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, by a computing device and from an information distribution system, a first group of one or more messages composed by one or more users of a first group of one or more client devices accessing a social media platform, wherein each of the messages in the first group of one or more messages includes a reference to a particular brand;
determining, by the computing device, using a machine learning model, an interest score for a candidate message based at least in part on content of the candidate message, wherein the candidate message is included in the first group of one or more messages;
responsive to determining that the interest score satisfies a threshold interest score, inserting, by the computing device, the candidate message into a group of one or more brand messages, wherein each brand message in the group of one or more brand messages includes a reference to the particular brand; and
sending, by the computing device and to the information distribution system, a targeted message to be output for display at a second group of one or more client devices, wherein the targeted message comprises an original portion and a carousel portion, wherein the carousel portion comprises a group of two or more transitional windows, wherein each transitional window in the group of two or more transitional windows includes one of the brand messages in the group of one or more brand messages, and wherein the original portion comprises content formed at the computing device,
the method further comprising:
initially receiving, by the computing device, an indication of user input from a particular client device of the second group of one or more client devices that indicates a selection of a trend, wherein the trend is related to the particular brand, and wherein each of the messages in the first group of one or more messages includes content associated with the trend; and
constructing, by the computing device, the carousel portion of the targeted message by:
placing a distinct graphical element that contains a respective brand message of the group of one or more brand messages and information identifying a user who composed the respective brand message into a respective transitional window of the group of two or more transitional windows,
forming an additional transitional window that includes the original portion of the targeted message, and
adding the additional transitional window to the group of one or more transitional windows to form an expanded group of three or more transitional windows; and
sending, by the computing device and to the information distribution system, the targeted message to be output for display at the particular client device of the second group of one or more client devices, wherein the targeted message is displayed such that only a single transitional window of the expanded group of three or more transitional windows is fully displayed at a given time, such that the particular client device of the second group of one or more client devices is configured to individually and cyclically display each transitional window in the expanded group of three or more transitional windows during a period of time, and such that a transition between the transitional windows of the expanded group of three or more transitional windows is a horizontal transition.
2. The method of claim 1 , wherein a brand message in the group of two or more brand messages includes media comprising one of audio, a video, a picture, or an animated image file, and wherein the media is automatically played upon display of the respective transitional window of the group of two or more transitional windows that contains the brand message.
3. The method of claim 1 , further comprising:
determining, by the computing device, secondary information for the candidate message, wherein the secondary information comprises one or more of:
an author of the candidate message,
a number of subscribers to a social media account of the author of the candidate message,
a probability that a user of a client device of the second group of one or more client devices will engage with the candidate message,
an interaction history between the user of the client device of the second group of one or more client devices and the author of the candidate message,
a time that the candidate message was authored,
a geolocation of a client device of the first group of one or more client devices used by the author of the candidate message to post the candidate message, or
a topic of the candidate message; and
determining, by the computing device based at least in part on the content of the candidate message and the secondary information for the candidate message, using the machine learning model, the interest score.
4. The method of claim 1 , further comprising:
receiving, by the computing device and from the information distribution system, an indication that a user of a client device of the second group of one or more client devices engaged with the targeted message, wherein engaging with the targeted message comprises one of viewing the targeted message, disseminating the targeted message to one or more subscribers of a social media account associated with the user, or interacting with one or more hyperlinks included in the targeted message; and
updating, by the computing device, the machine learning model to indicate that the user of the client device of the second group of client devices engaged with the targeted message.
5. The method of claim 4 , further comprising:
responsive to receiving the indication that the user of the client device of the second group of one or more client devices engaged with the targeted message, receiving, by an account associated with the computing device, a credit from an account associated with the information distribution system.
6. The method of claim 1 , wherein determining the interest score comprises:
determining, by the computing device, a strength of a relation between the content of the candidate message and a particular product belonging to the particular brand; and
determining, by the computing device and based at least in part on the strength of the relation between the content of the candidate message and the particular product belonging to the particular brand, the interest score.
7. The method of claim 1 , further comprising:
cycling, by a client device of the second group of one or more client devices, the carousel portion automatically after a predetermined amount of time such that a different transitional window of the expanded group of three or more transitional windows is shown in a graphical user interface at the client device.
8. The method of claim 1 , further comprising:
cycling, by a client device of the second group of one or more client devices, the carousel portion responsive to receiving an indication of user input at the client device such that a different transitional window of the expanded group of three or more transitional windows is shown in a graphical user interface at the client device.
9. A non-transitory computer-readable storage medium storing instructions that, when executed, cause at least one processor to:
receive, from an information distribution system, a first group of one or more messages composed by one or more users of a first group of one or more client devices accessing a social media platform, wherein each of the messages in the first group of one or more messages includes a reference to a particular brand;
determine, using a machine learning model, an interest score for a candidate message based at least in part on content of the candidate message, wherein the candidate message is included in the first group of one or more messages;
responsive to determining that the interest score satisfies a threshold interest score, insert the candidate message into a group of one or more brand messages, wherein each brand message in the group of one or more brand messages includes a reference to the particular brand; and
send, to the information distribution system, a targeted message to be output for display at a second group of one or more client devices, wherein the targeted message comprises an original portion and a carousel portion, wherein the carousel portion comprises a group of two or more transitional windows, wherein each transitional window in the group of two or more transitional windows includes one of the brand messages in the group of one or more brand messages, and wherein the original portion comprises content formed at the computing device,
the non-transitory computer-readable storage medium further comprising instructions that, when executed, cause the at least one processor to:
initially receive an indication of user input from a particular client device of the second group of one or more client devices that indicates a selection of a trend, wherein the trend is related to the particular brand, and wherein each of the messages in the first group of one or more messages includes content associated with the trend;
construct the carousel portion of the targeted message by:
placing a distinct graphical element that contains a respective brand message of the group of one or more brand messages and information identifying a user who composed the respective brand message into a respective transitional window of the group of two or more transitional windows,
forming an additional transitional window that includes the original portion of the targeted message, and
adding the additional transitional window to the group of one or more transitional windows to form an expanded group of three or more transitional windows; and
send, to the information distribution system, the targeted message to be output for display at the particular client device of the second group of one or more client devices, wherein the targeted message is displayed such that only a single transitional window of the expanded group of three or more transitional windows is fully displayed at a given time, such that the particular client device of the second group of one or more client devices is configured to individually and cyclically display each transitional window in the expanded group of three or more transitional windows during a period of time, and such that a transition between the transitional windows of the expanded group of three or more transitional windows is a horizontal transition.
10. The non-transitory computer-readable storage medium of claim 9 , wherein the instructions that cause the at least one processor to determine the interest score comprise instructions that, when executed, cause the at least one processor to:
determine a strength of a relation between the content of the candidate message and a particular product belonging to the particular brand; and
determine, based at least in part on the strength of the relation between the content of the candidate message and the particular product belonging to the particular brand, the interest score.
11. The non-transitory computer-readable storage medium of claim 9 , further comprising instructions that, when executed, cause the at least one processor to:
cycle the carousel portion automatically after a predetermined amount of time such that a different transitional window of the group three or more transitional windows is shown in a graphical user interface at the client device.
12. The non-transitory computer-readable storage medium of claim 9 , further comprising instructions that, when executed, cause the at least one processor to:
cycle the carousel portion responsive to receiving an indication of user input at the client device such that a different transitional window of the group of three or more transitional windows is shown in a graphical user interface at the client device.
13. The non-transitory computer-readable storage medium of claim 9 , wherein a brand message in the group of one or more brand messages includes media comprising one of audio, a video, a picture, or an animated image file, and wherein the media is automatically played upon display of the respective transitional window of the group of two or more transitional windows that contains the brand message.
14. The non-transitory computer-readable storage medium of claim 9 , further comprising instructions that, when executed, cause the at least one processor to:
determine secondary information for the candidate message, wherein the secondary information comprises one or more of:
an author of the candidate message,
a number of subscribers to a social media account of the author of the candidate message,
a probability that a user of a client device of the second group of one or more client devices will engage with the candidate message,
an interaction history between the user of the client device of the second group of one or more client devices and the author of the candidate message,
a time that the candidate message was authored,
a geolocation of a client device of the first group of one or more client devices used by the author of the candidate message to post the candidate message, or
a topic of the candidate message; and
determine, based at least in part on the content of the candidate message and the secondary information for the candidate message, using the machine learning model, the interest score.
15. The non-transitory computer-readable storage medium of claim 9 , further comprising instructions that, when executed, cause the at least one processor to:
receive, from the information distribution system, an indication that a user of a client device of the second group of one or more client devices engaged with the targeted message, wherein engaging with the targeted message comprises one of viewing the targeted message, disseminating the targeted message to one or more subscribers of a social media account associated with the user, or interacting with one or more hyperlinks included in the targeted message; and
update the machine learning model to indicate that the user of the client device of the second group of client devices engaged with the targeted message.
16. The non-transitory computer-readable storage medium of claim 15 , further comprising instructions that, when executed, cause the at least one processor to:
responsive to receiving the indication that the user of the client device of the second group of one or more client devices engaged with the targeted message, receive, by an account associated with the computing device, a credit from an account associated with the information distribution system.
17. A computing 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, from an information distribution system, a first group of one or more messages composed by one or more users of a first group of one or more client devices accessing a social media platform, wherein each of the messages in the first group of one or more messages includes a reference to a particular brand;
determine, using a machine learning model, an interest score for a candidate message based at least in part on content of the candidate message, wherein the candidate message is included in the first group of one or more messages;
responsive to determining that the interest score satisfies a threshold interest score, insert the candidate message into a group of one or more brand messages, wherein each brand message in the group of one or more brand messages includes a reference to the particular brand; and
send, to the information distribution system, a targeted message to be output for display at a second group of one or more client devices, wherein the targeted message comprises an original portion and a carousel portion, wherein the carousel portion comprises a group of two or more transitional windows, wherein each transitional window in the group of two or more transitional windows includes one of the brand messages in the group of one or more brand messages, and wherein the original portion comprises content formed at the computing device,
the computing device further comprising instructions executable by the at least one processor to:
initially receive an indication of user input from a particular client device of the second group of one or more client devices that indicates a selection of a trend, wherein the trend is related to the particular brand, and wherein each of the messages in the first group of one or more messages includes content associated with the trend;
construct the carousel portion of the targeted message by:
placing a distinct graphical element that contains a respective brand message of the group of one or more brand messages and information identifying a user who composed the respective brand message into a respective transitional window of the group of two or more transitional windows,
forming an additional transitional window that includes the original portion of the targeted message, and
adding the additional transitional window to the group of one or more transitional windows to form an expanded group of three or more transitional windows; and
send, to the information distribution system, the targeted message to be output for display at the particular client device of the second group of one or more client devices, wherein the targeted message is displayed such that only a single transitional window of the expanded group of three or more transitional windows is fully displayed at a given time, such that the particular client device of the second group of one or more client devices is configured to individually and cyclically display each transitional window in the expanded group of three or more transitional windows during a period of time, and such that a transition between the transitional windows of the expanded group of three or more transitional windows is a horizontal transition.
18. The computing device of claim 17 , wherein the instructions that are executable by the at least one processor to determine the interest score comprise instructions that are executable by the at least one processor to:
determine a strength of a relation between the content of the candidate message and a particular product belonging to the particular brand; and
determine, based at least in part on the strength of the relation between the content of the candidate message and the particular product belonging to the particular brand, the interest score.
19. The computing device of claim 17 , wherein the non-transitory computer-readable storage medium further stores instructions that are executable by the at least one processor to:
cycle the carousel portion automatically after a predetermined amount of time such that a different transitional window of the group of three or more transitional windows is shown in a graphical user interface at the client device.
20. The computing device of claim 17 , wherein the non-transitory computer-readable storage medium further stores instructions that are executable by the at least one processor to:
cycle the carousel portion responsive to receiving an indication of user input at the client device such that a different transitional window of the group of three or more transitional windows is shown in a graphical user interface at the client device.
21. The computing device of claim 17 , wherein the non-transitory computer-readable storage medium further stores instructions that are executable by the at least one processor to:
determine secondary information for the candidate message, wherein the secondary information comprises one or more of:
an author of the candidate message,
a number of subscribers to a social media account of the author of the candidate message,
a probability that a user of a client device of the second group of one or more client devices will engage with the candidate message,
an interaction history between the user of the client device of the second group of one or more client devices and the author of the candidate message,
a time that the candidate message was authored,
a geolocation of a client device of the first group of one or more client devices used by the author of the candidate message to post the candidate message, or
a topic of the candidate message; and
determine, based at least in part on the content of the candidate message and the secondary information for the candidate message, using the machine learning model, the interest score.
22. The computing device of claim 17 , wherein the non-transitory computer-readable storage medium further stores instructions that are executable by the at least one processor to:
receive, from the information distribution system, an indication that a user of a client device of the second group of one or more client devices engaged with the targeted message, wherein engaging with the targeted message comprises one of viewing the targeted message, disseminating the targeted message to one or more subscribers of a social media account associated with the user, or interacting with one or more hyperlinks included in the targeted message;
update the machine learning model to indicate that the user of the client device of the second group of client devices engaged with the targeted message; and
responsive to receiving the indication that the user of the client device of the second group of one or more client devices engaged with the targeted message, receive, by an account associated with the computing device, a credit from an account associated with the information distribution system.