Systems and methods for associating tags with media assets based on verbal input
View Patent ↗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.
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.
2. The method of claim 1 , wherein each of the plurality of users is located in a different household when accessing the media asset.
3. The method of claim 1 , wherein the attribute is different from the identified word.
4. The method of claim 1 further comprising:
retrieving closed-captioning information corresponding to the range of play positions;
identifying a subject based on the retrieved closed-captioning information; and
associating the attribute with the identified subject.
5. The method of claim 4 , wherein the subject is an actor, character or person within the media asset.
6. The method of claim 4 further comprising:
identifying a website associated with the subject; and
causing at least one of the attribute and the identified word to be posted on the website.
7. The method of claim 4 , wherein identifying the subject comprises:
determining a character whose speech corresponds to the closed-captioning information; and
selecting, as the subject, an actor who is performing a role of the character.
8. The method of claim 4 further comprising processing a cast list associated with the media asset to identify the subject.
9. The method of claim 1 , wherein the retrieved attribute includes a genre or category associated with the identified word.
10. The method of claim 1 further comprising generating a recommendation or search result based on the retrieved attribute.
11. A system for tagging a media asset, the system comprising:
control circuitry configured to:
receive 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;
select 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;
identify a word that a threshold number of the selected communications have in common;
retrieve from an attribute database an attribute associated with the word; and
assign the retrieved attribute to the media asset within the range of play positions.
12. The system of claim 11 , wherein each of the plurality of users is located in a different household when accessing the media asset.
13. The system of claim 11 , wherein the attribute is different from the identified word.
14. The system of claim 11 , wherein the control circuitry is further configured to:
retrieve closed-captioning information corresponding to the range of play positions;
identify a subject based on the retrieved closed-captioning information; and
associate the attribute with the identified subject.
15. The system of claim 14 , wherein the subject is an actor, character or person within the media asset.
16. The system of claim 14 , wherein the control circuitry is further configured to:
identify a website associated with the subject; and
cause at least one of the attribute and the identified word to be posted on the website.
17. The system of claim 14 , wherein the control circuitry is further configured to:
determine a character whose speech corresponds to the closed-captioning information; and
select, as the subject, an actor who is performing a role of the character.
18. The system of claim 14 , wherein the control circuitry is further configured to process a cast list associated with the media asset to identify the subject.
19. The system of claim 11 , wherein the retrieved attribute includes a genre or category associated with the identified word.
20. The system of claim 11 , wherein the control circuitry is further configured to generate a recommendation or search result based on the retrieved attribute.