Modifying advertising policies enforced by an online system based on likelihood of user interaction with content items

1. A method comprising:

maintaining, by an online system, one or more advertising policies identifying one or more positions in a newsfeed of content items in which advertisements may not be presented, the online system presenting content items and advertisements to a user of the online system in the newsfeed within a limited display space in a user interface;

receiving, by the online system, information describing an advertisement request from an advertiser;

retrieving prior interactions by the user with content items presented by the online system from information maintained by the online system;

determining a likelihood of the user performing one or more interactions with the advertisement included in the advertisement request based at least in part on the prior interactions by the user with the content items presented by the online system;

determining that the likelihood of the user performing the one or more interactions with the advertisement including the advertisement request is greater than a threshold likelihood;

responsive to determining that the likelihood of the user performing the one or more interactions with the advertisement is greater than the threshold likelihood, generating a modification to the one or more of the advertising policies, the modification to the one or more advertising policies allowing insertion of the advertisement into a position in the newsfeed identified by the one or more advertising policies as one of the identified positions in the newsfeed of content items in which advertisements may not be presented;

selecting, for inclusion in the newsfeed in compliance with the generated modification, the advertisement for inclusion in the newsfeed in the position identified by the one or more advertising policies, a plurality of content items, and one or more additional advertisements; and

providing, by the online system, the newsfeed including the selected content items and advertisements within the limited display space in the user interface to a client device for presentation to the user.

2. The method of claim 1 , wherein the threshold value is based at least in part on likelihoods of the user interacting with one or more content items identified as eligible for inclusion in the newsfeed of content items.

3. The method of claim 1 , wherein generating the modification to the one or more of the advertising policies comprises:

determining likelihoods of the user interacting with one or more content items identified as eligible for inclusion in the newsfeed based on prior interactions by the user with content items;

ranking the likelihood of the user interacting with the advertisement and the likelihoods of the user interacting with the one or more content items identified as eligible for inclusion in the newsfeed; and

modifying one or more of the advertising policies if the likelihood of the user performing one or more interactions with the advertisement has at least a threshold position in the ranking.

4. The method of claim 1 , wherein generating the modification to the one or more of the advertising policies comprises:

determining to modify one or more of the advertising policies; and

ignoring one or more of the advertising policies in response to determining to modify one or more of the advertising policies.

5. The method of claim 1 , wherein generating the modification to the one or more of the advertising policies comprises:

determining to modify one or more of the advertising policies; and

modifying one or more advertising policies to increase a likelihood of the advertisement being selected for inclusion in the newsfeed of content items.

6. The method of claim 5 , wherein modifying one or more advertising policies comprises:

modifying an advertising policy based at least in part on the likelihood of the user performing one or more interactions with the advertisement included in the advertisement request.

7. The method of claim 1 , wherein the one or more advertising policies include a minimum distance between positions in which advertisements are presented in the newsfeed.

8. The method of claim 1 , wherein the one or more advertising policies include a minimum number of content items presented in the newsfeed between advertisements presented in the newsfeed.

9. The method of claim 1 , wherein selecting, for inclusion in the newsfeed in compliance with the generated modification, the advertisement for inclusion in the newsfeed in the position identified by the one or more advertising policies, a plurality of content items, and one or more additional advertisements comprises:

ranking the advertisement for inclusion in the position, the plurality of content items, and the one or more additional advertisements based at least in part on a bid amount associated with the advertisement for inclusion in the position and bid amounts associated with the one or more additional advertisements; and

selecting content items for presentation to the user via the newsfeed of content items based at least in part on the ranking and the generated modification.

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

maintain, by an online system, one or more advertising policies identifying one or more positions in a newsfeed of content items in which advertisements may not be presented, the online system presenting content items and advertisements to a user of the online system in the newsfeed within a limited display space in a user interface;

receive, by the online system, information describing an advertisement request from an advertiser;

retrieve prior interactions by the user with content items presented by the online system from information maintained by the online system;

determine a likelihood of the user performing one or more interactions with the advertisement included in the advertisement request based at least in part on the prior interactions by the user with the content items presented by the online system;

responsive to determining that the likelihood of the user performing the one or more interactions with the advertisement is greater than a threshold likelihood, generate a modification to the one or more of the advertising policies, the modification to the one or more advertising policies allowing insertion of the advertisement into a position in the newsfeed identified by the one or more advertising policies as one of the identified positions in the newsfeed of content items in which advertisements may not be presented;

select, for inclusion in the newsfeed in compliance with the generated modification, the advertisement for inclusion in the newsfeed in the position identified by the one or more advertising policies, a plurality of content items, and one or more additional advertisements; and

provide, by the online system, the newsfeed including the selected content items and advertisements to a client device within the limited display space in the user interface of the client device for presentation to the user.

11. The computer program product of claim 10 , wherein the threshold value is based at least in part on likelihoods of the user interacting with one or more content items identified as eligible for inclusion in the newsfeed of content items.

12. The computer program product of claim 10 , wherein generate the modification to the one or more of the advertising policies based at least in part on the likelihood of the user performing one or more interactions with the advertisement included in the advertisement request comprises:

determine likelihoods of the user interacting with one or more content items identified as eligible for inclusion in the newsfeed based on prior interactions by the user with content items;

rank the likelihood of the user interacting with the advertisement and the likelihoods of the user interacting with the one or more content items identified as eligible for inclusion in the newsfeed; and

modify one or more of the advertising policies if the likelihood of the user performing one or more interactions with the advertisement has at least a threshold position in the ranking.

13. The computer program product of claim 10 , wherein generate the modification to the one or more of the advertising policies based at least in part on the likelihood of the user performing one or more interactions with the advertisement included in the advertisement request comprises:

determine to modify one or more of the advertising policies; and

ignore one or more of the advertising policies in response to determining to modify one or more of the advertising policies.

14. The computer program product of claim 10 , wherein generate the modification to the one or more of the advertising policies based at least in part on the likelihood of the user performing one or more interactions with the advertisement included in the advertisement request comprises:

determine to modify one or more of the advertising policies; and

modify one or more advertising policies to increase a likelihood of the advertisement being selected for inclusion in the newsfeed of content items.

15. The computer program product of claim 14 , wherein modify one or more advertising policies comprises:

modify an advertising policy based at least in part on the likelihood of the user performing one or more interactions with the advertisement included in the advertisement request.

16. The computer program product of claim 10 , wherein the one or more advertising policies include a minimum distance between positions in which advertisements are presented in the newsfeed.

17. The computer program product of claim 10 , wherein select, for inclusion in the newsfeed in compliance with the generated modification, the advertisement for inclusion in the newsfeed in the position identified by the one or more advertising policies, a plurality of content items, and one or more additional advertisements comprises:

rank the advertisement for inclusion in the position, the plurality of content items, and the one or more advertisements based at least in part on a bid amount associated with the advertisement for inclusion in the position and the amounts associated with the one or more additional advertisements; and

select content items for presentation to the user via the newsfeed of content items based at least in part on the ranking and the generated modification.