Determining user affinities for content generation applications

A computer-implemented method comprising:

• publishing, to a media platform, a first digital content and corresponding metadata that includes a set of tags associated with a characteristic of a graphical image and a linguistic element in the first digital content;
• identifying a user interaction with the first digital content;
• based on the identified user interaction, generating an interaction report that includes the metadata corresponding to the first digital content and metadata corresponding to the identified user interaction;
• based on the interaction report, adding the metadata corresponding to the first digital content and the metadata corresponding to the identified user interaction from the interaction report to an affinity profile for the user including the set of tags associated with the characteristic of the graphical image and the linguistic element in the first digital content;
• and
• processing the affinity profile and a second digital content prior to publication of the second digital content to the internet connected media platform to predict a user interest in the second digital content.

A computing system comprising:

• a processor;
• and
• computer storage memory having computer-executable instructions stored thereon which, when executed by the processor, configure the computing system to:
• generate an affinity profile for a user, the affinity profile including a first set of tags associated with a first set of characteristics of a first graphical image and a first linguistic element in a first digital content;
• identify a second set of tags associated with a second set of characteristics of a second graphical image and a second linguistic element in a second digital content;
• process, by a machine learning model, the second set of tags associated with the second digital content and the first set of tags in the affinity profile of the user to determine an extent of similarity between the second set of tags associated with the second digital content and the first set of tags in the affinity profile of the user;
• and
• provide, for display, the extent of similarity to indicate a predicted user affinity for the second digital content.