Methods and systems for selecting and presenting content based on dynamically identifying microgenres associated with the content
A method of selecting and presenting content based on learned user preferences is provided. The method includes providing a content System including a set of content items organized by genre characterizing the content items, and wherein the set of content items contains microgenre metadata further characterizing the content items. The method also includes receiving search input from the user for identifying desired content items and, in response, presenting a subset of content items to the user. The method further includes receiving content item selection actions from the user and analyzing the microgenre metadata within the selected content items to learn the preferred microgenres of the user. The method includes, in response to receiving subsequent user search input, selecting and presenting content items in an order that portrays as relatively more relevant those content items containing microgenre metadata that more closely match the learned microgenre preferences of the user.
1. A computer-implemented method comprising:
receiving, at a server and from a client device, a user interface interaction with a particular content item of a plurality of content items, wherein each content item of a subset of the plurality of content items is associated with:
a respective macro-theme that broadly characterizes the respective content item,
a respective micro-theme that, with respect to the respective macro-theme, narrowly characterizes the respective content item, and
a respective relevance value that indicates how relevant the respective content item is to a user profile;
identifying, based on the user profile, at least one content item of the subset of the plurality of content items, wherein a micro-theme associated with the at least one identified content item comprises the micro-theme of the particular content item;
increasing a relevance value associated with the at least one identified content item of the subset, based on the user interface interaction;
ranking the plurality of content items in an order based at least in part on the respective relevance value associated with each content item of the subset of content items; and
generating for display the plurality of content items based on the ranking.
2. The method of claim 1 , wherein ranking the plurality of content items is further based at least in part on criteria other than the respective relevance values of the subset of the plurality of content items.
3. The method of claim 1 , wherein ranking the plurality of content items is further based at least in part on at least one of date, day, or time.
4. The method of claim 1 , wherein ranking the plurality of content items is further performed based at least in part on user interface interactions with other user profiles.
5. The method of claim 1 , wherein ranking the plurality of content items is further performed based at least in part on historical data indicating content items the user profile previously interacted with via an application.
6. The method of claim 1 , wherein ranking the plurality of content items is further performed based at least in part on a stochastic signature comprising statistical values associated with a plurality of micro-themes, and wherein at least one micro-theme of the plurality of micro-themes is associated with a statistical value indicating its relevance to the user profile.
7. The method of claim 1 , wherein a trained model is used to:
identify the micro-theme of the particular content item associated with the user interface interaction;
perform the identifying of the at least one content item of the subset of the plurality of content items; and
perform the ranking of the plurality of content items.
8. The method of claim 1 , wherein the order comprises the plurality of content items sorted based at least in part on a descending order of relevance, wherein a content item having a higher relevance value has a greater probability of being positioned at a top portion of a display or other prominent portion of the display.
9. The method of claim 1 , wherein:
the user interface interaction is further associated with a first context comprising at least one of a geographic location, client device identifier, date, day, or time associated with the user interface interaction, and the increasing further comprises:
comparing the first context with a second context associated with at least one content item of the plurality of content items;
determining, based on the comparing, that the second context associated with the at least one content item comprises an attribute of the first context; and
increasing the relevance value associated with the at least one content item.
10. The method of claim 1 , wherein at least one content item of the plurality of content items comprises at least one of an audio item, a video item, a web content item, an advertisement, or any combination thereof.
11. A computer-implemented system, comprising:
a database for storing metadata for a plurality of content items;
a server comprising processing circuitry configured to:
receive, at a server and from a client device, a user interface interaction with a particular content item of a plurality of content items, wherein each content item of a subset of the plurality of content items is associated with:
a respective macro-theme that broadly characterizes the respective content item,
a respective micro-theme that, with respect to the respective macro-theme, narrowly characterizes the respective content item, and
a respective relevance value that indicates how relevant the respective content item is to a user profile;
identify, based on the user profile, at least one content item of the subset of the plurality of content items, wherein a micro-theme associated with the at least one identified content item comprises the micro-theme of the particular content item;
increase a relevance value associated with the at least one identified content item of the subset, based on the user interface interaction;
rank the plurality of content items in an order based at least in part on the respective relevance value associated with each content item of the subset of content items; and
generate for display the plurality of content items based on the ranking.
12. The system of claim 11 , wherein the processing circuitry is configured to rank the plurality of content items further based at least in part on criteria other than the respective relevance values of the subset of the plurality of content items.
13. The system of claim 11 , wherein the processing circuitry is configured to rank the plurality of content items further based at least in part on at least one of date, day, or time.
14. The system of claim 11 , wherein the processing circuitry is configured to rank the plurality of content items based at least in part on user interface interactions with other user profiles.
15. The system of claim 11 , wherein the processing circuitry is configured to rank the plurality of content items further based at least in part on historical data indicating content items the user profile previously interacted with via an application.
16. The system of claim 11 , wherein the processing circuitry is configured to rank the plurality of content items further based at least in part on a stochastic signature comprising statistical values associated with a plurality of micro-themes, and wherein at least one micro-theme of the plurality of micro-themes is associated with a statistical value indicating its relevance to the user profile.
17. The system of claim 11 , wherein the processing circuitry is configured to use a trained model to:
identify the micro-theme of the particular content item associated with the user interface interaction;
perform the identifying of the at least one content item of the subset of the plurality of content items; and
perform the ranking of the plurality of content items.
18. The system of claim 11 , wherein the order comprises the plurality of content items sorted based at least in part on a descending order of relevance, wherein a content item having a higher relevance value has a greater probability of being positioned at a top portion of a display or other prominent portion of the display.
19. The system of claim 11 , wherein:
the user interface interaction is further associated with a first context comprising at least one of a geographic location, client device identifier, date, day, or time associated with the user interface interaction, and the processing circuitry is configured to perform the increasing by:
comparing the first context with a second context associated with at least one content item of the plurality of content items;
determining, based on the comparing, that the second context associated with the at least one content item comprises an attribute of the first context; and
increasing the relevance value associated with the at least one content item.
20. The system of claim 11 , wherein at least one content item of the plurality of content items comprises at least one of an audio item, a video item, a web content item, an advertisement, or any combination thereof.
21. One or more non-transitory computer-readable media storing instructions which, when executed by one or more processors, cause performance of:
receiving, at a server and from a client device, a user interface interaction with a particular content item of a plurality of content items, wherein each content item of a subset of the plurality of content items is associated with:
a respective macro-theme that broadly characterizes the respective content item,
a respective micro-theme that, with respect to the respective macro-theme, narrowly characterizes the respective content item, and
a respective relevance value that indicates how relevant the respective content item is to a user profile;
identifying, based on the user profile, at least one content item of the subset of the plurality of content items, wherein a micro-theme associated with the at least one identified content item comprises the micro-theme of the particular content item;
increasing a relevance value associated with the at least one identified content item of the subset, based on the user interface interaction;
ranking the plurality of content items in an order based at least in part on the respective relevance value associated with each content item of the subset of content items; and
generating for display the plurality of content items based on the ranking.
22. The one or more non-transitory computer-readable media of claim 21 , wherein ranking the plurality of content items is further based at least in part on criteria other than the respective relevance values of the subset of the plurality of content items.
23. The one or more non-transitory computer-readable media of claim 21 , wherein ranking the plurality of content items is further based at least in part on at least one of date, day, or time.
24. The one or more non-transitory computer-readable media of claim 21 , wherein ranking the plurality of content items is further performed based at least in part on user interface interactions with other user profiles.
25. The one or more non-transitory computer-readable media of claim 21 , wherein ranking the plurality of content items is further performed based at least in part on historical data indicating content items the user profile previously interacted with via an application.
26. The one or more non-transitory computer-readable media of claim 21 , wherein ranking the plurality of content items is further performed based at least in part on a stochastic signature comprising statistical values associated with a plurality of micro-themes, and wherein at least one micro-theme of the plurality of micro-themes is associated with a statistical value indicating its relevance to the user profile.
27. The one or more non-transitory computer-readable media of claim 21 , wherein a trained model is used to:
identify the micro-theme of the particular content item associated with the user interface interaction;
perform the identifying of the at least one content item of the subset of the plurality of content items; and
perform the ranking of the plurality of content items.
28. The one or more non-transitory computer-readable media of claim 21 , wherein the order comprises the plurality of content items sorted based at least in part on a descending order of relevance, wherein a content item having a higher relevance value has a greater probability of being positioned at a top portion of a display or other prominent portion of the display.
29. The one or more non-transitory computer-readable media of claim 21 , wherein:
the user interface interaction is further associated with a first context comprising at least one of a geographic location, client device identifier, date, day, or time associated with the user interface interaction, and the increasing further comprises:
comparing the first context with a second context associated with at least one content item of the plurality of content items;
determining, based on the comparing, that the second context associated with the at least one content item comprises an attribute of the first context; and
increasing the relevance value associated with the at least one content item.
30. The one or more non-transitory computer-readable media of claim 21 , wherein at least one content item of the plurality of content items comprises at least one of an audio item, a video item, a web content item, an advertisement, or any combination thereof.