Metadata refinement using behavioral patterns

摘要

A system and method of metadata refinement using behavioral patterns is disclosed. In some embodiments, user behavioral data for results of a search query is received. The results can include an untagged item and a plurality of tagged items. A determination can then be made that the tagged items have been assigned a first type of metadata not assigned to the untagged item. The untagged item can then be identified as a candidate to be tagged with the first type of metadata assigned to the tagged items based on the user behavioral data. In some embodiments, the user behavioral data comprises clickstream data indicating that a user selected the untagged item and the tagged items during a single search event.

主权项

1. A method comprising:
receiving user behavioral data for search results of a search query, the user behavioral data comprising clickstream data indicating that a user selected the search results including an untagged item and a plurality of tagged items during a single search event; determining that the selected plurality of tagged items corresponds to a first type of metadata and the untagged items are selected during the single search event that includes the plurality of tagged items, the selected plurality of tagged items transgressing a threshold number of selected tagged items that corresponds to the first type of metadata; identifying, by a machine having a memory and at least one processor, the untagged item as a candidate to be tagged with the first type of metadata corresponding to the tagged items based on the determined plurality of tagged items corresponding to the first type of metadata and transgressing the threshold number of selected tagged items; and assigning data corresponding to the first type of metadata for the tagged items to the untagged item in response to the identifying the untagged item as the candidate to be tagged with the first type of metadata.