Abstract: Methods, systems, and computer programs are presented for recommending a group for posting content generated by a user. One method includes an operation for detecting a post of a user being added to an online service. The method further includes an operation for determining post interest scores for the post. The post interest scores are for a plurality of interests and each interest is associated with a topic. A match score is calculated for a plurality of groups based on the post interest scores, where the match score for each group indicates a degree of relevance of the post to the group. The method further includes operations for determining whether to recommend a group, from the plurality of groups, for including the post of the user in a feed of the recommended group, and for causing presentation of the recommended group based on the determined recommendation.

Abstract: Methods, systems, and computer programs are presented for determining when to recommend posting in a group and joining a group. One method includes clustering posts by associating a topic identifier with each post based on the post text, and mapping each of the groups to one of the topic identifiers based on topics associated with the posts. A topic-to-group table, mapping each of the topic identifiers to one or more of the groups, is created, and a post classifier model is trained with the posts text and the topic identifiers. When an additional post is entered, the model determines a topic identifier for the additional post based on text of the additional post, and a group recommendation is determined for posting the additional post based on the topic identifier for the additional post and the table. The group recommendation is presented for posting the additional post in the recommended group.

Abstract: Methods, systems, and computer programs are presented for recommending a group for posting content generated by a user. One method includes an operation for detecting a post of a user being added to an online service. The method further includes an operation for determining post interest scores for the post. The post interest scores are for a plurality of interests and each interest is associated with a topic. A match score is calculated for a plurality of groups based on the post interest scores, where the match score for each group indicates a degree of relevance of the post to the group. The method further includes operations for determining whether to recommend a group, from the plurality of groups, for including the post of the user in a feed of the recommended group, and for causing presentation of the recommended group based on the determined recommendation.