DIGITAL MAGAZINE RECOMMENDATIONS BY TOPIC

摘要

A digital magazine server scores digital magazines based on how related the digital magazines are to each of a set of topics in a topic vector space, which allows ranking for each topic the magazines that are most closely related to the topic. The digital magazine server generates a magazine vector for the magazine in the topic vector space by aggregating extracted topics for the magazine and compares the magazine vector to each of the topics to determine a magazine-topic relevance score that indicates the relevance of the digital magazine to each topic in the topic vector space. The digital magazine server then ranks each of the digital magazines by their magazine-topic relevance scores for a particular topic, e.g., a trending topic from a user request, and selects a top number of magazines for the trending topic for the user.

主权项

1. A method for recommending content items on a topic to a user of a digital magazine server, the method comprising:
for each of a plurality of digital magazines:
identifying a plurality of content items associated with the digital magazine,extracting a topic vector for each content item, where the topic vector for a content item describes a relevance of the content item to each of a plurality of predefined topics in a topic vector space, anddetermining a topic vector for the digital magazine by aggregating the plurality of topic vectors for the content items of the digital magazine; and for each topic in the topic vector space:
calculating a magazine-topic relevance score for each digital magazine of the plurality of digital magazines, andranking the plurality of digital magazines based on the magazine-topic relevance scores associated with the plurality of digital magazines.