Systems and methods for providing recommendations and explanations
View Patent ↗Provided herein is a system or method for a users-to-follow recommendation engine for, based at least in part on social network information and information about users in one or more social networks, determining features relating to users, including topical features and social features, determining, using a model constructed utilizing the determined features, for a set or users, a subset of the set of users for which the user has a high linkage, relative to other linkages in the set, and determining, using the model, and displaying to the user, a recommendation to follow and an associated explanation, of at least one particular user of the subset of the users wherein the associated explanation includes a topical-based explanation when a predominant basis for the high linkage is determined to be topical and a social-based explanation when a predominant basis for the high linkage is determined to be social.
1. A computing device comprising:
a processor; and
memory comprising processor-executable instructions that when executed by the processor cause performance of operations, the operations comprising:
collecting features associated with a plurality of users of a social network including a first remote device user and a second user;
storing the features in a database;
analyzing the database to determine one or more linkages between one or more users, wherein the one or more linkages includes a linkage between the first user and the second user;
responsive to determining that the linkage between the first user and the second user exceeds a first threshold, generating an electronic recommendation for the first user to follow the second user, wherein the generating comprises:
responsive to determining that a strength of a social linkage between the first user and the second user exceeds a strength of a topical linkage between the first user and the second user, generating, as at least part of the electronic recommendation, a first explanation of the social linkage between the first user and the second user, wherein the first explanation is indicative of one or more social connection links between the first user and the second user; and
responsive to determining that the strength of the topical linkage between the first user and the second user exceeds the strength of the social linkage, generating, as at least part of the electronic recommendation, a second explanation of the topical linkage between the first user and the second user; and
controlling a graphical user interface of the first user to display the electronic recommendation, wherein the electronic recommendation is associated with an increased effectiveness based upon inclusion of at least one of the first explanation of the social linkage or the second explanation of the topical linkage in the electronic recommendation, and enables the building of a first network of the first user at an increased speed.
2. The computing device of claim 1 , wherein the features comprise at least one of one or more profiles of one or more users, one or more interests of one or more users or one or more activities of one or more users.
3. The computing device of claim 1 , the operations comprising:
determining the linkage based upon a predicted affinity of the first remote device user with respect to the second user.
4. The computing device of claim 1 , the operations comprising:
determining the linkage based upon a predicted probability of the first user accepting a recommendation to follow the second user.
5. The computing device of claim 1 , the operations comprising:
determining the social linkage based upon at least one of a common bond between the first user and the second user, one or more social personal connections between the first user and the second user, a density of links exceeding a second third threshold or a reciprocity of links exceeding a third fourth threshold.
6. The computing device of claim 1 , the operations comprising:
determining the topical linkage based upon an interest in a topic.
7. The computing device of claim 1 , wherein the one or more social connection links indicated in the first explanation comprise one or more common contacts between the first user and the second user.
8. A method, implemented via a computer comprising a processor, comprising:
collecting features associated with a plurality of users of a social network including a first user and a second user;
storing the features in a database;
analyzing the database to determine one or more linkages between one or more users, wherein the one or more linkages includes a linkage between the first user and the second user;
responsive to determining that the linkage between the first user and the second user exceeds a first threshold, generating an electronic recommendation for the first user to follow the second user, wherein the generating comprises:
responsive to determining that a strength of a social linkage between the first user and the second user exceeds a strength of a topical linkage between the first user and the second user, generating, as at least part of the electronic recommendation, a first explanation of the social linkage between the first user and the second user, wherein the first explanation is indicative of one or more social connection links between the first user and the second user; and
responsive to determining that the strength of the topical linkage between the first user and the second user exceeds the strength of the social linkage, generating, as at least part of the electronic recommendation, a second explanation of the topical linkage between the first user and the second user; and
controlling a graphical user interface of the first user to display the electronic recommendation, wherein the electronic recommendation is associated with an increased effectiveness based upon inclusion of at least one of the first explanation of the social linkage or the second explanation of the topical linkage in the electronic recommendation, and enables the building of a first network of the first user at an increased speed.
9. The method of claim 8 , wherein the features comprise at least one of one or more profiles of one or more users, one or more interests of one or more users or one or more activities of one or more users.
10. The method of claim 8 , comprising:
determining the linkage based upon a predicted affinity of the first user with respect to the second user.
11. The method of claim 8 , comprising:
determining the linkage based upon a predicted probability of the first user accepting a recommendation to follow the second user.
12. The method of claim 8 , comprising:
determining the social linkage based upon at least one of a common bond between the first user and the second user, one or more social personal connections between the first user and the second user, a density of links exceeding a second threshold or a reciprocity of links exceeding a third threshold.
13. The method of claim 8 , comprising:
determining the topical linkage based upon an interest in a topic.
14. The method of claim 8 , wherein the one or more social connection links indicated in the first explanation comprise one or more common contacts between the first user and the second user.
15. A non-transitory computer readable medium comprising instructions that when executed cause performance of operations, the operations comprising:
collecting features associated with a plurality of users of a social network including a first user and a second user;
storing the features in a database;
analyzing the database to determine one or more linkages between one or more users, wherein the one or more linkages includes a linkage between the first user and the second user;
responsive to determining that the linkage between the first user and the second user exceeds a first threshold, generating an electronic recommendation for the first user to follow the second user, wherein the generating comprises:
responsive to determining that a strength of a social linkage between the first user and the second user exceeds a strength of a topical linkage between the first user and the second user, generating, as at least part of the electronic recommendation, a first explanation of the social linkage between the first user and the second user, wherein the first explanation is indicative of one or more social connection links between the first user and the second user; and
responsive to determining that the strength of the topical linkage between the first user and the second user exceeds the strength of the social linkage, generating, as at least part of the electronic recommendation, a second explanation of the topical linkage between the first user and the second user; and
controlling a graphical user interface of the first user to display the electronic recommendation, wherein the electronic recommendation is associated with an increased effectiveness based upon inclusion of at least one of the first explanation of the social linkage or the second explanation of the topical linkage in the electronic recommendation, and enables the building of a first network of the first user at an increased speed.
16. The non-transitory computer readable medium of claim 15 , wherein the features comprise at least one of one or more profiles of one or more users, one or more interests of one or more users or one or more activities of one or more users.
17. The non-transitory computer readable medium of claim 15 , the operations comprising:
determining the linkage based upon a predicted affinity of the first user with respect to the second user.
18. The non-transitory computer readable medium of claim 15 , the operations comprising:
determining the linkage based upon a predicted probability of the first user accepting a recommendation to follow the second user.
19. The non-transitory computer readable medium of claim 15 , the operations comprising:
determining the social linkage based upon at least one of a common bond between the first user and the second user, one or more social personal connections between the first user and the second user, a density of links exceeding a second threshold or a reciprocity of links exceeding a third threshold.
20. The non-transitory computer readable medium of claim 15 , the operations comprising:
determining the topical linkage based upon an interest in a topic.