Systems and methods for associating tags with media assets based on verbal input

摘要

Systems and methods for tagging a media asset are provided. A plurality of communications is received from a plurality of users. Each of the plurality of communications includes words spoken by a respective one of the users while accessing the media asset and is associated with a media asset play position during which the respective words were spoken. A subset of the plurality of communications is selected for which the associated media asset play position is within a range of play positions, the range of play positions being shorter than the duration of the media asset. A word that a threshold number of the selected communications have in common is identified. The word is cross-referenced with an attribute database to retrieve an attribute associated with the word. The retrieved attribute is assigned to the media asset within the range of play positions.

主权项

1. A method for tagging a media asset, the method comprising:
receiving, with control circuitry, a plurality of communications from a plurality of users, wherein each of the plurality of communications includes words spoken by a respective one of the users while accessing the media asset, and wherein each of the communications is associated with a media asset play position during which the respective words were spoken; selecting a subset of the plurality of communications for which the associated media asset play position is within a range of play positions, the range of play positions being shorter than a duration of the media asset; identifying, with the control circuitry, a word that a threshold number of the selected communications have in common; retrieving from an attribute database an attribute associated with the word; and assigning the retrieved attribute to the media asset within the range of play positions.