Sentiment mapping in a media content item

Abstract

A media content item is evaluated for its “sentiment states.” That is, segments of the content item are determined to be, for example, “happy,” “exciting,” “sad,” “funny,” and the like. A “sentiment map” is created that delimits segments of the content item and contains the sentiment-state keywords associated with the segments. Some maps include an amplitude for each assigned sentiment keyword and a confidence value for the segment delimitation and for each keyword. As an exemplary use of the sentiment map, an advertisement broker matches the sentiments of his advertisement offerings with segments of a content item in order to place appropriate advertisements at times when they would be most favorably received. In another example, a recommender system recommends to a user a content item whose sentiment map compares favorably to that of a content item already enjoyed by the user.

We claim: 
     
         1 . A method for associating a second media content item with a first media content item, the method comprising:
 receiving, by a recommender system, a first map of a first delimited segment of the first media content item, the first map comprising a first sentiment-state keyword associated with the first segment and a delimitation of the first segment;   receiving, by the recommender system, a second map of a second delimited segment of the second media content item, the second map comprising a second sentiment-state keyword associated with the second segment and a delimitation of the second segment;   comparing, by the recommender system, the first and second maps; and   if a result of the comparison is favorable, then associating, by the recommender system, the second media content item with the first media content item.   
     
     
         2 . The method of  claim 1  wherein the first and second media content items are selected from the group consisting of: a movie, a television program, a radio program, a segment of video, a segment of audio, a song, a music video, a personal message, a public-service message, a service alert, a health-service recommendation, a web page, an e-mail message, and a telephone call. 
     
     
         3 . The method of  claim 1  wherein the recommender system is selected from the group consisting of: a set-top box, a personal communications device, a mobile telephone, a personal digital assistant, a personal computer, a tablet computer, a gaming console, a head-end server, a server, and a plurality of servers. 
     
     
         4 . The method of  claim 1  wherein the first delimited segment comprises the entire first media content item. 
     
     
         5 . The method of  claim 1  wherein the first map further comprises a confidence value associated with the delimitation of the first segment. 
     
     
         6 . The method of  claim 1 :
 wherein receiving the first map comprises receiving maps of a plurality of segments of the first media content item; and   wherein at least two of the plurality of delimited segments overlap.   
     
     
         7 . The method of  claim 1  wherein the first sentiment-state keyword is selected from the group consisting of: happy, sad, funny, successful, romantic, exciting, violent, unknown. 
     
     
         8 . The method of  claim 1  wherein the first map comprises an amplitude value associated with the first sentiment-state keyword. 
     
     
         9 . The method of  claim 1  wherein the first map comprises a keyword confidence value associated with the first sentiment-state keyword. 
     
     
         10 . The method of  claim 1  wherein the first map comprises a plurality of sentiment-state keywords associated with the first delimited segment. 
     
     
         11 . The method of  claim 1  further comprising:
 sending, by the recommender system to a consumer of the first media content item, a recommendation of the second media content item. 
 
     
     
         12 . A recommender system for associating a second media content item with a first media content item, the recommender system comprising:
 a network interface configured for receiving a map of a first delimited segment of the first media content item, the map comprising a first sentiment-state keyword associated with the first segment and a delimitation of the first segment, and for receiving a map of a second delimited segment of the second media content item, the map comprising a second sentiment-state keyword associated with the second segment and a delimitation of the second segment; and   a processor operatively connected to the network interface, the processor configured for:
 comparing the maps of the first and second delimited segments; and 
 if a result of the comparison is favorable, then associating the second media content item with the first media content item.