of posts associated with the page based on the candidate posts having more than a threshold amount of interaction by users with the candidate posts indicating popularity of the candidate posts comprises:

providing the plurality the plurality of posts associated with the page to a plurality of users of the social networking system;

observing one or more user interactions with the plurality of posts by users in the plurality of users; and

selecting the set of candidate posts from the plurality of posts based at least in part on the observed one or more user interactions with the plurality of posts by users in the plurality of users.

21. The method of claim 11, wherein defining the user demographic groups for each candidate post further comprises:

identifying one or more keywords associated with the page to be promoted; and

identifying user demographic groups including users who performed one or more of the observed user interactions with the candidate post and whose user profiles include keywords matching at least one of the identified keywords associated with the page.

22. The method of claim 1, wherein measuring a promotion efficacy of each candidate post for each user demographic group further comprises:

predicting a statistical likelihood of users within the user demographic group performing at least one of following types of conversion events if presented with the candidate post;

accessing the candidate post, expressing preference for the candidate post, sharing the candidate post with another user, and commenting on the candidate post.

23. The method of claim 1, wherein the promotion efficacy for each demographic group is further measured based on whether the candidate post was presented to users of the demographic group as organic content, viral content, or paid content.

24. The method of claim 1, further comprising:

receiving, from the content provider, a goal for target user engagement with the page to be promoted;

comparing the measured promotion efficacy against the specified goal of the content provider; and

modifying presentation of one or more of the candidate posts to the one or more additional users based on a result of the comparing.

25. The method of claim 11, wherein the observed one or more user interactions are based on users who have directly interacted with the page.

12. A computer system comprising:

a processor;

memory coupled to the processor, the memory having encoded thereon instructions that, when executed by the processor, cause the processor to;

receive from a content provider at a social networking system an indication of an page in the social networking system to be promoted;

select a set of candidate posts from a plurality of posts associated with the page based on the candidate posts having more than a threshold amount of interaction by users with the candidate posts indicating popularity of the candidate posts;

identify, by a processor, for each candidate post, demographic characteristics of the users who interacted with the candidate posts;

define, for each candidate post, a plurality of user demographic groups into which the users are grouped based on the demographic characteristics of the users who interacted with the candidate posts, wherein the identified demographic characteristics associated with each user demographic group for the candidate post are demographic characteristics identified as being common to at least a threshold number of users who performed the threshold amount of interaction with the candidate post;

measure a promotion efficacy of each candidate post for each of the plurality of user demographic groups defined for the candidate post by;

present the candidate post to a test set of users in one of the user demographic groups that have not previously interacted with the page in the social networking system; and

compute a measure of user interaction with the candidate posts by users in the test set of users that have not previously interacted with the page in the social networking system;

identify one or more additional users in each of the plurality of user demographic groups;

select a candidate post from the set of candidate posts for presentation to the one or more additional users in each of the user demographic groups based at least in part on the measured promotion efficacy the candidate posts for the test set of users from a same demographic group; and

provide, for display by the processor, a user interface for each of the one or more additional users, the user interface comprising a newsfeed including the selected candidate post amongst a plurality of stories describing actions performed by other users connected to the additional user.

13. The system of claim 12, wherein measure promotion efficacy of each candidate post for each of the plurality of user demographic groups comprises:

compute a total number of users in the test set of users in the user demographic group presented with the candidate post;

compute a measure of user interaction based on a number of users in the test set of users that interacted with the page within a specified time interval after being presented with the candidate post; and

determine a measure of promotion efficacy of the candidate post for the user demographic group based at least in part on the total number of users in the test set of users and the measure of user interaction.

14. The system of claim 12, wherein measure promotion efficacy of each candidate post for each of the plurality of the user demographic groups comprises:

determine a statistical likelihood of each user in the user demographic group performing a conversion event after being presented with the candidate post based at least in part on characteristics of each user in the user demographic group.

15. The system of claim 12, wherein the memory further includes instructions that, when executed by the processor, cause the processor to:

identify the selected candidate post and each of the user demographic groups to the content provider.

16. The system of claim 15, wherein identify the selected candidate post and each of the user demographic groups further comprises:

identify one or more demographic characteristics associated with each of the user demographic groups to the content provider.

17. The system of claim 12, wherein the memory further includes instructions that, when executed by the processor, cause the processor to:

present the selected candidate post to the one or more additional users in each of the user demographic groups.

18. The computer system of claim 12, wherein the instructions that, when executed by the processor, cause the processor to select the set of candidate posts from the plurality of posts associated with the page based on the candidate posts having more than a threshold amount of interaction by users with the candidate posts indicating popularity of the candidate posts comprise instructions, that when executed by the processor, cause the processor to:

provide the plurality the plurality of posts associated with the page to a plurality of users of the social networking system;

observe one or more user interactions with the plurality of posts by users in the plurality of users; and

select the set of candidate posts from the plurality of posts based at least in part on the observed one or more user interactions with the plurality of posts by users in the plurality of users.

19. A computer program product comprising a non-transitory computer-readable storage medium including instructions that, when executed by a processor, cause the processor to:

receive from a content provider at a social networking system an indication of an page in the social networking system to be promoted;

select a set of candidate posts from a plurality of posts associated with the page based on the candidate posts having more than a threshold amount of interaction by users with the candidate posts indicating popularity of the candidate posts;

identify, by a processor, for each candidate post, demographic characteristics of the users who interacted with the candidate posts;

define, by a processor, for each candidate post, a plurality of user demographic groups into which the users are grouped based on the demographic characteristics of the users who interacted with the candidate posts, wherein the identified demographic characteristics associated with each user demographic group for the candidate post are demographic characteristics identified as being common to at least a threshold number of users who performed the threshold amount of interaction with the candidate post;

measure a promotion efficacy of each candidate post for each of the plurality of user demographic groups defined for the candidate post by;

present the candidate post to a test set of users in one of the user demographic groups that have not previously interacted with the page in the social networking system; and

compute a measure of user interaction with the candidate posts by users in the test set of users that have not previously interacted with the page in the social networking system;

identify one or more additional users in each of the plurality of user demographic groups;

select a candidate post from the set of candidate posts for presentation to the one or more additional users in each of the user demographic groups based at least in part on the measured promotion efficacy of the candidate posts for the test set of users from a same demographic group; and

provide, for display by the processor, a user interface for each of the one or more additional users, the user interface comprising a newsfeed including the selected candidate post amongst a plurality of stories describing actions performed by other users connected to the additional user.

20. The computer program product of claim 19, wherein measure promotion efficacy of each candidate post for each of the plurality of user demographic groups comprises:

compute a total number of users in the test set of users in the user demographic group presented with the candidate post;

compute a measure of user interaction based on a number of users in the test set of users that interacted with the page within a specified time interval after being presented with the candidate post; and

determine a measure of promotion efficacy of the candidate post for the user demographic group based at least in part on the total number of users in the test set of users and the measure of user interaction.