Algorithm Radio for Arbitrary Text Queries

摘要

Text queries from the user may be received. Playlists associated with the text query can be identified. The relevance score may be calculated for each of the playlists based at least in part on the relevance of the corresponding playlist to the text query. In addition, content items may be identified, where each of the content items is included in a playlist of at least one of the playlists. For each of the identified content items, one or more playlists containing the corresponding content item may be identified. The score for each of the content items may be calculated based on a relevance score for each of the playlists that include the corresponding content item. In addition, a new playlist may be created for the user based on the scores for each of the content items.