SYSTEMS AND METHODS FOR PROVIDING EPHEMERAL CONTENT ITEMS CREATED FROM LIVE STREAM VIDEOS
Systems, methods, and non-transitory computer readable media can generate an ephemeral content item from a live stream video that has concluded, wherein the ephemeral content item from the live stream video is included in an ephemeral content item collection. A plurality of ephemeral content item collections, including the ephemeral content item collection, can be ranked based on a machine learning model. At least one of the ranked plurality of ephemeral content item collections is provided in an ephemeral content feed of a user.
1 . A computer-implemented method comprising:
generating, by the computing system, an ephemeral content item from a live stream video that has concluded, wherein the ephemeral content item from the live stream video is included in an ephemeral content item collection;
ranking, by the computing system, a plurality of ephemeral content item collections, including the ephemeral content item collection, based on a machine learning model; and
providing, by the computing system, at least one of the ranked plurality of ephemeral content item collections in an ephemeral content feed of a user.
2 . The computer-implemented method of claim 1 , wherein the generating an ephemeral content item from the live stream video includes dividing the live stream video into a plurality of chunks.
3 . The computer-implemented method of claim 1 , wherein each of the plurality of ephemeral content item collections is associated with a type of ephemeral content item collection, wherein the type of ephemeral content item collection is selected from one or more of: a post-live ephemeral content item collection or a non-post-live ephemeral content item collection.
4 . The computer-implemented method of claim 3 , wherein the machine learning model is trained based on features relating to one or more of: ephemeral content item collection attributes, ephemeral content item attributes, or user attributes.
5 . The computer-implemented method of claim 4 , wherein the ephemeral content item collection attributes include one or more of: the type of ephemeral content item collection, an amount of time a user spent on an ephemeral content item collection, an aggregate or average amount of time a user spent on ephemeral content item collections, or a number of skips associated with an ephemeral content item collection.
6 . The computer-implemented method of claim 4 , wherein the ephemeral content item attributes include one or more of: a type of ephemeral content item, an amount of time a user spent on an ephemeral content item, an aggregate or average amount of time a user spent on ephemeral content items, or a number of skips associated with an ephemeral content item.
7 . The computer-implemented method of claim 1 , wherein each of the plurality of ephemeral content item collections includes one or more ephemeral content items, wherein each ephemeral content item is associated with a type of ephemeral content item, wherein the type of ephemeral content item is selected from one or more of: a post-live ephemeral content item or a non-post-live ephemeral content item.
8 . The computer-implemented method of claim 1 , wherein the machine learning model is trained to predict a likelihood of a user engaging with an ephemeral content item collection.
9 . The computer-implemented method of claim 1 , wherein a total number of views associated with the live stream video includes a number of views of the ephemeral content item generated from the live stream video.
10 . The computer-implemented method of claim 1 , wherein feedback associated with the live stream video is presented during playback of the ephemeral content item generated from the live stream video.
11 . A system comprising:
at least one hardware processor; and
a memory storing instructions that, when executed by the at least one processor, cause the system to perform:
generating an ephemeral content item from a live stream video that has concluded, wherein the ephemeral content item from the live stream video is included in an ephemeral content item collection;
ranking a plurality of ephemeral content item collections, including the ephemeral content item collection, based on a machine learning model; and
providing at least one of the ranked plurality of ephemeral content item collections in an ephemeral content feed of a user.
12 . The system of claim 11 , wherein each of the plurality of ephemeral content item collections is associated with a type of ephemeral content item collection, wherein the type of ephemeral content item collection is selected from one or more of: a post-live ephemeral content item collection or a non-post-live ephemeral content item collection.
13 . The system of claim 12 , wherein the machine learning model is trained based on features relating to one or more of: ephemeral content item collection attributes, ephemeral content item attributes, or user attributes.
14 . The system of claim 13 , wherein the ephemeral content item collection attributes include one or more of: the type of ephemeral content item collection, an amount of time a user spent on an ephemeral content item collection, an aggregate or average amount of time a user spent on ephemeral content item collections, or a number of skips associated with an ephemeral content item collection.
15 . The system of claim 13 , wherein the ephemeral content item attributes include one or more of: a type of ephemeral content item, an amount of time a user spent on an ephemeral content item, an aggregate or average amount of time a user spent on ephemeral content items, or a number of skips associated with an ephemeral content item.
16 . A non-transitory computer readable medium including instructions that, when executed by at least one hardware processor of a computing system, cause the computing system to perform a method comprising:
generating an ephemeral content item from a live stream video that has concluded, wherein the ephemeral content item from the live stream video is included in an ephemeral content item collection;
ranking a plurality of ephemeral content item collections, including the ephemeral content item collection, based on a machine learning model; and
providing at least one of the ranked plurality of ephemeral content item collections in an ephemeral content feed of a user.
17 . The non-transitory computer readable medium of claim 16 , wherein each of the plurality of ephemeral content item collections is associated with a type of ephemeral content item collection, wherein the type of ephemeral content item collection is selected from one or more of: a post-live ephemeral content item collection or a non-post-live ephemeral content item collection.
18 . The non-transitory computer readable medium of claim 17 , wherein the machine learning model is trained based on features relating to one or more of: ephemeral content item collection attributes, ephemeral content item attributes, or user attributes.
19 . The non-transitory computer readable medium of claim 18 , wherein the ephemeral content item collection attributes include one or more of: the type of ephemeral content item collection, an amount of time a user spent on an ephemeral content item collection, an aggregate or average amount of time a user spent on ephemeral content item collections, or a number of skips associated with an ephemeral content item collection.
20 . The non-transitory computer readable medium of claim 18 , wherein the ephemeral content item attributes include one or more of: a type of ephemeral content item, an amount of time a user spent on an ephemeral content item, an aggregate or average amount of time a user spent on ephemeral content items, or a number of skips associated with an ephemeral content item.