Content carousel in a social media timeline
Techniques of the disclosure are directed to a computing device creating and outputting, for display at client devices accessing a social media platform, targeted content. The computing device may receive candidate messages composed by users of a group of client devices, where the candidate messages each include a reference to the requisite product, brand, or market. If a candidate message has a determined interest score that satisfies a threshold interest score, the computing device includes the candidate message into a group of brand messages. The computing device may then send the targeted message to be output for display at another group of client devices, where the targeted message includes both an original portion and a carousel portion. The carousel portion includes a group of transitional windows, where each transitional window includes one of the brand messages from the group of brand messages.
1. A method, comprising:
receiving, at a compute device, a plurality of candidate messages associated with a promoted entity;
selecting, by the compute device, a first candidate message from the set of candidate based on an interest score associated with the first candidate messages, the interest score indicating a likelihood of a user interacting with the first candidate message, further comprising calculating, using a machine learning model, the interest score associated with the first candidate message; and
forming, by the compute device, a set of target messages including the first candidate message, wherein each target message in the set of target messages includes a reference to the promoted entity;
generating, by the compute device, for display in a vertical stream of a set of cards on a user device, a target card, the target card including a carousel portion having a set of transitional windows, such that during display on the user device:
each transitional window in the set of transitional windows includes a different target message of the set of target messages;
only one transitional window of the set of transitional windows is fully rendered at a time on the display of the user device; and
the set of transitional windows is displayed in a cyclical manner such that each transitional window of the set of transitional windows horizontally transitions to a next transitional window of the set of transitional windows;
transmitting, by the compute device to the user device for display, the target card;
receiving an indication of user interaction with the transitional window of the set of transitional windows including the first candidate message; and
updating the machine learning model based on the indication of user interaction.
2. The method of claim 1 , wherein the set of transitional windows is a set of sequential transition windows, and wherein the horizontal transition from a last horizontal window of the set of sequential transition windows to the next transition window is a horizontal transition to a first transition window of the set of sequential transition windows.
3. The method of claim 1 , wherein the set of transitional windows is a set of sequential transition windows, and wherein the horizontal transition from a first horizontal window of the set of sequential transition windows to the next transition window is a horizontal transition to a last transition window of the set of sequential transition windows.
4. The method of claim 1 , wherein the horizontal transition is responsive to user input.
5. The method of claim 1 , wherein the horizontal transition occurs automatically after a predetermined amount of time.
6. The method of claim 1 , wherein the target card includes a static portion that is unchanged during the horizontal transition.
7. The method of claim 1 , wherein at least one transitional window of the set of transitional windows includes time-lapse media, and wherein the time-lapse media is automatically played upon full rendering of that transitional window.
8. The method of claim 1 , wherein at least one target message of the set of target messages includes video.
9. The method of claim 1 , wherein a first target message and a second target message of the set of target messages each independently include one or more of text, an image, video, audio, or combinations thereof.
10. A non-transitory computer-readable storage medium storing instructions, the instructions when executed cause at least one processor to:
receive a plurality of candidate messages associated with a promoted entity;
select a first candidate message from the set of candidate based on an interest score associated with the first candidate messages, the interest score indicating a likelihood of a user interacting with the first candidate message, wherein the instructions further include instructions for calculating, using a machine learning model, the interest score associated with the first candidate message; and
form a set of target messages including the first candidate message, wherein each target message in the set of target messages includes a reference to the promoted entity;
generate, for display in a vertical stream of a set of cards on a user device, a target card, the target card including a carousel portion having a set of transitional windows, such that during display on the user device:
each transitional window in the set of transitional windows includes a different target message of the set of target messages;
only one transitional window of the set of transitional windows is fully rendered at a time on the display of the user device; and
the set of transitional windows is displayed in a cyclical manner such that each transitional window of the set of transitional windows horizontally transitions to a next transitional window of the set of transitional windows;
transmit, to the user device for display, the target card; and
receive an indication of user interaction with the transitional window of the set of transitional windows including the first candidate message; and
update the machine learning model based on the indication of user interaction.
11. The non-transitory computer-readable storage medium of claim 10 , wherein the target card includes a static portion that is unchanged during the horizontal transition.
12. The non-transitory computer-readable storage medium of claim 10 , wherein at least one transitional window of the set of transitional windows includes time-lapse media, and wherein the time-lapse media is automatically played upon full rendering of that transitional window.
13. The non-transitory computer-readable storage medium of claim 10 , wherein at least one target message of the set of target messages includes video.
14. The non-transitory computer-readable storage medium of claim 10 , wherein a first target message and a second target message of the set of target messages each independently include one or more of text, an image, video, audio, or combinations thereof.
15. A compute device, comprising:
at least one processor; and
at least one non-transitory computer-readable storage medium storing instructions that are executable by the at least one processor to:
receive a plurality of candidate messages associated with a promoted entity;
select a first candidate message from the set of candidate based on an interest score associated with the first candidate messages, the interest score indicating a likelihood of a user interacting with the first candidate message, wherein the instructions further include instructions for calculating, using a machine learning model, the interest score associated with the first candidate message; and
form a set of target messages including the first candidate message, wherein each target message in the set of target messages includes a reference to the promoted entity;
generate, for display in a vertical stream of a set of cards on a user device, a target card, the target card including a carousel portion having a set of transitional windows, such that during display on the user device:
each transitional window in the set of transitional windows includes a different target message of the set of target messages;
only one transitional window of the set of transitional windows is fully rendered at a time on the display of the user device; and
the set of transitional windows is displayed in a cyclical manner such that each transitional window of the set of transitional windows horizontally transitions to a next transitional window of the set of transitional windows;
transmit, to the user device for display, the target card;
receive an indication of user interaction with the transitional window of the set of transitional windows including the first candidate message; and
update the machine learning model based on the indication of user interaction.
16. The compute device of claim 15 , wherein the set of transitional windows is a set of sequential transition windows, and wherein the horizontal transition from a last horizontal window of the set of sequential transition windows to the next transition window is a horizontal transition to a first transition window of the set of sequential transition windows.
17. The compute device of claim 15 , wherein the set of transitional windows is a set of sequential transition windows, and wherein the horizontal transition from a first horizontal window of the set of sequential transition windows to the next transition window is a horizontal transition to a last transition window of the set of sequential transition windows.
18. The compute device of claim 15 , wherein the horizontal transition is responsive to user input.
19. The compute device of claim 15 , wherein the horizontal transition occurs automatically after a predetermined amount of time.
20. The compute device of claim 15 , wherein the target card includes a static portion that is unchanged during the horizontal transition.
21. The compute device of claim 15 , wherein at least one transitional window of the set of transitional windows includes time-lapse media, and wherein the time-lapse media is automatically played upon full rendering of that transitional window.
22. The compute device of claim 21 , wherein the time-lapse media includes video.
23. The compute device of claim 15 , wherein at least one target message of the set of target messages includes video.
24. The compute device of claim 15 , wherein a first target message and a second target message of the set of target messages each independently include one or more of text, an image, video, audio, or combinations thereof.