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 comprising:
obtaining, by a computing system, a set of videos;
determining, by the computing system, a list of characters that are depicted in videos of the set of videos;
determining, by the computing system, values of at least one character attribute for respective characters of the list of characters;
determining, by the computing system, a first salience value for a first character of the list of characters, wherein the first character is depicted in a first video of the set of videos, and wherein the first salience value is a salience of the first character relative to a total salience of other characters associated with the first video, and wherein the salience of the first character is calculated by a measuring software module, and is at least one of:
a measure a number of reactions detected in social media relating to the first character,
a measure of a prevalence of social media coverage of the first character, or
based on observation of physiological response of viewers;
determining, by the computing system, a first attribute-level value for the first video based at least on the first salience value;
determining, by the computing system, a second salience value for a second character of the list of characters, wherein the second character is depicted in a second video of the set of videos, and wherein the second salience value is a salience of the second character relative to other characters associated with the second video;
determining, by the computing system, a second attribute-level value for the second video based at least on the second salience value;
computing, by the computing system, an index of videos based at least on (i) the first attribute-level value as determined based at least on the first salience value, and (ii) the second attribute-level value;
indexing, by the computing system, the first video and the second video by the index of videos;
storing, by the computing system, the index of videos in a database;
retrieving, by the computing system, information for at least one video of the set of videos using the index of videos; and
generating, for a display device, a display of at least one of the at least one video or the retrieved information for the at least one video, selected based on the index of videos, wherein generating the display comprises recommending, base at least on the first salience value, the at least one video.
2. The computer-implemented method of claim 1 , wherein the first attribute-level is based further on a first value of a first character attribute for the first character.
3. The computer-implemented method of claim 2 , determining the first salience value for the first character of the list of characters further comprises:
aggregating the first value of the character attribute for the first character and a third value of the first character attribute for a third character of the first video.
4. The computer-implemented method of claim 1 , wherein the second attribute-level is based further on a second value of a second character attribute for the second character.
5. The computer-implemented method of claim 1 , further comprising:
determining a number of occurrences in social media of at least one form of reference to the first character; and
determining a number of occurrences in social media of the at least one form of reference to the other characters.
6. The computer-implemented method of claim 1 , further comprising:
determining a number of social media search results for the first character; and
determining a number of social media search results for the other characters.
7. The computer-implemented method of claim 1 , further comprising:
using eye-tracking data to assess a measure of how much time at least one viewer looked at the first character.
8. The computer-implemented method of claim 1 , wherein determining the second salience value for the second character of the list of characters comprises:
determining at least one of:
the salience of the second character relative to the other characters in the second video,
the salience of the second character as a measure of social media reactions for the second character relative to that of the other characters,
the salience of the second character as a measure of a prevalence of social media coverage of the second character, or
the salience of the second character according to observation of physiological response of viewers.
9. The computer-implemented method of claim 1 , further comprising:
indexing, by the computing system, the respective characters using the values of the at least one character attribute for the respective characters;
retrieving, by the computing system, information for at least one character depicted in a video of the set of videos using the index of characters;
obtaining a query that specifies a value of a third character attribute and a value of a fourth character attribute;
identifying, using the index of characters, one or more characters having the value of the third character attribute and the value of the fourth character attribute;
identifying a video that depicts a character of the one or more characters; and
providing an indication of the video for display.
10. The computer-implemented method of claim 1 , wherein determining the values of the at least one character attribute for the respective characters of the list of characters comprises:
accessing a database that stores character models for the respective characters; and
retrieving the values of the at least one character attribute from the character models.
11. The computer-implemented method of claim 1 , wherein the at least one character attribute comprises a social trait, a physical trait, or an intellectual trait.
12. A computing system comprising a processor coupled to a memory, the computing system configured for performing a set of acts comprising:
obtaining a set of videos;
determining a list of characters that are depicted in videos of the set of videos;
determining values of at least one character attribute for respective characters of the list of characters;
determining a first salience value for a first character of the list of characters, wherein the first character is depicted in a first video of the set of videos, and wherein the first salience value is a salience of the first character relative to a total salience of other characters associated with the first video, and wherein the salience of the first character is calculated by a measuring software module, and is at least one of:
a measure a number of reactions detected in social media relating to the first character,
a measure of a prevalence of social media coverage of the first character, or
based on observation of physiological response of viewers;
determining a first attribute-level value for the first video based at least on the first salience value;
determining a second salience value for a second character of the list of characters, wherein the second character is depicted in a second video of the set of videos, and wherein the second salience value is a salience of the second character relative to other characters associated with the second video;
determining a second attribute-level value for the second video based at least on the second salience value;
computing an index of videos based at least on (i) the first attribute-level value as determined based at least on the first salience value, and (ii) the second attribute-level value;
indexing first video and the second video by the index of videos; and
storing the index of videos in a database;
retrieving information for at least one video of the set of videos using the index of videos; and
generating, for a display device, a display of at least one of the at least one video or the retrieved information for the at least one video, selected based on the index of videos, wherein generating the display comprises recommending, base at least on the first salience value, the at least one video.
13. The computing system of claim 12 , wherein the first attribute-level is based further on a first value of a first character attribute for the first character.
14. The computing system of claim 12 , wherein the set of acts further comprises:
determining a number of occurrences in social media of at least one form of reference to the first character; and
determining a number of occurrences in social media of the at least one form of reference to the other characters.
15. The computing system of claim 12 , wherein the set of acts further comprises:
determining a number of social media search results for the first character; and
determining a number of social media search results for the other characters.
16. The computing system of claim 12 , wherein the set of acts further comprises:
using eye-tracking data to assess a measure of how much time at least one viewer looked at the first character.
17. The computing system of claim 12 , wherein the acts further comprise:
indexing, by the computing system, the respective characters using the values of the at least one character attribute for the respective characters;
retrieving, by the computing system, information for at least one character depicted in a video of the set of videos using the index of characters;
obtaining a query that specifies a value of a third character attribute and a value of a fourth character attribute;
identifying, using the index of characters, one or more characters having the value of the third character attribute and the value of the fourth character attribute;
identifying a video that depicts a character of the one or more characters; and
providing an indication of the video for display.
18. 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:
obtaining a set of videos;
determining a list of characters that are depicted in videos of the set of videos;
determining values of at least one character attribute for respective characters of the list of characters;
determining a first salience value for a first character of the list of characters, wherein the first character is depicted in a first video of the set of videos, and wherein the first salience value is a salience of the first character relative to a total salience of other characters associated with the first video, and wherein the salience of the first character is calculated by a measuring software module, and is at least one of:
a measure a number of reactions detected in social media relating to the first character,
a measure of a prevalence of social media coverage of the first character, or
based on observation of physiological response of viewers;
determining a first attribute-level value for the first video based at least on the first salience value;
determining a second salience value for a second character of the list of characters, wherein the second character is depicted in a second video of the set of videos, and wherein the second salience value is a salience of the second character relative to other characters associated with the second video;
determining a second attribute-level value for the second video based at least on the second salience value;
computing an index of videos based at least on (i) the first attribute-level value as determined based at least on the first salience value, and (ii) the second attribute-level value;
indexing first video and the second video by the index of videos; and
storing the index of videos in a database;
retrieving information for at least one video of the set of videos using the index of videos; and
generating, for a display device, a display of at least one of the at least one video or the retrieved information for the at least one video, selected based on the index of videos, wherein generating the display comprises recommending, base at least on the first salience value, the at least one video.