Estimating social interest in time-based media
Social media content items are mapped to relevant time-based media events. These mappings may be used as the basis for multiple applications, such as ranking of search results for time-based media, automatic recommendations for time-based media, prediction of audience interest for media purchasing/planning, and estimating social interest in the time-based media. Social interest in time-based media (e.g., video and audio streams and recordings) segments is estimated through a process of data ingestion and integration. The estimation process determines social interest in specific events represented as segments in time-based media, such as particular plays in a sporting event, scenes in a television show, or advertisements in an advertising block. The resulting estimates of social interest also can be graphically displayed.
1. A computer-executed method for identifying content associated with time-based media events, the method comprising:
determining that a plurality of content items authored by users of a social networking system are correlated with a broadcast media event, wherein each content item in the plurality of content items is determined to be correlated to the media event based on a confidence score of the content item, the confidence score indicating a probability that the content item is relevant to the media event;
generating a social media graphical user interface (GUI) element associated with the media event that visually depicts the plurality of content items;
computing audience interest metrics based at least on the plurality of content items, wherein each audience interest metric measures a response of the users of the social networking system to the media event at a respective different point in time during the broadcast of the media event;
generating a metrics GUI element that includes a set of indicators, each indicator being associated with a different point in time during the broadcast of the media event and visually depicting the audience interest metric computed for the associated point in time; and
transmitting the metrics GUI element and the social media GUI element for display.
2. The method of claim 1 , wherein a first indicator in the set of indicators comprises a vertical bar having a height corresponding to the audience interest metric computed for a portion of the media event associated with the first indicator.
3. The method of claim 1 , wherein a first indicator in the set of indicators comprises a color corresponding to an intensity level of the audience interest metric computed for a portion of the media event associated with the first indicator.
4. The method of claim 1 , wherein a first indicator in the set of indicators comprises a visual pattern corresponding to an intensity level of the audience interest metric computed for a portion of the media event associated with the first indicator.
5. The method of claim 1 , wherein a first indicator in the set of indicators comprises a first section corresponding to a number of content items with a positive sentiment toward a portion of the media event associated with the first indicator and also comprises a second section corresponding to a number of content items with a negative sentiment toward the portion of the media event associated with the first indicator.
6. The method of claim 1 , further comprising:
receiving a search parameter specifying a first portion of the media event; and
updating the metrics GUI element to only include one or more indicators associated with the first portion of the media event.
7. The method of claim 1 , wherein the plurality of content items visually depicted in the social media GUI element are correlated with a portion of the media event that was aired most recently.
8. The computer-executed method of claim 1 , wherein the plurality of content items depicted in the social media GUI element are chronologically sorted.
9. The method of claim 1 , wherein the confidence score is determined based on an amount of co-occurring information within the media event and the content item, wherein more co-occurring information results in a higher confidence score.
10. The method of claim 1 , wherein the confidence score is determined based on a difference between (i) a time at which the media event was broadcasted and (ii) a time at which the content item was authored, wherein a lower difference results in a higher confidence score.
11. The method of claim 1 , wherein the media event is associated with an event type, and the confidence score of the content item is determined based on a probability that an author of the content item would post about the event type in the social network.
12. A non-transitory computer readable storage medium for identifying content associated with time-based media events, the computer readable storage medium storing instructions that, when executed by a processor, cause the processor to:
determine that a plurality of content items authored by users of a social networking system are correlated with a broadcast media event, wherein each content item in the plurality of content items is determined to be correlated to the media event based on a confidence score of the content item, the confidence score indicating a probability that the content item is relevant to the media event;
generate a social media graphical user interface (GUI) element associated with the media event that visually depicts the plurality of content items;
compute audience interest metrics based at least on the plurality of content items, wherein each audience interest metric measures a response of the users of the social networking system to the media event at a respective different point in time during the broadcast of the media event;
generate a metrics GUI element that includes a set of indicators, each indicator associated being with a different point in time during the broadcast of the media event and visually depicting the audience interest metric computed for the associated point in time; and
transmit the metrics GUI element and the social media GUI element for display.
13. The computer readable storage medium of claim 12 , wherein a first indicator in the set of indicators comprises a vertical bar having a height corresponding to the audience interest metric computed for a portion of the media event associated with the first indicator.
14. The computer readable storage medium of claim 12 , wherein a first indicator in the set of indicators comprises a color corresponding to an intensity level of the audience interest metric computed for a portion of the media event associated with the first indicator.
15. The computer readable storage medium of claim 12 , wherein a first indicator in the set of indicators comprises a visual pattern corresponding to an intensity level of the audience interest metric computed for a portion of the media event associated with the first indicator.
16. The computer readable storage medium of claim 12 , wherein a first indicator in the set of indicators comprises a first section corresponding to a number of content items with a positive sentiment toward a portion of the media event associated with the first indicator and also comprises a second section corresponding to a number of content items with a negative sentiment toward the portion of the media event associated with the first indicator.
17. The computer readable storage medium of claim 12 , wherein the instructions, when executed by the processor, cause the processor to:
receive a search parameter specifying a first portion of the media event; and
update the metrics GUI element to only include one or more indicators associated with the first portion of the media event.
18. The computer readable storage medium of claim 12 , wherein the plurality of content items visually depicted in the social media GUI element are correlated with a portion of the media event that was aired most recently.
19. The computer readable storage medium of claim 12 , wherein the confidence score of the content item is determined based on one or more content features, geo-temporal features, or authority features of the content item compared to respective features of the media event.
20. A system comprising:
a computer processor; and
a memory storing instructions that, when executed by the processor, cause the processor to:
determine that a plurality of content items authored by users of a social networking system are correlated with a broadcast media event, wherein each content item in the plurality of content items is determined to be correlated to the media event based on a confidence score of the content item, the confidence score indicating a probability that the content item is relevant to the media event,
generate a social media graphical user interface (GUI) element associated with the media event that visually depicts the plurality of content items,
compute audience interest metrics based at least on the plurality of content items, wherein each audience interest metric measures a response of the users of the social networking system to the media event at a respective different point in time during the broadcast of the media event,
generate a metrics GUI element that includes a set of indicators, each indicator associated being with a different point in time during the broadcast of the media event and visually depicting the audience interest metric computed for the associated point in time, and
transmit the metrics GUI element and the social media GUI element for display.