SELECTING COMMENTS FOR PRESENTATION TO A SOCIAL NETWORKING SYSTEM USER ALONG WITH A CONTENT ITEM
A social networking system maintains various content items with one or more content items associated with comments provided by social networking system users. When a user requests a content item associated with one or more comments, the social networking system determines likelihoods of the user performing a type of interaction with the one or more comments based on characteristics of the comments. For example, the social networking system determines likelihoods of the user requesting to view one or more of the comments. Based on the determined likelihoods, the social networking system generates an instruction describing presentation of comments. The instruction may identify a set of comments for presentation along with the content item that are selected based on the determined likelihoods.
1 . A computer-implemented method comprising:
receiving, from a client device of a user of a social networking system, a request for a content item associated with one or more comments representing information provided by users of the social networking system;
determining a likelihood of the user performing a type of interaction with one or more of the comments associated with the content item based at least in part on characteristics of the one or more comments;
generating information describing presentation of the one or more comments associated with the content item based at least in part on the determined likelihoods; and
transmitting the information describing presentation of the one or more comments associated with the content item to the client device along with instructions to present the content item and to present information associated with the one or more comments based on the information describing presentation of the one or more comments associated with the content item.
2 . The computer-implemented method of claim 1 , wherein determining likelihoods of the user performing a type of interaction with one or more of the comments associated with the content item based at least in part on characteristics of the one or more comments comprises:
determining a likelihood of the user requesting to view the one or more comments based on one or more characteristics of the one or more comments.
3 . The computer-implemented method of claim 2 , wherein generating information describing presentation of the one or more comments associated with the content item based at least in part on the determined likelihoods comprises:
generating an instruction to present at least a set of the one or more comments if the determined likelihood of the user requesting to view the one or more comments has at least a threshold value.
4 . The computer-implemented method of claim 3 , wherein the set of the one or more comments is selected based at least in part on the likelihoods of the user performing the type of interaction with one or more of the comments.
5 . The computer-implemented method of claim 4 , wherein the set of the one or more comments includes comments having at least a threshold likelihood of the user performing the type of interaction.
6 . The computer-implemented method of claim 1 , wherein generating information describing presentation of the one or more comments associated with the content item based at least in part on the determined likelihoods comprises:
ranking the one or more comments based at least in part on the determined likelihoods;
selecting a set of the one or more comments based at least in part on the ranking; and
generating information identifying the set of the one or more comments.
7 . The computer-implemented method of claim 1 , wherein a characteristic of a comment comprises an affinity between the user and an additional user associated with the comment.
8 . The computer-implemented method of claim 1 , wherein a characteristic of a comment comprises an affinity between the user and an additional user associated with the content item.
9 . The computer-implemented method of claim 1 , wherein the type of interaction with one or more of the comments comprises indicating a preference for one or more of the comments.
10 . A computer-implemented method comprising:
receiving, from a client device of a user of a social networking system, a request for a content item associated with one or more comments representing information provided by users of the social networking system;
determining likelihoods of the user performing a type of interaction with one or more of the comments associated with the content item based at least in part on characteristics of the one or more comments;
selecting a set of the one or more comments based at least in part on the determined likelihoods; and
transmitting the set of the one or more comments to a client device associated with the user along with the content item.
11 . The computer-implemented method of claim 10 , wherein selecting the set of the one or more comments based at least in part on the determined likelihoods comprises:
ranking the one or more comments based at least in part on the determined likelihoods;
selecting the set of the one or more comments based at least in part on the ranking;
and generating information identifying the set of the one or more comments.
12 . The computer-implemented method of claim 10 , wherein selecting the set of the one or more comments based at least in part on the determined likelihoods comprises:
selecting one or more comments having at least a threshold likelihood of the user performing the type of interaction.
13 . The computer-implemented method of claim 10 , further comprising:
determining a likelihood of the user requesting to view the one or more comments based on one or more characteristics of the one or more comments; and
transmitting an instruction to the client device to present the set of comments if the likelihood of the user requesting to view the one or more comments equals or exceeds a threshold value.
14 . The computer-implemented method of claim 10 , wherein a characteristic of a comment comprises an affinity between the user and an additional user associated with the content item.
15 . The computer-implemented method of claim 10 , wherein a characteristic of a comment comprises an affinity between the user and an additional user associated with the comment.
16 . The computer-implemented method of claim 10 , wherein the type of interaction with one or more of the comments comprises indicating a preference for one or more of the comments.
17 . The computer-implemented method of claim 10 , wherein selecting the set of the one or more comments based at least in part on the determined likelihoods comprises:
determining a type of the client device; and
selecting the set based at least in part on the determined likelihoods and the determined type.
18 . A computer program product comprising a computer readable storage medium having instructions encoded thereon that, when executed by a processor, cause the processor to:
receive, from a client device of a user of a social networking system, a request for a content item associated with one or more comments representing information provided by users of the social networking system;
determine likelihoods of the user performing a type of interaction with one or more of the comments associated with the content item based at least in part on characteristics of the one or more comments;
select a set of the one or more comments based at least in part on the determined likelihoods; and
transmit the set of the one or more comments to a client device associated with the user along with the content item.
19 . The computer program product of claim 18 , wherein select the set of the one or more comments based at least in part on the determined likelihoods comprises:
determine a type of the client device; and
select the set based at least in part on the determined likelihoods and the determined type.
20 . The computer program product of claim 18 , wherein select the set of the one or more comments based at least in part on the determined likelihoods comprises:
rank the one or more comments based at least in part on the determined likelihoods;
select the set of the one or more comments based at least in part on the ranking; and
generate information identifying the set of the one or more comments.