Search-Powered Connection Targeting

Abstract

A social networking system extends the reach of an ad by allowing an advertiser to seed a search for suggesting targeting criteria for an ad. Using the seeds, the social networking system identifies a set of seed objects from a social graph. The social networking system traverses the social graph to compute the similarity between the seed objects and candidate objects related to the seed objects. Based on the computed similarity, the social networking system suggests a set of target objects to the advertiser. The social networking system receives a selection of one or more target objects from the advertiser. From the selected target objects the social networking system determines one or more targeting criteria for the ad, so users with an edge in the social graph to any of the selected target objects are eligible to receive the ad.

What is claimed is: 
     
         1 . A method comprising:
 identifying one or more seed objects based on one or more seeds for suggesting targeting criteria for an advertisement;   identifying a plurality of other objects stored in a database of a social networking system based on connections between the one or more seed objects and the identified other objects;   computing a similarity between one or more of the seed objects and the plurality of other objects, the similarity between a seed object and each of the plurality of other objects determined based at least in part on a comparison of objects in the social networking system having connections to both the other object and to the seed objects and objects not having connections to both the other object and to the seed objects;   presenting one or more candidate objects for use in targeting criteria for the advertisement, the one or more candidate objects selected from the plurality of other objects based on the computed similarities; and   responsive to a selection of one or more target objects from the one or more candidate objects, determining one or more targeting criteria for the advertisement based on the selected target objects.   
     
     
         2 . The method of  claim 1 , wherein the one or more seeds comprise one or more keywords associated with the advertisement. 
     
     
         3 . The method of  claim 1 , wherein the one or more seeds comprise one or more objects maintained by the social networking system and associated with the advertisement. 
     
     
         4 . The method of  claim 3 , wherein objects comprise at least one of pages, groups, events, posts, comments, and content. 
     
     
         5 . The method of  claim 1 , wherein the one or more seeds comprises a list of users. 
     
     
         6 . The method of  claim 1 , wherein identifying the one or more seed objects comprises receiving the seed objects from an advertiser associated with the advertisement. 
     
     
         7 . The method of  claim 1 , further comprising:
 presenting a second set of candidate objects for use in the targeting criteria for the advertisement, the second set of candidate objects selected from the plurality of other objects based on the computed similarities; and   providing the second set of candidate objects to an advertiser associated with the advertisement.   
     
     
         8 . The method of  claim 7 , further comprising:
 receiving a selection of one or more additional target objects from the second set of candidate objects; and   determining one or more additional targeting criteria for the advertisement based on the selected one or more additional target objects.   
     
     
         9 . The method of  claim 1 , wherein the one or more candidate objects include one or more of the seed objects. 
     
     
         10 . A method comprising:
 identifying one or more seed objects based on one or more seeds for suggesting targeting criteria for an advertisement;   identifying a plurality of other objects stored in a database of a social networking system based on connections between the one or more seed objects and the identified other objects;   computing a similarity between one or more of the seed objects and the plurality of other objects, the similarity between a seed object and each of the plurality of other objects determined based at least in part on a comparison of objects in the social networking system having connections to both the other object and to the seed objects and objects not having connections to both the other object and to the seed objects; and   determining one or more targeting criteria for the advertisement based at least in part on the computed similarities of the seed object and the plurality of other objects.   
     
     
         11 . The method of  claim 10 , wherein the one or more seeds comprise one or more keywords associated with the advertisement. 
     
     
         12 . The method of  claim 10 , wherein the one or more seeds comprise one or more objects maintained by the social networking system and associated with the advertisement. 
     
     
         13 . The method of  claim 12 , wherein objects comprise at least one of pages, groups, events, posts and comments. 
     
     
         14 . The method of  claim 10 , wherein the one or more seeds comprises a list of users. 
     
     
         15 . The method of  claim 10 , wherein identifying the one or more seed objects comprises receiving the seed objects from an advertiser system. 
     
     
         16 . The method of  claim 10 , wherein the one or more targeting criteria for the advertisement is determined based on a highest computed similarity of the seed object and the plurality of other objects. 
     
     
         17 . The method of  claim 10 , wherein the one or more targeting criteria for the advertisement is determined based on a highest computed similarity of the seed object and a range of object types from the plurality of other objects. 
     
     
         18 . The method of  claim 10 , further comprising determining one or more targeting criteria for the advertisement based at least in part on a preference specified by an advertiser, the preference specifying one or a combination of a number of candidate objects, a candidate object type, and a threshold computed similarity of the seed object and each of the plurality of other objects. 
     
     
         19 . A non-transitory computer readable medium comprising instructions that when executed by a processor, cause the processor to:
 identify one or more seed objects based on one or more seeds for suggesting targeting criteria for an advertisement;   identify a plurality of other objects stored in a database of a social networking system based on connections between the one or more seed objects and the identified other objects;   compute a similarity between one or more of the seed objects and the plurality of other objects, the similarity between a seed object and each of the plurality of other objects determined based at least in part on a comparison of objects in the social networking system having connections to both the other object and to the seed objects and objects not having connections to both the other object and to the seed objects; and   determine one or more targeting criteria for the advertisement based at least in part on the computed similarities of the seed object and the plurality of other objects.   
     
     
         20 . The non-transitory computer readable medium of  claim 19 , further comprising instructions that when executed by the processor, cause the processor to determine one or more targeting criteria for the advertisement based at least in part on a preference specified by an advertiser, the preference specifying one or a combination of a number of candidate objects, a candidate object type, and a threshold computed similarity of the seed object and each of the plurality of other objects.