Content recommendation based on context

A system comprising:

• a processor;
• and
• a memory storing instructions that, when executed, cause the system to:
• receive data describing one or more first engagement actions performed by a first user;
• generate an engagement profile associated with the first user based on the one or more first engagement actions;
• receive data describing one or more images associated with the first user;
• determine one or more locations associated with the one or more images;
• generate a location profile associated with the first user based on the one or more locations;
• receive data describing one or more content items;
• determine a degree of match between one or more subjects associated with the one or more content items and at least one of the engagement profile and the location profile;
• determine one or more interest scores for the one or more content items based on the degree of match;
• determine one or more recommended items from the one or more content items based on the one or more interest scores;
• and
• provide the one or more recommended items to the first user.

A computer program product comprising a non-transitory computer usable medium including a computer readable program, wherein the computer readable program when executed on a computer causes the computer to:

• receive data describing one or more first engagement actions performed by a first user;
• generate an engagement profile associated with the first user based on the one or more first engagement actions;
• receive data describing one or more images associated with the first user;
• determine one or more locations associated with the one or more images;
• generate a location profile associated with the first user based on the one or more locations;
• receive data describing one or more content items;
• determine a degree of match between one or more subjects associated with the one or more content items and at least one of the engagement profile and the location profile;
• determine one or more interest scores for the one or more content items based on the degree of match;
• determine one or more recommended items from the one or more content items based on the one or more interest scores;
• and
• provide the one or more recommended items to the first user.