Method for inferring latent user interests based on image metadata
Techniques disclosed herein describe inferring user interests based on metadata of a plurality of multimedia objects captured by a plurality of users. An analysis tool receives, for each of the users, metadata describing each multimedia object in the plurality of objects associated with that user. Each multimedia object includes one or more attributes imputed to that object based on the metadata. The analysis tool identifies one or more concepts from the one or more attributes. Each concept includes at least a first attribute that co-occurs with a second attribute imputed to a first multimedia object. The analysis tool associates a first one of the plurality of users with at least one of the concepts based on the attributes imputed to multimedia objects associated with the first one of the plurality of users.
1. A method for inferring user interests based on metadata of a plurality of multimedia objects captured by a plurality of users, the method comprising:
receiving, for each of the users, metadata describing each multimedia object in the plurality of objects associated with that user, wherein each multimedia object includes one or more attributes imputed to that object based on the metadata and wherein each multimedia object is one of an image or a video;
identifying one or more concepts from the one or more attributes, wherein each concept includes at least a first attribute that co-occurs with a second attribute imputed to a first multimedia object; and
associating a first one of the plurality of users with at least one of the concepts based on the attributes imputed to multimedia objects associated with the first one of the plurality of users.
2. The method of claim 1 , further comprising:
training a learning model based on the association of the first one of the plurality of users with the at least one of the one or more concepts, wherein the learning model predicts associations of the first one of the plurality of users to one or more concepts not currently associated with the first one of the plurality of users.
3. The method of claim 2 , wherein the prediction is based on a correlation between at least a first concept in the associated one or more concepts and each of the one or more concepts.
4. The method of claim 2 , further comprising:
receiving metadata of a plurality of multimedia objects associated with a second one of the plurality of users, wherein each of the multimedia objects associated with the second one of the plurality of users includes one or more attributes imputed to that object based on the metadata; and
associating at least one of the one or more concepts with the second one of the plurality of users based on the learning model.
5. The method of claim 1 , wherein associating the first one of the plurality of users with at least one of the one or more concepts comprises:
determining a correlation measure between the first one of the plurality of users to each of the concepts based on the attributes imputed to multimedia objects in the plurality of multimedia objects associated with the first one of the plurality of users.
6. The method of claim 4 , wherein the first one of the plurality of users is associated with the at least one of the one or more concepts based on the correlation measure associated with that concept.
7. The method of claim 1 , wherein the concepts are identified based on Latent Dirichlet Allocation (LDA).
8. The method of claim 1 , further comprising:
determining, from the one or more concepts, a hierarchical relationship between a first concept and at least a second concept.
9. A non-transitory computer-readable storage medium storing instructions, which, when executed on a processor, performs an operation for inferring user interests based on metadata of a plurality of multimedia objects captured by a plurality of users, the operation comprising:
receiving, for each of the users, metadata describing each multimedia object in the plurality of objects associated with that user, wherein each multimedia object includes one or more attributes imputed to that object based on the metadata and wherein each multimedia object is one of an image or a video;
identifying one or more concepts from the one or more attributes, wherein each concept includes at least a first attribute that co-occurs with a second attribute imputed to a first multimedia object; and
associating a first one of the plurality of users with at least one of the concepts based on the attributes imputed to multimedia objects associated with the first one of the plurality of users.
10. The computer-readable storage medium of claim 9 , wherein the operation further comprises:
training a learning model based on the association of the first one of the plurality of users with the at least one of the one or more concepts, wherein the learning model predicts associations of the first one of the plurality of users to one or more concepts not currently associated with the first one of the plurality of users.
11. The computer-readable storage medium of claim 10 , wherein the prediction is based on a correlation between at least a first concept in the associated one or more concepts and each of the one or more concepts.
12. The computer-readable storage medium of claim 10 , wherein the operation further comprises:
receiving metadata of a plurality of multimedia objects associated with a second one of the plurality of users, wherein each of the multimedia objects associated with the second one of the plurality of users includes one or more attributes imputed to that object based on the metadata; and
associating at least one of the one or more concepts with the second one of the plurality of users based on the learning model.
13. The computer-readable storage medium of claim 9 , wherein associating the first one of the plurality of users with at least one of the one or more concepts comprises:
determining a correlation measure between the first one of the plurality of users to each of the concepts based on the attributes imputed to multimedia objects in the plurality of multimedia objects associated with the first one of the plurality of users.
14. The computer-readable storage medium of claim 13 , wherein the first one of the plurality of users is associated with the at least one of the one or more concepts based on the correlation measure associated with that concept.
15. The computer-readable storage medium of claim 9 , wherein the concepts are identified based on Latent Dirichlet Allocation (LDA).
16. A system, comprising:
a processor; and
a memory storing one or more application programs configured to perform an operation for inferring user interests based on metadata of a plurality of multimedia objects captured by a plurality of users, the operation comprising:
receiving, for each of the users, metadata describing each multimedia object in the plurality of objects associated with that user, wherein each multimedia object includes one or more attributes imputed to that object based on the metadata;
identifying one or more concepts from the one or more attributes, wherein each concept includes at least a first attribute that co-occurs with a second attribute imputed to a first multimedia object; and
associating a first one of the plurality of users with at least one of the concepts based on the attributes imputed to multimedia objects associated with the first one of the plurality of users by determining a correlation measure between the first one of the plurality of users to each of the concepts based on the attributes imputed to multimedia objects in the plurality of multimedia objects associated with the first one of the plurality of users.
17. The system of claim 16 , wherein the operation further comprises:
training a learning model based on the association of the first one of the plurality of users with the at least one of the one or more concepts, wherein the learning model predicts associations of the first one of the plurality of users to one or more concepts not currently associated with the first one of the plurality of users.
18. The system of claim 17 , wherein the prediction is based on a correlation between at least a first concept in the associated one or more concepts and each of the one or more concepts.
19. The system of claim 17 , wherein the operation further comprises:
receiving metadata of a plurality of multimedia objects associated with a second one of the plurality of users, wherein each of the multimedia objects associated with the second one of the plurality of users includes one or more attributes imputed to that object based on the metadata; and
associating at least one of the one or more concepts with the second one of the plurality of users based on the learning model.
20. The system of claim 16 , wherein the first one of the plurality of users is associated with the at least one of the one or more concepts based on the correlation measure associated with that concept.
21. The system of claim 16 , wherein the concepts are identified based on Latent Dirichlet Allocation (LDA).
22. The system of claim 16 , wherein each multimedia object is one of an image or a video.
23. The system of claim 16 , wherein the operation further comprises:
determining, from the one or more concepts, a hierarchical relationship between a first concept and at least a second concept.