Arranging stories on newsfeeds based on expected value scoring on a social networking system
A social networking system generates a newsfeed for a user to view when accessing the social networking system. Candidate stories associated with users of the social networking system are selected and an expected value score for each candidate story is determined. An expected value score is based on the probability of a user performing various types of interactions with a candidate story and a numerical value for each type of interaction. The numerical value for a type of interaction represents a value to the social networking system of the type of interaction. Based on the expected value scores, the candidate stories are ranked and the ranking used to select candidate stories for the newsfeed.
1. A method comprising:
receiving a request from a viewing user of an online system for posts associated with a plurality of other users of the online system for presentation on a newsfeed of the viewing user;
selecting candidate posts for the viewing user, the candidate posts posted by one or more other users of the online system;
ranking the candidate posts for presentation on the newsfeed to the viewing user;
determining a neediness value for each other user of the one or more other users associated with the candidate posts, the neediness value for the other user determined by comparing historical interactions with the online system associated with the other user to a set of engagement criteria indicative of an overall level of engagement of the other user with the online system;
identifying, using the determined neediness values, a disengaged user of the one or more other users, the disengaged user having a neediness value above a threshold level indicating a lack of overall engagement of the disengaged user with the online system;
modifying, based on the neediness value of the disengaged user, the ranking of the candidate posts to increase the ranking of the candidate post associated with the disengaged user relative to others of the candidate posts, the modifying increasing the likelihood the candidate post of the disengaged user is viewed by the viewing user on the newsfeed;
selecting a set of the candidate posts based at least in part on the modified ranking; and
sending the selected set of candidate posts for display to the viewing user on the newsfeed.
2. The method of claim 1 , wherein the neediness values of the one or more other users are determined using posts posted by the one more other users.
3. The method of claim 1 , wherein the historical interactions with the online system include a rate at which the other user provides posts to the online system.
4. The method of claim 1 , wherein the historical interactions with the online system include an amount of user feedback received on posts posted by the other user.
5. The method of claim 4 , wherein the feedback is selected from a group consisting of: comments on a post, shares of a post, likes of a post, and hides of a post.
6. The method of claim 1 , wherein the historical interactions with the online system include an elapsed time between a current time and a time when the other user established an account with the online system.
7. The method of claim 1 , wherein determining the neediness value for each other user of the one or more other users comprises:
comparing the historical interactions with the online system associated with the other user to respective threshold interaction levels.
8. The method of claim 7 , wherein the neediness value is proportional to a difference between the historical interactions associated with the disengaged user and the threshold interaction levels.
9. The method of claim 7 , wherein modifying the ranking of the candidate posts for the viewing user to increase the ranking of the candidate post associated with the disengaged user comprises increasing the ranking of the candidate post associated with the disengaged user by an amount proportional to the neediness value of the disengaged user.
10. The method of claim 9 , wherein increasing the ranking of the candidate post associated with the disengaged user further comprises:
determining that the disengaged user has a higher neediness value than another disengaged user; and
ranking the candidate post associated with the disengaged user higher than a post of the other disengaged user based on the higher neediness value, the higher ranked post being presented in the newsfeed above the post of the other disengaged user.
11. The method of claim 1 , wherein ranking the candidate posts comprises:
ranking the candidate posts such that candidate posts having higher expected value scores have a higher position in the ranking.
12. A computer program product comprising a non-transitory computer readable storage medium having instructions encoded therein that, when executed by a processor, cause the processor to:
receive a request from a viewing user of an online system for posts associated with a plurality of other users of the online system for presentation on a newsfeed of the viewing user;
select candidate posts for the viewing user, the candidate posts posted by one or more other users of the online system;
rank the candidate posts for presentation on the newsfeed to the viewing user;
determine a neediness value for each other user of the one or more other users associated with the candidate posts, the neediness value for the other user determined by comparing historical interactions with the online system associated with the other user to a set of engagement criteria indicative of an overall level of engagement of the other user with the online system;
identify, using the determined neediness values, a disengaged user of the one or more other users, the disengaged user having a neediness value above a threshold level indicating a lack of overall engagement of the disengaged user with the online system;
modify, based on the neediness value of the disengaged user, the ranking of the candidate posts to increase the ranking of the candidate post associated with the disengaged user relative to others of the candidate posts, the modifying increasing the likelihood the candidate post of the disengaged user is viewed by the viewing user on the newsfeed;
select a set of the candidate posts based at least in part on the modified ranking; and
send the selected set of candidate posts for display to the viewing user on the newsfeed.
13. The computer program product of claim 12 , wherein the neediness values of the one or more other users are determined using posts posted by the one more other users.
14. The computer program product of claim 12 , wherein the historical interactions with the online system include a rate at which the other user provides posts to the online system.
15. The computer program product of claim 12 , wherein the historical interactions with the online system include an amount of user feedback received on posts posted by the other user.
16. The computer program product of claim 12 , wherein the instructions that cause the processor to identify determine the neediness value for each other user of the one or more other users comprise further instructions that cause the processor to:
compare the historical interactions with the online system associated with the other user to respective threshold interaction levels.
17. The computer program product of claim 16 , wherein the instructions that cause the processor to modify the ranking of the candidate posts for the viewing user to increase the ranking of the candidate post associated with the disengaged user comprise instructions to increase the ranking of the candidate post associated with the disengaged user by an amount proportional to the neediness value of the disengaged user.
18. The computer program product of claim 17 , wherein the instructions that cause the processor to increase the ranking of the candidate post associated with the disengaged user further comprise instructions to:
determine that the disengaged user has a higher neediness value than another disengaged user; and
ranking the candidate post associated with the disengaged user higher than a post of the other disengaged user based on the higher neediness value, the higher ranked post being presented in the newsfeed above the post of the other disengaged user.
19. The computer program product of claim 16 , wherein the neediness value is proportional to a difference between historical interactions associated with the disengaged user and the threshold interaction levels.
20. The computer program product of claim 12 , wherein the instructions that cause the processor to rank the candidate posts comprise instructions to:
rank the candidate posts such that candidate posts having higher expected value scores have a higher position in the ranking.