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 computer-implemented method comprising:
determining, by a computing system, one or more user attribute values characterizing a given user from at least one of user input or a stored user profile;
accessing, by the computing system from respective user profiles stored in a database, respective character preference functions for a plurality of other users having at least one user attribute value in common with the one or more user attribute values of the given user, wherein each respective character preference function comprises information identifying a respective plurality of preference coefficients, with each preference coefficient of the respective plurality of preference coefficients associated with a respective character attribute of a plurality of character attributes;
statistically analyzing, by the computing system, the respective character preference functions, accessed from the respective user profiles, for the plurality of other users to make a determination of a character preference function for the given user, wherein the character preference function comprises information identifying a plurality of preference coefficients, with each preference coefficient of the plurality of preference coefficients associated with a respective character attribute of the plurality of character attributes, and wherein character preference function information for the given user has not been provided by the given user separately from the determination; and
applying, by the computing system, a media rating determined from the character preference function for the given user to select one or more media contents from among a plurality of media contents.
2. The computer-implemented method of claim 1 , wherein the one or more user attribute values of the given user comprise a gender, and wherein the at least one user attribute value in common is the gender.
3. The computer-implemented method of claim 1 , wherein the one or more user attribute values of the given user correspond to an education attribute, and wherein the at least one user attribute value in common corresponds to the education attribute.
4. The computer-implemented method of claim 3 , wherein the education attribute comprises a type of degree.
5. The computer-implemented method of claim 1 , wherein statistically analyzing the respective character preference functions for the plurality of other users to make the determination of the character preference function for the given user comprises deriving the character preference function for the given user from statistics indicative of the respective preference coefficients within the respective character preference functions for the plurality of other users.
6. The computer-implemented method of claim 1 , wherein statistically analyzing the respective character preference functions for the plurality of other users to make the determination of the character preference function for the given user comprises:
determining that the respective character preference functions for a majority of users of the plurality of other users include a given preference coefficient having values that are greater than zero; and
designating as the given preference coefficient within the character preference function for the given user a value that is greater than zero.
7. The computer-implemented method of claim 1 , further comprising identifying the plurality of other users having the at least one user attribute value in common with the one or more user attribute values of the given user.
8. The computer-implemented method of claim 1 , wherein applying the criteria determined from the character preference function for the given user to select the one or more media contents from among a plurality of media contents comprises determining a character rating for a character in a media content from among the plurality of media contents based on the character preference function for the given user and a character model for the character.
9. The computer-implemented method of claim 8 , wherein the character model for the character comprises a multidimensional representation of the plurality of attributes.
10. The computer-implemented method of claim 8 , further comprising determining a media content rating for the media content based on the character rating for the character.
11. The computer-implemented method of claim 10 , further comprising recommending the media content to the given user based on the media content rating.
12. The computer-implemented method of claim 8 , further comprising rating a likelihood that the given user will enjoy the media content based on the character preference function for the given user and the character model.
13. A non-transitory computer-readable medium having stored thereon program instructions that, upon execution by a processor of a system, cause the system to perform a set of acts comprising:
determining one or more user attribute values characterizing a given user from at least one of user input or a stored user profile;
accessing, from respective user profiles stored in a database, respective character preference functions for a plurality of other users having at least one user attribute value in common with the one or more user attribute values of the given user, wherein each respective character preference function comprises information identifying a respective plurality of preference coefficients, with each preference coefficient of the respective plurality of preference coefficients associated with a respective character attribute of a plurality of character attributes;
statistically analyzing the respective character preference functions, accessed from the respective user profiles, for the plurality of users to make a determination of a character preference function for the given user, wherein the character preference function comprises information identifying a plurality of preference coefficients, with each preference coefficient of the plurality of preference coefficients associated with a respective character attribute of the plurality of character attributes, and wherein character preference function information for the given user has not been provided by the given user separately from the determination; and
applying a media rating determined from the character preference function for the given user to select one or more media contents from among a plurality of media contents.
14. The non-transitory computer-readable medium of claim 13 , wherein statistically analyzing the respective character preference functions for the plurality of other users to make the determination of the character preference function for the given user comprises deriving the character preference function for the given user from statistics indicative of the respective preference coefficients within the respective character preference functions for the plurality of other users.
15. The non-transitory computer-readable medium of claim 13 , wherein statistically analyzing the respective character preference functions for the plurality of other users to make the determination of the character preference function for the given user comprises:
determining that the respective character preference functions for a majority of users of the plurality of other users include a given preference coefficient having values that are greater than zero; and
designating as the given preference coefficient within the character preference function for the given user a value that is greater than zero.
16. The non-transitory computer-readable medium of claim 13 , wherein applying the criteria determined from the character preference function for the given user to select the one or more media contents from among a plurality of media contents comprises determining a character rating for a character in a media content from among the plurality of media contents based on the character preference function for the given user and a character model for the character.
17. A computing system comprising a processor coupled to a memory, the computing system configured for performing a set of acts comprising:
determining one or more user attribute values characterizing a given user from at least one of user input or a stored user profile;
accessing, from respective user profiles stored in a database, respective character preference functions for a plurality of other users having at least one user attribute value in common with the one or more user attribute values of the given user, wherein each respective character preference function comprises information identifying a respective plurality of preference coefficients, with each preference coefficient of the respective plurality of preference coefficients associated with a respective character attribute of a plurality of character attributes;
statistically analyzing the respective character preference functions, accessed from the respective user profiles, for the plurality of other users to make a determination of a character preference function for the given user, wherein the character preference function comprises information identifying a plurality of preference coefficients, with each preference coefficient of the plurality of preference coefficients associated with a respective character attribute of the plurality of character attributes, and wherein character preference function information for the given user has not been provided by the given user separately from the determination; and
applying a media rating determined from the character preference function for the given user to select one or more media contents from among a plurality of media contents.
18. The computing system of claim 17 , wherein statistically analyzing the respective character preference functions for the plurality of other users to make the determination of the character preference function for the given user comprises deriving the character preference function for the given user from statistics indicative of the respective preference coefficients within the respective character preference functions for the plurality of other users.
19. The computing system of claim 17 , wherein statistically analyzing the respective character preference functions for the plurality of other users to make the determination of the character preference function for the given user comprises:
determining that the respective character preference functions for a majority of users of the plurality of other users include a given preference coefficient having values that are greater than zero; and
designating as the given preference coefficient within the character preference function for the given user a value that is greater than zero.
20. The computing system of claim 17 , wherein applying the criteria determined from the character preference function for the given user to select the one or more media contents from among a plurality of media contents comprises determining a character rating for a character in a media content from among the plurality of media contents based on the character preference function for the given user and a character model for the character.