Character based media analytics
Techniques for analyzing media content are described. One technique generally comprises performing a regression analysis for characters in a plurality of media content based on user demographics, content outcome measure, and character models. The technique determines an attribute of significance. In some embodiments, the technique selects media content for display that depicts a character having at least a threshold value of the attribute of significance. In some embodiments, the technique displays media analytics for the attribute of significance determined based on a value of the attribute of significance exceeding a threshold significance value.
1. A computer-implemented method for analyzing a plurality of media content, the method comprising:
accessing respective character models of multiple female characters represented in the plurality of media content from an indexed table of a database;
determining, based on the respective character models of the multiple female characters, respective female attribute values of an attribute for the multiple female characters;
determining, based on the respective female attribute values, an overall female attribute value, wherein the overall female attribute value is an average of the respective female attribute values;
accessing respective character models of multiple male characters represented in the plurality of media content from the indexed table of the database;
determining, based on the respective character models of the multiple male characters, respective male attribute values of the attribute for the multiple male characters;
determining, based on the respective male attribute values, an overall male attribute value, wherein the overall male attribute value is an average of the respective male attribute values;
comparing the overall female attribute value with the the overall male attribute value, wherein comparing the overall female attribute value with the overall male attribute value comprises determining whether a difference between the overall female attribute value and the overall male attribute value satisfies a threshold; and
based on a result of the comparing, providing a notification for display, wherein the notification includes a prompt encouraging a user to decrease the difference between the overall female attribute value and the overall male attribute value.
2. The computer-implemented method of claim 1 , further comprising accessing salience values for the multiple female characters and salience values for the multiple male characters, wherein the average of the respective female attribute values is a salience-weighted average of the respective female attribute values that is based on the salience values for the multiple female characters, and wherein the average of the respective male attribute values is a salience-weighted average of the respective male attribute values that is based on the salience values for the multiple male characters.
3. The computer-implemented method of claim 1 , wherein providing the notification for display based on a result of the comparing comprises providing the notification for display based on the difference satisfying the threshold.
4. The computer-implemented method of claim 1 , wherein the notification includes an indication of whether the overall female attribute value or the overall male attribute value is greater and an indication of the attribute.
5. The computer-implemented method of claim 1 , wherein the attribute refers to a character quality, and wherein the character quality is a career, a demographic, a location, a social trait, a physical trait, or an intellectual trait.
6. The computer-implemented method of claim 5 , wherein the attribute is represented in a binary space.
7. The computer-implemented method of claim 5 , wherein the attribute is represented in a continuous space.
8. The computer-implemented method of claim 5 , wherein the attribute is one of a plurality of attributes, wherein the respective character models of the multiple female characters and the respective character models of the multiple male characters comprise respective multidimensional representations of the plurality of attributes.
9. The computer-implemented method of claim 1 , wherein the plurality of media content is a plurality of advertisements for a company.
10. The computer-implemented method of claim 1 , wherein the plurality of media content is a plurality of advertisements for an industry.
11. A non-transitory computer-readable medium having stored therein instructions that upon execution by a processor, cause performance of a set of acts comprising:
accessing respective character models of multiple female characters represented in a plurality of media content from an indexed table of a database;
determining, based on the respective character models of the multiple female characters, respective female attribute values of an attribute for the multiple female characters;
determining, based on the respective female attribute values, an overall female attribute value, wherein the overall female attribute value is an average of the respective female attribute values;
accessing respective character models of multiple male characters represented in the plurality of media content from the indexed table of the database;
determining, based on the respective character models of the multiple male characters, respective male attribute values of the attribute for the multiple male characters;
determining, based on the respective male attribute values, an overall male attribute value, wherein the overall male attribute value is an average of the respective male attribute values;
comparing the overall female attribute value with the overall male attribute value, wherein comparing the overall female attribute value with the overall male attribute value comprises determining whether a difference between the overall female attribute value and the overall male attribute value satisfies a threshold; and
based on a result of the comparing, providing a notification for display, wherein the notification includes a prompt encouraging a user to decrease the difference between the overall female attribute value and the overall male attribute value.
12. The non-transitory computer-readable medium of claim 11 , wherein the attribute is intelligence.
13. A computing system comprising:
a processor; and
a non-transitory computer-readable storage medium, having stored thereon program instructions that, upon execution by the processor, cause performance of a set of operations comprising:
accessing respective character models of multiple female characters represented in a plurality of media content from an indexed table of a database,
determining, based on the respective character models of the multiple female characters, respective female attribute values of an attribute for the multiple female characters,
determining, based on the respective female attribute values, an overall female attribute value, wherein the overall female attribute value is an average of the respective female attribute values,
accessing respective character models of multiple male characters represented in the plurality of media content from the indexed table of the database,
determining, based on the respective character models of the multiple male characters, respective male attribute values of the attribute for the multiple male characters,
determining, based on the respective male attribute values, an overall male attribute value, wherein the overall female attribute value is an average of the respective female attribute values,
comparing the overall female attribute value with the overall male attribute value, wherein comparing the overall female attribute value with the overall male attribute value comprises determining whether a difference between the overall female attribute value and the overall male attribute value satisfies a threshold, and
based on a result of the comparing, providing a notification for display, wherein the notification includes a prompt encouraging a user to decrease the difference between the overall female attribute value and the overall male attribute value.