METHODS AND SYSTEMS FOR UTILIZING ACTIVITY DATA WITH CLUSTERED EVENTS

摘要

The present disclosure relates to methods and systems for clustering individual items of web content, and then utilizing activity and profile data to both select clusters of content items for presentation to a user, and determining how the selected clusters of content items are presented to the user of an online social network service. With some embodiments, the activity data are derived by monitoring and detection interactions with the individual items of web content by an individual user, or other users with whom the individual user is related, as established via, and defined by, the social network service.

主权项

1. A method comprising:
by one or more processors of a set of machines, performing an analysis of a plurality of documents among which some documents each reference a common topic; by one or more processors of the set of machines, clustering the plurality of documents by topic into a set of document clusters that each correspond to a different topic and that includes a document cluster in which the documents that reference the common topic are grouped; by one or more processors of the set of machines, detecting that a first member of a social networking service has interacted with a first document in the document cluster, the social networking service storing a profile that indicates a type of relationship between the first member and a second member of the social networking service; by one or more processors of the set of machines, determining a rank of the document cluster, the rank representing a likelihood that the second member is interested in the common topic of the document cluster, the determining being based on the detecting that the first member has interacted with the first document and based on the type of relationship between the first and second members; and by one or more processors of the set of machines, presenting the second member with a reference to a second document selected from the document cluster based on the determined rank of the document cluster.