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:
accessing, by a computing system, character preference data for a user, wherein the character preference data identifies a first character that the user likes and a second character that the user dislikes, and wherein the first character and the second character appear in media content;
accessing, by the computing system, attribute values of the first character that the user likes;
accessing, by the computing system, attribute values of the second character that the user dislikes;
determining, by the computing system based on the attribute values of the first character and the attribute values of the second character, a character preference function for the 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 attribute of a plurality of attributes; and
using, by the computing system, the character preference function for the user to select one or more media contents from among a plurality of media contents, wherein using the character preference function for the user to select one or more media contents from among a plurality of media contents comprises determining a character rating for a character in a given media content from among the plurality of media contents based on the character preference function for the user and a character model for the character and recommending, based on the character rating, the given media content to the user.
2. The computer-implemented method of claim 1 , wherein determining the character preference function for the user comprises determining that the plurality of preference coefficients maximize a joint probability that the user likes the first character and dislikes the second character.
3. The computer-implemented method of claim 1 , further comprising:
prompting the user to identify characters that the user likes; and
based on the prompting, receiving the character preference data identifying the first character that the user likes.
4. The computer-implemented method of claim 1 , further comprising:
accessing physiological recording data for the user; and
determining the first character that the user likes using the physiological recording data for the user.
5. The computer-implemented method of claim 4 , wherein the physiological recording data comprises eye-tracking information or facial response information.
6. The computer-implemented method of claim 4 , wherein the physiological recording data is indicative of reactions of the user to characters as the user consumes the media content.
7. The computer-implemented method of claim 1 , wherein the character model for the character comprises a multidimensional representation of the plurality of attributes.
8. The computer-implemented method of claim 1 , further comprising determining a media content rating for the given media content based on the character rating for the character.
9. The computer-implemented method of claim 8 , wherein the recommending the given media content to the user is further based on the media content rating.
10. The computer-implemented method of claim 1 , further comprising rating a likelihood that the user will enjoy the given media content based on the character preference function for the user and the character model.
11. The computer-implemented method of claim 1 , wherein accessing attribute values of the first character that the user likes comprises:
accessing a character model for the first character that the user likes; and
accessing, from the character model for the first character that the user likes, the attribute values of the first character that the user likes.
12. 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:
accessing character preference data for a user, wherein the character preference data identifies a first character that the user likes and a second character that the user dislikes, and wherein the first character and the second character appear in media content;
accessing attribute values of the first character that the user likes;
accessing attribute values of the second character that the user dislikes;
determining, based on the attribute values of the first character and the attribute values of the second character, a character preference function for the 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 attribute of a plurality of attributes; and
using the character preference function for the user to select one or more media contents from among a plurality of media contents, wherein using the character preference function for the user to select one or more media contents from among a plurality of media contents comprises determining a character rating for a character in a given media content from among the plurality of media contents based on the character preference function for the user and a character model for the character and recommending, based on the character rating, the given media content to the user.
13. The non-transitory computer-readable medium of claim 12 , wherein the set of acts further comprises:
prompting the user to identify characters that the user likes; and
based on the prompting, receiving the character preference data identifying the first character that the user likes.
14. The non-transitory computer-readable medium of claim 12 , wherein the set of acts further comprises:
accessing physiological recording data for the user; and
determining the first character that the user likes using the physiological recording data for the user.
15. A computing system comprising a processor coupled to a memory, the computing system configured for performing a set of acts comprising:
accessing character preference data for a user, wherein the character preference data identifies a first character that the user likes and a second character that the user dislikes, and wherein the first character and the second character appear in media content;
accessing attribute values of the first character that the user likes;
accessing attribute values of the second character that the user dislikes;
determining, based on the attribute values of the first character and the attribute values of the second character, a character preference function for the 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 attribute of a plurality of attributes; and
using the character preference function for the user to select one or more media contents from among a plurality of media contents, wherein using the character preference function for the user to select one or more media contents from among a plurality of media contents comprises determining a character rating for a character in a given media content from among the plurality of media contents based on the character preference function for the user and a character model for the character and recommending, based on the character rating, the given media content to the user.
16. The computing system of claim 15 , wherein the set of acts further comprises:
prompting the user to identify characters that the user likes; and
based on the prompting, receiving the character preference data identifying the first character that the user likes.
17. The computing system of claim 15 , wherein the set of acts further comprises:
accessing physiological recording data for the user; and
determining the first character that the user likes using the physiological recording data for the user.