Media content discovery and character organization techniques
Techniques for recommending media are described. A character preference function comprising a plurality of preference coefficients is accessed. A first character model comprises a first set of attribute values for the plurality of attributes of a first character. The first and second characters are associated with a first and second salience value, respectively. A second character model comprises a second set of attribute values for the plurality of attributes of a second character of the plurality of characters. A first character rating is calculated using the plurality of preference coefficients and the first set of attribute values. A second character rating of the second character is calculated using the plurality of preference coefficients with the second set of attribute values. A media rating is calculated based on the first and second salience values and the first and second character ratings. A media is recommended based on the media rating.
1. A method comprising:
identifying, by a computing system, textual content that is associated with a character of a media content, wherein the textual content is contained within an electronic source;
determining, by the computing system from the textual content, an attribute term associated with the character;
mapping, by the computing system using stored mapping data, the attribute term to an attribute of a plurality of attributes of the character; and
updating, by the computing system based on the attribute term, an attribute value for the attribute in a character model for the character, wherein the character model comprises a multidimensional representation of the plurality of attributes.
2. The method of claim 1 , wherein updating the attribute value based on the attribute term comprises:
determining a strength value corresponding to the attribute term; and
increasing or decreasing the attribute value based on the strength value.
3. The method of claim 1 , wherein the electronic source comprises a webpage, social networking page, or social networking chatter.
4. The method of claim 1 , wherein determining the attribute term associated with the character comprises determining an attribute term that appears in the electronic source less than a threshold number of words away from a name of the character or an image of the character.
5. The method of claim 1 , wherein the electronic source comprises user feedback.
6. The method of claim 5 , further comprising:
determining that a user has consumed the media content; and
responsive to the determining that the user has consumed the media content, prompting the user to provide the user feedback.
7. The method of claim 1 , wherein the attribute refers to a quality of the character, and wherein the quality is a career, a demographic, a location, a social trait, a physical trait, or an intellectual trait.
8. The method of claim 1 , wherein the attribute is represented in a binary space.
9. The method of claim 1 , wherein the attribute is represented in a continuous space.
10. The method of claim 1 , further comprising:
accessing a character preference function of a user; and
recommending the media content to the user based on the character preference function and the character model.
11. The method of claim 1 , further comprising:
accessing a character preference function of a user; and
rating a likelihood that the user will enjoy the media content based on the character preference function and the character model.
12. The method of claim 1 , further comprising:
accessing a character preference function of a user; and
recommending the character to the user based on the character preference function and the character model.
13. The method of claim 1 , further comprising:
determining that a user likes the character;
determining a second character that has a distance from the character that is below a threshold, wherein the distance represents a degree of similarity between the character and the second character; and
based on the determining that the distance is below the threshold, recommending the second character to the user.
14. The method of claim 13 , wherein recommending the second character to the user comprises representing a second media content that includes the second character to the user.
15. The method of claim 1 , further comprising:
determining that a user likes a second character;
determining that a distance between the character and the second character is below a threshold, wherein the distance represents a degree of similarity between the character and the other character; and
based on the determining that the distance is below the threshold, recommending the character to the user.
16. A non-transitory computer-readable medium having stored thereon program instructions that upon execution by a processor, cause performance of a set of acts comprising:
identifying textual content that is associated with a character of a media content, wherein the textual content is contained within an electronic source;
determining, from the textual content, an attribute term associated with the character;
mapping, using stored mapping data, the attribute term to an attribute of a plurality of attributes of the character; and
updating, based on the attribute term, an attribute value for the attribute in a character model for the character, wherein the character model comprises a multidimensional representation of the plurality of attributes.
17. The non-transitory computer-readable medium of 16 , wherein updating the attribute value based on the attribute term comprises:
determining a strength value corresponding to the attribute term; and
increasing or decreasing the attribute value based on the strength value.
18. The non-transitory computer-readable medium of claim 16 , wherein the electronic source comprises a webpage, social networking page, or social networking chatter.
19. The non-transitory computer-readable medium of claim 16 , wherein the attribute refers to a quality of the character, and wherein the quality is a career, a demographic, a location, a social trait, a physical trait, or an intellectual trait.
20. A computing system comprising a computer processor coupled to a memory, the computer system configured for performing a set of acts comprising:
identifying textual content that is associated with a character of a media content, wherein the textual content is contained within an electronic source;
determining, from the textual content, an attribute term associated with the character;
mapping, using stored mapping data, the attribute term to an attribute of a plurality of attributes of the character; and
updating, based on the attribute term, an attribute value for the attribute in a character model for the character, wherein the character model comprises a multidimensional representation of the plurality of attributes.