Systems and methods for suggesting content
Systems, methods, and non-transitory computer-readable media can train a machine learning model to output respective scores for content items based at least in part on information describing a user, wherein a score for a content item measures a likelihood that the user will select the content item to be included in a social profile of the user. A determination is made that a first user of the social networking system is eligible for a content item suggestion. A first content item to be provided as a suggestion to the first user is determined based at least in part on the model. The first content item is provided as a suggestion to the first user for use in a social profile of the first user.
1. A computer-implemented method comprising:
determining, by a social networking system, that a user of the social networking system is eligible for a cover photo suggestion;
providing, by the social networking system, a set of images associated with the user and one or more sets of words determined from content associated with the user along with each image as input to a machine learning model, wherein the content includes at least one of posts, comments, or groups of the user;
obtaining, by the social networking system, respective scores for the set of images as output of the machine learning model, wherein a score for a corresponding image measures a likelihood that the user selects the corresponding image as a cover photo in a social profile of the user; and
selecting, by the social networking system, among the set of images, an image having the highest score as a cover photo suggestion for use in a social profile of the user.
2. The computer-implemented method of claim 1 , wherein determining that the user of the social networking system is eligible for a cover photo suggestion further comprises:
determining, by the social networking system, that the user has not selected a cover photo for use in the social profile of the user.
3. The computer-implemented method of claim 1 , wherein determining that the user of the social networking system is eligible for a cover photo suggestion further comprises:
determining, by the social networking system, that the user has uploaded an image to the social networking system.
4. The computer-implemented method of claim 1 , further comprising:
generating, by the social networking system, a set of training examples to train the model, wherein each training example includes information describing a user and a corresponding set of features that describe a cover photo being used in a social profile of the user.
5. The computer-implemented method of claim 4 , wherein generating the set of training examples further comprises:
determining, by the social networking system, one or more sets of words that describe a user from content that was published by the user through the social networking system.
6. The computer-implemented method of claim 5 , wherein determining the one or more sets of words further comprises:
extracting, by the social networking system, at least one noun, verb, or concept from the content that was published by the user.
7. The computer-implemented method of claim 4 , wherein generating the set of training examples further comprises:
determining, by the social networking system, one or more sets of words that describe a user from images that are associated with the user in the social networking system.
8. The computer-implemented method of claim 1 , wherein the respective scores are adjusted based at least in part on a temporal degradation function.
9. The computer-implemented method of claim 1 , wherein the set of images includes images uploaded to the social networking system by the user.
10. A system comprising:
at least one processor; and
a memory storing instructions that, when executed by the at least one processor, cause the system to perform:
determining that a user of the social networking system is eligible for a cover photo suggestion;
providing a set of images associated with the user and one or more sets of words determined from content associated with the user along with each image as input to a machine learning model, wherein the content includes at least one of posts, comments, or groups of the user;
obtaining respective scores for the set of images as output of the machine learning model, wherein a score for a corresponding image measures a likelihood that the user selects the corresponding image as a cover photo in a social profile of the user;
and selecting among the set of images, an image having the highest score as a cover photo suggestion for use in a social profile of the user.
11. The system of claim 10 , wherein determining that the user of the social networking system is eligible for a cover photo suggestion further causes the system to perform:
determining that the user has not selected a cover photo for use in the social profile of the user.
12. The system of claim 10 , wherein determining that the user of the social networking system is eligible for a cover photo suggestion further causes the system to perform:
determining that the user has uploaded an image to the social networking system.
13. The system of claim 10 , wherein the instructions further cause the system to perform:
generating a set of training examples to train the model, wherein each training example includes information describing a user and a corresponding set of features that describe a cover photo being used in a social profile of the user.
14. The system of claim 13 , wherein generating the set of training examples further causes the system to perform:
determining one or more sets of words that describe a user from content that was published by the user through the social networking system.
15. A non-transitory computer-readable storage medium including instructions that, when executed by at least one processor of a computing system, cause the computing system to perform a method comprising:
determining that a user of the social networking system is eligible for a cover photo suggestion;
providing a set of images associated with the user and one or more sets of words determined from content associated with the user along with each image as input to a machine learning model, wherein the content includes at least one of posts, comments, or groups of the user as input to a machine learning model;
obtaining respective scores for the set of images as output of the machine learning model, wherein a score for a corresponding image measures a likelihood that the user selects the corresponding image as a cover photo in a social profile of the user; and
selecting among the set of images, an image having the highest score as a cover photo suggestion for use in a social profile of the user.
16. The non-transitory computer-readable storage medium of claim 15 , wherein determining that the user of the social networking system is eligible for a cover photo suggestion further causes the computing system to perform:
determining that the user has not selected a cover photo for use in the social profile of the user.
17. The non-transitory computer-readable storage medium of claim 15 , wherein determining that the user of the social networking system is eligible for a cover photo suggestion further causes the computing system to perform:
determining that the user has uploaded an image to the social networking system.
18. The non-transitory computer-readable storage medium of claim 15 , wherein the instructions further cause the computing system to perform:
generating a set of training examples to train the model, wherein each training example includes information describing a user and a corresponding set of features that describe a cover photo being used in a social profile of the user.
19. The non-transitory computer-readable storage medium of claim 15 , wherein generating the set of training examples further causes the computing system to perform:
determining one or more sets of words that describe a user from content that was published by the user through the social networking system.