Recommending groups to join in a social networking system
View Patent ↗Based on information associated with users, a social networking system recommends one or more groups for a target user to join or to create. Characteristics of the target user, characteristics of users connected to the target user, characteristics of candidate groups in the social networking system may be used to identify groups for recommendation. The social networking system may provide questions to the target user and recommend a group to the target user based on received answers to the questions. For example, the answers to the provided question identify one or more characteristics of the target user, which are used to select a group for recommendation. Additionally, the social networking system may recommend additional users for the target user to add or invite to a group based on characteristics of the target user, the additional users, and/or the group.
1. A method comprising:
storing a plurality of groups in a social networking system, each group including one or more users of the social networking system;
accessing user profile information in the social networking system including information about a target user;
identifying a set of users connected to the target user in the social networking system;
identifying a set of candidate groups from the plurality of groups, the set of candidate groups including groups including one or more of the users connected to the target user;
determining, by one or more processors, a candidate score for each candidate group based on a number of connections between the users in the candidate group and the target user;
selecting a group from the candidate groups based on the candidate scores; and
presenting the selected group to the target user.
2. The method of claim 1 , wherein the candidate score associated with each candidate group is further determined based in part on one or more affinities between the target user and users in a candidate group.
3. The method of claim 2 , wherein determining the candidate score for each candidate group comprises:
determining affinities between users in the candidate group and the target user;
determining a level of activity of users in the candidate group;
for each user in the candidate group, determining a product of an affinity between a user in the candidate group and the target user and a level of activity of the user; and
summing the products.
4. The method of claim 1 , wherein presenting the selected group to the target user comprises:
displaying the selected group to the target user;
receiving a request from the target user to join the selected group; and
adding the target user to the selected candidate group.
5. A method comprising:
storing a plurality of groups in a social networking system, each group including one or more users of the social networking system;
determining a target user of the social networking system;
accessing a user profile in the social networking system of the target user;
identifying a set of social networking system users connected to the target user;
identifying a set of candidate groups from the plurality of groups based on characteristics of the target user and characteristics of the social networking system users connected to the target user;
determining, by one or more processors, a candidate score for each candidate group based on affinities between the users in the candidate group and the target user;
selecting a group from the candidate groups based on the candidate scores; and
presenting the selected group to the target user.
6. The method of claim 5 , wherein identifying the set of candidate groups from the plurality of groups based on characteristics of the target user and characteristics of the social networking system users connected to the target user comprises:
identifying candidate groups including one or more social networking system users connected to the target user.
7. The method of claim 5 , wherein identifying the set of candidate groups from the plurality of groups based on characteristics of the target user and characteristics of the social networking system users connected to the target user comprises:
identifying candidate groups including one or more social networking system users connected to the target user and having user profiles with at least a threshold number of common characteristics with the user profile in the social networking system of the target user.
8. The method of claim 5 , wherein selecting a group from the candidate groups based on the candidate scores comprises:
selecting a candidate group having a highest candidate score.
9. The method of claim 5 , wherein selecting a group from the candidate groups based on the candidate scores comprises:
selecting one or more candidate groups having candidate scores equaling or exceeding a threshold value.
10. The method of claim 5 , wherein determining the candidate score for each candidate group comprises:
for each user in a candidate group, determining a product of an affinity between a user in the candidate group and the target user and a level of activity of the user; and
summing the products.
11. The method of claim 10 , wherein determining the candidate score for each candidate group further comprises:
modifying candidate scores associated with candidate groups based on characteristics of the candidate groups stored by the social networking system.
12. The method of claim 11 , wherein the characteristics of a candidate group are selected from a group consisting of: an indication whether the candidate group is open or closed, a number of users in the candidate group, and a level of activity by users in the candidate group.
13. The method of claim 10 , wherein determining the candidate score for each candidate group further comprises:
modifying candidate scores associated with candidate groups based on at least one of: characteristics of the target user and characteristics of users in the candidate groups.
14. The method of claim 5 , further comprising:
displaying the selected group to the target user;
receiving a request from the target user to join the selected group; and
adding the target user to the selected candidate group.
15. The method of claim 5 , further comprising:
adding the target user to the selected group.
16. A method comprising:
storing a plurality of groups in a social networking system, each group including one or more users of the social networking system;
determining a target user of the social networking system;
accessing a user profile in the social networking system of the target user;
identifying a set of candidate groups from the plurality of groups based on one or more characteristics of the target user and one or more characteristics of each of the plurality of groups;
determining, by one or more processors, a candidate score for each candidate group based on affinities between the users in the candidate group and the target user;
selecting a group from the candidate groups based on the candidate scores; and
presenting the selected group to the target user.
17. The method of claim 16 , wherein identifying the set of candidate groups from the plurality of groups based on one or more characteristics of the target user and one or more characteristics of each of the plurality of groups comprises:
identifying a characteristic of the target user;
identifying the subject matter associated with each of the plurality of groups; and
selecting groups from the plurality of groups associated with subject matter related to the identified characteristic of the target user.
18. The method of claim 16 , wherein identifying the set of candidate groups from the plurality of groups based on one or more characteristics of the target user and one or more characteristics of each of the plurality of groups comprises:
identifying users in each candidate group; and
identifying candidate groups including at least a threshold number of users connected to the target user.
19. The method of claim 16 , wherein identifying the set of candidate groups from the plurality of groups based on one or more characteristics of the target user and one or more characteristics of each of the plurality of groups comprises:
identifying users in each candidate group; and
identifying candidate groups including at least a threshold number of users having a common characteristic with the target user.
20. The method of claim 16 , wherein determining the candidate score for each candidate group comprises:
for each user in a candidate group, determining a product of an affinity between a user in the candidate group and the target user and a level of activity of the user; and
summing the products.