Systems and methods for social network post audience prediction and selection

1. A computer-implemented method comprising:

receiving, by a computing system, a post associated with a posting user;

analyzing, by the computing system, the post for post information, wherein the post information includes at least one of: location information, content information, sentiment information, and participant information;

ranking, by the computing system, potential viewers by interest-level ratings based on the post information and viewer ranking criteria, wherein the viewer ranking criteria includes a potential interest determination based on interactions of the potential viewers visible to the posting user, the interactions being limited based on privacy protections associated with the potential viewers and the posting user, and previous instances in which the posting user added or removed the potential viewers from previous selected audiences for one or more previous posts, the potential viewers that were added being ranked higher than the potential viewers that were removed;

determining, by the computing system, a size of a predicted relevant audience based on the post information;

providing, by the computing system, a set of the potential viewers that satisfy an interest-level ratings threshold associated with the ranking and a set of additional potential viewers of a common category associated with the potential viewers based on a number of the potential viewers being less than the size of the predicted relevant audience, wherein an affordance is provided that describes why the set of the potential viewers and the set of additional potential viewers were provided;

determining, by the computing system, the predicted relevant audience based on the potential viewers that satisfy the interest-level ratings threshold and a selection of one or more additional potential viewers of the set of additional potential viewers;

receiving, by the computing system, a selected audience for the post based on confirmation or revision of the predicted relevant audience by the posting user; and

providing, by the computing system, the post to each user in the selected audience for inclusion in a news feed associated with each respective user.

2. The computer-implemented method of claim 1 , wherein the interest-level ratings indicate levels of interest in the post by the potential viewers.

3. The computer-implemented method of claim 1 , wherein the potential viewers are connections of the posting user within a threshold number of degrees of separation.

4. The computer-implemented method of claim 1 , wherein the predicted relevant audience comprises each of the potential viewers ranked above the interest-level ratings threshold.

5. The computer-implemented method of claim 1 , wherein the receiving the selected audience comprises revising the predicted relevant audience by changing the interest-level ratings threshold.

6. The computer-implemented method of claim 1 , wherein the common category is determined based on a trait shared by the potential viewers.

7. The computer-implemented method of claim 1 , wherein the set of additional potential viewers include the potential viewers that belong to the common category and that do not satisfy the interest-level ratings threshold.

8. The computer-implemented method of claim 1 , wherein the viewer ranking criteria further includes a friendship coefficient.

9. The computer-implemented method of claim 1 , wherein the providing the post is based on one or more machine learning models.

10. A system comprising:

at least one processor; and

a memory storing instructions that, when executed by the at least one processor, cause the system to perform a method comprising:

receiving a post associated with a posting user;

analyzing the post for post information, wherein the post information includes at least one of: location information, content information, sentiment information, and participant information;

ranking potential viewers by interest-level ratings based on the post information and viewer ranking criteria, wherein the viewer ranking criteria includes a potential interest determination based on interactions of the potential viewers visible to the posting user, the interactions being limited based on privacy protections associated with the potential viewers and the posting user, and previous instances in which the posting user added or removed the potential viewers from previous selected audiences for one or more previous posts, the potential viewers that were added being ranked higher than the potential viewers that were removed;

determining a size of a predicted relevant audience based on the post information;

providing a set of the potential viewers that satisfy an interest-level ratings threshold associated with the ranking and a set of additional potential viewers of a common category associated with the potential viewers based on a number of the potential viewers being less than the size of the predicted relevant audience, wherein an affordance is provided that describes why the set of the potential viewers and the set of additional potential viewers were provided;

determining the predicted relevant audience based on the potential viewers that satisfy the interest-level ratings threshold and a selection of one or more additional potential viewers of the set of additional potential viewers;

receiving a selected audience for the post based on confirmation or revision of the predicted relevant audience by the posting user; and

providing the post to each user in the selected audience for inclusion in a news feed associated with each respective user.

11. The system of claim 10 , wherein the interest-level ratings indicate levels of interest in the post by the potential viewers.

12. The system of claim 10 , wherein the potential viewers are connections of the posting user within a threshold number of degrees of separation.

13. The system of claim 10 , wherein the predicted relevant audience comprises each of the potential viewers ranked above the interest-level ratings threshold.

14. The system of claim 10 , wherein the providing the post is based on one or more machine learning models.

15. A non-transitory computer-readable storage medium including instructions that, when executed by at least one processor of a computing system, cause the computing system to perform a method comprising:

receiving a post associated with a posting user;

analyzing the post for post information, wherein the post information includes at least one of: location information, content information, sentiment information, and participant information;

ranking one or more potential viewers by interest-level ratings based on the post information and viewer ranking criteria, wherein the viewer ranking criteria includes a potential interest determination based on interactions of the potential viewers visible to the posting user, the interactions being limited based on privacy protections associated with the potential viewers and the posting user, and previous instances in which the posting user added or removed the potential viewers from previous selected audiences for one or more previous posts, the potential viewers that were added being ranked higher than the potential viewers that were removed;

determining a size of a predicted relevant audience based on the post information;

providing a set of the potential viewers that satisfy an interest-level ratings threshold associated with the ranking and a set of additional potential viewers of a common category associated with the potential viewers based on a number of the potential viewers being less than the size of the predicted relevant audience, wherein an affordance is provided that describes why the set of the potential viewers and the set of additional potential viewers were provided;

determining the predicted relevant audience based on the potential viewers that satisfy the interest-level ratings threshold and a selection of one or more additional potential viewers of the set of additional potential viewers;

receiving a selected audience for the post based on confirmation or revision of the predicted relevant audience by the posting user; and

providing the post to each user in the selected audience for inclusion in a news feed associated with each respective user.

16. The non-transitory computer-readable storage medium of claim 15 , wherein the interest-level ratings indicate levels of interest in the post by the potential viewers.

17. The non-transitory computer-readable storage medium of claim 15 , wherein the potential viewers are connections of the posting user within a threshold number of degrees of separation.

18. The non-transitory computer-readable storage medium of claim 15 , wherein the predicted relevant audience comprises each of the potential viewers ranked above the interest-level ratings threshold.

19. The non-transitory computer-readable storage medium of claim 15 , wherein the providing the post is based on one or more machine learning models.