Determining user affinities for content generation applications
Methods, computer systems, computer-storage media, and graphical user interfaces are provided for determining user affinities by tracking historical user interactions with tagged digital content and using the user affinities in content generation applications. Accordingly, the system may track user interactions with published digital content in order to generate user interaction reports whenever a user engages with the digital content. The system may aggregate the interaction reports to generate an affinity profile for a user or audience of users. A marketer may then generate digital content for a target user or audience of users and the system may process the digital content to generate a set of tags for the digital content. Based on the set of tags, the system may then evaluate the digital content in view of the affinity profile for the target user/audience to determine similarities or differences between the digital content and the affinity profile.
1. A non-transitory computer-readable medium storing executable instructions, which when executed by a processing device, cause the processing device to perform operations comprising:
receive, at a user interface of a content editing application, a selection of a target audience of one or more digital content users;
access an affinity profile associated with the target audience, wherein the affinity profile represents one or more tracked user interactions by users of the target audience with published first digital content, wherein the affinity profile further represents affinity values associated with one or more tags representing one or more characteristics of the first digital content, wherein a first set of tags of the one or more tags are associated with at least one of a characteristic of a graphical image or a linguistic element in the first digital content, the first set of tags embedded within metadata associated with the first digital content;
determine a second set of tags representing one or more characteristics of second digital content displayed on the user interface of the content editing application, wherein the second set of tags are associated with at least one of a characteristic of a graphical image or a linguistic element in the second digital content displayed on the user interface;
process the affinity profile and the second digital content displayed on the user interface to determine a set of similarities based on the second set of tags and affinity values associated with one or more tags from the first set of tags of the affinity profile;
display one or more affinity indicators on the user interface, wherein each of the one or more affinity indicators indicates an affinity score for each characteristic of the one or more characteristics of the digital content, based on the set of similarities;
modify, via the user interface, the second digital content based on at least one input received via the user interface, wherein the modified second digital content has an increased set of similarities with the affinity profile; and
publish, via a network to a media platform, an output of third digital content from the content editing application based on the modified second digital content.
2. The non-transitory computer-readable medium storing executable instructions of claim 1 , the operations further comprising:
display one or more content items from a library to suggest elements for inclusion in the second digital content displayed on the user interface based on computing the affinity score for the elements using the affinity profile.
3. The non-transitory computer-readable medium storing executable instructions of claim 2 , the operations further comprising:
rank the one or one or more content items in the library based at least on the affinity profile.
4. The non-transitory computer-readable medium storing executable instructions of claim 1 , wherein the affinity profile comprises an aggregate of a plurality of single user affinity profiles.
5. The non-transitory computer-readable medium storing executable instructions of claim 1 , the operations further comprising:
generate the second set of tags based on applying the published first digital content to a machine learning model.
6. The non-transitory computer-readable medium storing executable instructions of claim 1 , wherein the affinity profile is generated based on publication of the published first digital content to the media platform with corresponding metadata that includes the first set of tags, and identifying the one or more user interactions with the published first digital content.
7. The non-transitory computer-readable medium storing executable instructions of claim 1 , the operations further comprising:
process, by a machine learning model, the second digital content to generate the second set of tags; and
compare the second set of tags to the affinity profile to determine similarities or differences between the second set of tags and the affinity profile.
8. The non-transitory computer-readable medium storing executable instructions of claim 1 , the operations further comprising:
using the affinity profile, cause a display of a suggestion of third digital content, wherein the suggestion is determined based on a similarity between the affinity profile and the second digital content.
9. The non-transitory computer-readable medium storing executable instructions of claim 1 , wherein the one or more affinity indicators include one or more of: a color affinity, a reading level, a word count preference, a linguistic affinity, an emotional sentiment, and an overall affinity.
10. A method one comprising:
receiving, from a user interface of a content editing application, a selection of a target audience of one or more digital content users;
displaying first digital content on a content preview window of a user interface;
determining a first set of tags representing one or more characteristics of the first digital content, wherein the first set of tags are associated with at least one of a characteristic of a graphical image or a linguistic element in the first digital content displayed on the user interface;
accessing an affinity profile associated with the target audience, wherein the affinity profile represents one or more tracked user interactions by users of the target audience with published second digital content, wherein the affinity profile further represents affinity values associated with one or more tags representing one or more characteristics of the second digital content, wherein a first set of tags of the one or more tags are associated with at least one of a characteristic of a graphical image or a linguistic element in the second digital content, the first set of tags embedded within metadata associated with the second digital content;
processing the affinity profile and the first digital content displayed on the user interface to determine a set of similarities based on the first set of tags and affinity values associated with one or more tags from the first set of tags of the affinity profile;
computing an affinity score for individual characteristics of the one or more characteristics based on the set of similarities; and
displaying one or more affinity indicators on the user interface, wherein each of the one or more affinity indicators indicates the affinity score for each characteristic of the one or more characteristics
modifying, via the user interface, the first digital content based on at least one input received via the user interface, wherein the modified first digital content has an increased set of similarities with the affinity profile; and
publishing, via a network to a media platform, an output of third digital content from the content editing application based on the modified second digital content.
11. The method of claim 10 , wherein the one or more affinity indicators include the affinity score for one or more of: a color affinity, a reading level, a word count preference, a linguistic affinity, an emotional sentiment, and an overall affinity.
12. The method of claim 10 , the method further comprising:
displaying one or more content items from a library to suggest elements for inclusion in the first digital content displayed on the user interface based on computing the affinity score for the elements using the affinity profile.
13. The method of claim 12 , the method further comprising:
ranking the one or one or more content items in the library based at least on the affinity profile.
14. The method of claim 10 , wherein the affinity profile comprises an aggregate of a plurality of single user affinity profiles.
15. The method of claim 10 , the method further comprising:
generating the first set of tags based on applying the published first digital content to a machine learning model.
16. A system comprising:
at least one memory component; and
one or more processing devices coupled to the at least one memory component, the one or more processing devices to perform operations comprising:
receive, at a user interface of a content editing application, a selection of a target audience of one or more digital content users;
access an affinity profile associated with the target audience, wherein the affinity profile represents one or more tracked user interactions by users of the target audience with published first digital content, wherein the affinity profile further represents affinity values associated with one or more tags representing one or more characteristics of the first digital content, wherein a first set of tags of the one or more tags are associated with at least one of a characteristic of a graphical image or a linguistic element in the first digital content, the first set of tags embedded within metadata associated with the first digital content;
determine a second set of tags representing one or more characteristics of second digital content displayed on the user interface of the content editing application, wherein the second set of tags are associated with at least one of a characteristic of a graphical image or a linguistic element in the second digital content displayed on the user interface;
process the affinity profile and the second digital content displayed on the user interface to determine a set of similarities between the second set of tags and affinity values associated with one or more tags from the first set of tags of the affinity profile;
compute an affinity score for individual characteristics of the one or more characteristics based on the set of similarities; and
display one or more affinity indicators on the user interface, wherein each of the one or more affinity indicators indicates the affinity score for each characteristic of the one or more characteristics;
modify, via the user interface, the second digital content based on at least one input received via the user interface, wherein the modified second digital content has an increased set of similarities with the affinity profile; and
publish, via a network to a media platform, an output of third digital content from the content editing application based on the modified second digital content.
17. The system of claim 16 , the operations further comprising:
display one or more content items from a library to suggest elements for inclusion in the second digital content displayed on the user interface based on computing the affinity score for the elements using the affinity profile.
18. The system of claim 16 , the operations further comprising:
generate the first set of tags based on applying the published first digital content to a machine learning model.
19. The system of claim 16 , the operations further comprising:
generate the affinity profile based on publication of the published second digital content to the media platform with corresponding metadata that includes the first set of tags, and identify the one or more user interactions with the published first digital content.
20. The system of claim 16 , the operations further comprising:
process, by a machine learning model, the second digital content to generate the second set of tags; and
compare the second set of tags to the affinity profile to determine similarities or differences between the second set of tags and the affinity profile.