Suppressing entity suggestions on online social networks
In one embodiment, a method includes receiving, by one or more computing devices of an online social network, from a client system of a first user of the online social network, a query inputted by the first user. The method further includes accessing a social graph of the online social network, the social graph including multiple nodes and multiple edges connecting the nodes, each node corresponding to an entity associated with the online social network. The method also includes identifying multiple entities matching the query, each identified entity having a duplication-value with respect to a canonical-entity, the duplication-values being based on a name similarity between the identified entity and the canonical-entity. The method also includes suppressing one or more entities of the identified entities based on the duplication-value of the entity and social-graph information associated with the entity.
1. A method comprising, by one or more computing devices of an online social network:
receiving, from a client system of a first user of the online social network, a query inputted by the first user;
accessing a social graph of the online social network, the social graph comprising a plurality of nodes and a plurality of edges connecting the nodes, each node corresponding to an entity associated with the online social network, wherein the first user corresponds to a first node of the plurality of nodes, and wherein each entity is associated with social-graph information that is based on its connections within the social graph;
identifying a plurality of entities matching the query, each identified entity having a duplication-value with respect to a canonical-entity, the duplication-values being based on (1) a name similarity between the identified entity and the canonical-entity and (2) one or more prior user interactions with respect to the identified entity and the canonical-entity, wherein the canonical-entity is identified based on its social-graph information;
suppressing one or more entities of the identified entities based on the duplication-value of the entity, with respect to the canonical entity, satisfying a predetermined threshold value and a value associated with the social-graph information associated with the entity, wherein each suppressed entity corresponds to a node that is not connected to the first node corresponding to the first user in the social graph; and
sending, to the client system, a search-results page for display to the first user, wherein the search-results page comprises references to one or more non-suppressed entities of the identified entities.
2. The method of claim 1 , wherein the duplication-value of each identified entity is further based on a geographic location or distance associated with the identified entity or the canonical-entity.
3. The method of claim 1 , wherein the duplication-value of each identified entity is further based on a number of check-ins, likes, or reviews associated with the entity.
4. The method of claim 1 , wherein the duplication-value of each identified entity is further based on crowdsourcing votes or redirects associated with the identified entity.
5. The method of claim 1 , wherein satisfying the predetermined threshold value comprises determining the duplication-value is above the predetermined threshold.
6. The method of claim 1 , wherein the duplication-value of each non-suppressed entity is below a threshold duplication-value.
7. The method of claim 1 , wherein the value associated with the social-graph information associated with the entity comprises a number of check-ins, likes, or reviews associated with the entity.
8. The method of claim 1 , wherein the value associated with the social-graph information associated with the entity comprises an affinity coefficient between the entity and the canonical-entity.
9. The method of claim 1 , wherein an affinity coefficient for each suppressed entity is below a threshold affinity-coefficient value.
10. The method of claim 1 , wherein the social-graph information associated with the entity comprises an affinity coefficient between the entity and the first user.
11. The method of claim 1 , further comprising updating a list of entities associated with the canonical-entity to remove one or more of the suppressed entities from the list.
12. The method of claim 1 , wherein the non-suppressed entities comprise two or more entities which are possible duplicate-entities having duplication-values above a threshold duplication-value.
13. The method of claim 1 , wherein the search-results page comprises a reference to the canonical-entity.
14. The method of claim 1 , wherein the search-results page comprises references to the canonical-entity and one of the non-suppressed entities.
15. The method of claim 14 , further comprising:
receiving, from the client system, a response indicating that the first user interacted with the canonical-entity; and
increasing the duplication-value of the one of the non-suppressed entities.
16. The method of claim 14 , further comprising:
receiving, from the client system, a response indicating that the first user interacted with the one of the non-suppressed entities; and
decreasing the duplication-value of the one of the non-suppressed entities.
17. The method of claim 1 , further comprising:
receiving, from the client system, a response indicating that the first user interacted with a particular reference corresponding to one of the non-suppressed entities; and
adjusting, based on the user interaction, the duplication-value of one or more of the non-suppressed entities.
18. The method of claim 1 , further comprising:
receiving, from the client system, a follow-up query inputted by the first user, the follow-up query indicating a suppressed entity of the suppressed one or more entities; and
decreasing, based on the follow-up query, the duplication-value of the suppressed entity.
19. The method of claim 1 , wherein the canonical-entity comprises a preferred entity with respect to a group of related entities.
20. One or more computer-readable non-transitory storage media embodying software that is operable when executed to:
receive, from a client system of a first user of an online social network, a query inputted by the first user;
access a social graph of the online social network, the social graph comprising a plurality of nodes and a plurality of edges connecting the nodes, each node corresponding to an entity associated with the online social network, wherein the first user corresponds to a first node of the plurality of nodes, and wherein each entity is associated with social-graph information that is based on its connections within the social graph;
identify a plurality of entities matching the query, each identified entity having a duplication-value with respect to a canonical-entity, the duplication-values being based on (1) a name similarity between the identified entity and the canonical-entity and (2) one or more prior user interactions with respect to the identified entity and the canonical-entity, wherein the canonical-entity is identified based on its social-graph information;
suppress one or more entities of the identified entities based on the duplication-value of the entity, with respect to the canonical entity, satisfying a predetermined threshold value and a value associated with the social-graph information associated with the entity, wherein each suppressed entity corresponds to a node that is not connected to the first node corresponding to the first user in the social graph; and
send, to the client system, a search-results page for display to the first user, wherein the search-results page comprises references to one or more non-suppressed entities of the identified entities.
21. A system comprising: one or more processors; and a memory coupled to the processors comprising instructions executable by the processors, the processors operable when executing the instructions to:
receive, from a client system of a first user of an online social network, a query inputted by the first user;
access a social graph of the online social network, the social graph comprising a plurality of nodes and a plurality of edges connecting the nodes, each node corresponding to an entity associated with the online social network, wherein the first user corresponds to a first node of the plurality of nodes, and wherein each entity is associated with social-graph information that is based on its connections within the social graph;
identify a plurality of entities matching the query, each identified entity having a duplication-value with respect to a canonical-entity, the duplication-values being based on (1) a name similarity between the identified entity and the canonical-entity and (2) one or more prior user interactions with respect to the identified entity and the canonical-entity, wherein the canonical-entity is identified based on its social-graph information;
suppress one or more entities of the identified entities based on the duplication-value of the entity, with respect to the canonical entity, satisfying a predetermined threshold value and a value associated with the social-graph information associated with the entity, wherein each suppressed entity corresponds to a node that is not connected to the first node corresponding to the first user in the social graph; and
send, to the client system, a search-results page for display to the first user, wherein the search-results page comprises references to one or more non-suppressed entities of the identified entities.