发明名称 |
FORMATION OF TOPIC PROFILES FOR PREDICTION OF TOPIC INTEREST GROUPS |
摘要 |
An analysis system analyzes known user affinities to identify particular objects that serve as useful predictors of whether a given user will have an affinity for a given topic, even if the user has not previously expressly specified an affinity for that topic. Specifically, both the topic group of users associated with a given topic and the category group of users associated with the topic's more general category are identified. For each of a set of objects, degrees of divergence between the topic group and the category group are evaluated for a criterion evaluated with respect to the object. A topic profile is created based on objects for which there is a high degree of divergence. |
申请公布号 |
US2014172857(A1) |
申请公布日期 |
2014.06.19 |
申请号 |
US201213720756 |
申请日期 |
2012.12.19 |
申请人 |
Facebook |
发明人 |
Powell Spencer |
分类号 |
G06F17/30 |
主分类号 |
G06F17/30 |
代理机构 |
|
代理人 |
|
主权项 |
1. A computer-implemented method comprising:
identifying a topic group of users of a social networking system that have expressed an affinity for a page of the social networking system that corresponds to a first topic; identifying a category that includes the first topic and a plurality of other topics; identifying a category group of users of the social networking system that have expressed an affinity for a page corresponding to at least one of the topics included in the category; for each page of a plurality of pages of a social networking system, each page having a corresponding topic:
computing a user interest measure quantifying an amount of interest expressed by users of the topic group in the topic corresponding to the page,computing a category interest measure quantifying an amount of interest expressed by users of the category group in the topic corresponding to the page, andcomputing a divergence measure based on the user interest measure and the category interest measure; generating, for the first topic, a topic profile based on the divergence measures; and storing the topic profile.
|
地址 |
Menlo Park CA US |