Google Inc.

Jiahui Liu

Peter J Dolan

Systems and methods for recommending media content items are provided. In some implementations, a method includes, identifying a first set of media items selected by a first plurality of users; causing a second set of media items to be displayed to a second user not included in the first plurality of users in accordance with the first set of media items. The first set of media items and the second set of media items are associated with a same media item category. In some implementations, the method optionally includes, identifying the second set of media items without regard to media content item selection history associated with the second user. In some implementations, the first and second sets of media items are news items.

Systems and methods for recommending media content items

A method includes: obtaining first click distribution data for a first subset of a plurality of media items, each of which is associated with one or more item categories, determining from the first click distribution data likelihood of a generic user selecting media items associated with at least a subset of the item categories, obtaining second click distribution data from a particular user for a second subset of the plurality of media items, determining, based on differences between the first and second click distribution data, an adjusted likelihood of the particular user selecting media items associated with the at least a subset of the item categories, and transmitting, based on the adjusted likelihood, to a client device associated with the particular user recommendations related to a third subset of the plurality of media items and respective item categories thereof.

News topic-interest-based recommendations twiddling

According to some embodiments, a plurality of media items having associated classes are collected and stored in a media item repository. Generic selection data for a plurality of users of the media repository is collected and stored. The plurality of users includes a particular user of the media item repository. A likelihood of a generic user selecting media items associated with particular classes is determined. A likelihood of a particular user selecting media items associated with particular classes is determined. A relative likelihood of the particular user selecting media items associated with the particular classes compared to the generic user is determined. A first collection of media items reflecting the relative likelihood is sent to the particular user. Each of the media items is selectable by the particular user.

Growing community of inventors

Mountain View, CA, United States of America

Jiahui Liu