System and methods for analyzing content engagement in conjunction with social media
Various embodiments disclose a system and methods for media content analysis based at least in part upon social media data. In some embodiments, a computer system may determine a viewership associated with a selected piece of televised content such as a television show or advertisement. The computer system may also identify social media data such as social media messages associated with the selected piece of televised content. The computer system may calculate an audience engagement measurement corresponding to the selected piece of televised content based upon the social media data and the viewership.
1. A method, implemented by a computing system, for generating an audience engagement measurement, the method comprising:
receiving at least one analysis parameter, the at least one analysis parameter comprising at least one of: a televised content selection parameter and a demographic selection parameter;
selecting a piece of televised content based on the at least one analysis parameter;
accessing televised content data associated with the selected piece of televised content;
accessing, from a first source, television viewing data of viewing entities;
accessing, from a second source different from the first source, social media data generated by users of social media services;
determining, by the computing system, viewership criteria based upon the televised content data and the at least one analysis parameter;
determining, by the computing system, a viewership associated with the selected piece of televised content based upon the viewership criteria, the determined viewership indicating a number of users that viewed the selected piece of televised content;
determining, by the computing system, a subset of the social media data associated with the selected piece of televised content by filtering the social media data using social media matching criteria, the filtering comprising:
comparing each of social media messages of the social media data with at least one of the social media matching criteria, the social media matching criteria determined based on the televised content data,
determining a confidence score of a match between each of the social media messages and the at least one social media matching criteria, and
discarding social media messages associated with confidence scores below a predefined threshold; and
generating, by the computing system, the audience engagement measurement corresponding to the selected piece of televised content based upon the subset of social media data and the determined viewership.
2. The method of claim 1 , wherein the televised content selection parameter comprises one of: a name of a televised program; a television network; and a time of a television broadcast.
3. The method of claim 1 , wherein the demographic selection parameter comprises one of: an age range; a geographic location; and a household income range.
4. The method of claim 1 , wherein generating the audience engagement measurement corresponding to the selected piece of televised content comprises dividing a number of social media messages in the subset of the social media data associated with the selected piece of televised content by the number of users that viewed the selected piece of televised content.
5. The method of claim 1 , wherein the social media matching criteria comprise at least one of: a geographic location, a time, and a keyword; and wherein the social media messages comprise a user-generated narrative.
6. The method of claim 5 , wherein the social media matching criteria further comprises a time range outside which social media messages are excluded.
7. The method of claim 5 , wherein the social media matching criteria further comprises a plurality of weighted keywords corresponding to the selected piece of televised content.
8. The method of claim 1 , wherein filtering the social media data further comprises weighing each of the social media messages based on the confidence score associated with each of the social media messages.
9. The method of claim 1 , wherein the television viewing data comprises data from at least one of: a digital broadcast satellite service provider, a cable television provider, and an Internet service provider.
10. The method of claim 1 , wherein the television viewing data comprises tuning data of television viewing devices,
wherein the viewership criteria comprises at least one of: a length of time a television viewing device is tuned to the selected piece of televised content, and an amount of time during which a time-shifted viewing occurs.
11. The method of claim 1 , further comprising calculating a correlation between television rating data associated with the selected piece of televised content and information associated with the subset of social media data.
12. A non-transitory computer-readable medium comprising instructions executable by at least one processor to perform a method for generating an audience engagement measurement, the method comprising:
receiving at least one analysis parameter, the at least one analysis parameter comprising at least one of: a televised content selection parameter and a demographic selection parameter;
selecting a piece of televised content based on the at least one analysis parameter;
accessing televised content data associated with the selected piece of televised content;
accessing, from a first source, television viewing data of viewing entities;
accessing, from a second source different from the first source, social media data generated by users of social media services;
determining viewership criteria based upon the televised content data and the at least one analysis parameter;
determining a viewership associated with the selected piece of televised content based upon the viewership criteria, the determined viewership indicating a number of users that viewed the selected piece of televised content;
determining a subset of the social media data associated with the selected piece of televised content by filtering the social media data using social media matching criteria, the filtering comprising:
comparing each of social media messages of the social media data with at least one of the social media matching criteria, the social media matching criteria determined based on the televised content data,
determining a confidence score of a match between each of the social media messages and the at least one social media matching criteria, and
discarding social media messages associated with confidence scores below a predefined threshold; and
generating the audience engagement measurement corresponding to the selected piece of televised content based upon the subset of social media data and the determined viewership.
13. The non-transitory computer-readable medium of claim 12 , wherein the social media matching criteria comprise at least one of: a geographic location, a time, and a keyword; and wherein the social media messages comprise a user-generated narrative.
14. The non-transitory computer-readable medium of claim 12 , wherein filtering the social media data further comprises weighing each of the social media messages based on the confidence score associated with each of the social media messages.
15. A computer system for generating an audience engagement measurement, the computer system comprising:
at least one processor;
at least one memory comprising instructions configured to be executed by the at least one processor to perform a method comprising:
receiving at least one analysis parameter, the at least one analysis parameter comprising at least one of: a televised content selection parameter and a demographic selection parameter;
selecting a piece of televised content based on the at least one analysis parameter;
accessing televised content data associated with the selected piece of televised content;
accessing, from a first source, television viewing data of viewing entities;
accessing, from a second source different from the first source, social media data generated by users of social media services;
determining viewership criteria based upon the televised content data and the at least one analysis parameter;
determining a viewership associated with the selected piece of televised content based upon the viewership criteria, the determined viewership indicating a number of users that viewed the selected piece of televised content;
determining a subset of the social media data associated with the selected piece of televised content by filtering the social media data using social media matching criteria, the filtering comprising:
comparing each of social media messages of the social media data with at least one of the social media matching criteria, the social media matching criteria determined based on the televised content data,
determining a confidence score of a match between each of the social media messages and the at least one social media matching criteria, and
discarding social media messages associated with confidence scores below a predefined threshold; and
generating the audience engagement measurement corresponding to the selected piece of televised content based upon the subset of social media data and the determined viewership.
16. The computer system of claim 15 , wherein the social media matching criteria comprise at least one of: a geographic location, a time, and a keyword; and wherein the social media messages comprise a user-generated narrative.
17. The computer system of claim 15 , wherein filtering the social media data further comprises weighing each of the social media messages based on the confidence score associated with each of the social media messages.