Systems and methods for identifying and grouping related content labels

Abstract

Systems, methods, and non-transitory computer-readable media can acquire a set of labels associated with a set of content items. Each label in the set of labels can be associated with at least one content item in the set of content items. It can be determined that at least two labels, out of the set of labels, are related. The at least two labels can be determined to be related based on at least one of a co-occurrence metric associated with the at least two labels or a topic similarity metric associated with the at least two labels. One label can be selected, out of the at least two labels, as being representative of the at least two labels.

What is claimed is: 
     
         1 . A computer-implemented method comprising:
 determining, by a computing system, that at least a first label and a second label associated with content items of a system are related;   selecting, by the computing system, the first label as representative of the second label based on usage of the first label and the second label on the system; and   replacing, by the computing system, the second label with the first label for an action taken on the system.   
     
     
         2 . The computer-implemented method of  claim 1 , wherein the system is a social networking system and the selecting the first label as representative of the second label based on usage of the first label and the second label comprises:
 determining a social engagement metric for the first label; and   determining a social engagement metric for the second label.   
     
     
         3 . The computer-implemented method of  claim 2 , wherein the selecting the first label as representative of the second label based on usage of the first label and the second label further comprises:
 determining the social engagement metric for the first label is greater than the social engagement metric for the second label; and   selecting the first label as representative of the second label based on the determining the social engagement metric for the first label is greater than the social engagement metric for the second label.   
     
     
         4 . The computer-implemented method of  claim 2 , wherein the social engagement metric for a label is based on a number of times the label has been posted. 
     
     
         5 . The computer-implemented method of  claim 2 , wherein the social engagement metric for a label is based on a recency property associated with posting of the label. 
     
     
         6 . The computer-implemented method of  claim 2 , wherein the social engagement metric for a label is based on a quantity of interactions associated with the label. 
     
     
         7 . The computer-implemented method of  claim 6 , wherein the interactions comprise at least one of clicks, taps, or shares. 
     
     
         8 . The computer-implemented method of  claim 2 , wherein the social engagement metric for a label is based on a quantity of distinct users who have utilized the label. 
     
     
         9 . The computer-implemented method of  claim 1 , wherein at least one of the first label or the second label are among a set of labels that are trending on the system. 
     
     
         10 . The computer-implemented method of  claim 1 , wherein the replacing the second label with the first label for the action taken on the system comprises:
 detecting that the second label is being entered; and   providing the first label instead of the second label.   
     
     
         11 . A computing system comprising:
 at least one processor; and   a memory storing instructions that, when executed by the at least one processor, cause the computing system to perform:   determining that a plurality of labels associated with content items of a system are related;   selecting a first label of the plurality of labels as representative of the plurality of labels based on usage of the plurality of labels on the system; and   utilizing the first label instead of other labels of the plurality of labels for user actions taken on the system.   
     
     
         12 . The computing system of  claim 11 , wherein the system is a social networking system and the selecting the first label of the plurality of labels as representative of the plurality of labels based on usage of the plurality of labels comprises:
 determining a social engagement metric for the first label; and   determining social engagement metrics for the other labels.   
     
     
         13 . The computing system of  claim 12 , wherein the selecting the first label of the plurality of labels as representative of the plurality of labels based on usage of the plurality of labels further comprises:
 determining the social engagement metric for the first label is greater than the social engagement metrics for the other labels; and   selecting the first label as representative of the plurality of labels based on the determining the social engagement metric for the first label is greater than the social engagement metrics for the other labels.   
     
     
         14 . The computing system of  claim 12 , wherein the social engagement metric for a label is based on a number of times the label has been posted. 
     
     
         15 . The computing system of  claim 12 , wherein the social engagement metric for a label is based on a recency property associated with posting of the label. 
     
     
         16 . A non-transitory computer-readable storage medium including instructions that, when executed by at least one processor of a computing system, cause the computing system to perform a method comprising:
 determining that a plurality of hashtags associated with content items of a social networking system are related;   selecting a first hashtag of the plurality of hashtags as representative of the plurality of hashtags based on usage of the plurality of hashtags on the social networking system; and   utilizing the first hashtag instead of other hashtags of the plurality of hashtags for a user action taken on the social networking system.   
     
     
         17 . The non-transitory computer-readable storage medium of  claim 16 , wherein the selecting the first hashtag of the plurality of hashtags as representative of the plurality of hashtags based on usage of the plurality of hashtags comprises:
 determining a social engagement metric for the first hashtag; and   determining social engagement metrics for the other hashtags.   
     
     
         18 . The non-transitory computer-readable storage medium of  claim 17 , wherein the selecting the first hashtag of the plurality of hashtags as representative of the plurality of hashtags based on usage of the plurality of hashtags further comprises:
 determining the social engagement metric for the first hashtag is greater than the social engagement metrics for the other hashtags; and   selecting the first hashtag as representative of the plurality of hashtags based on the determining the social engagement metric for the first hashtag is greater than the social engagement metrics for the other hashtags.   
     
     
         19 . The non-transitory computer-readable storage medium of  claim 17 , wherein the social engagement metric for a hashtag is based on a quantity of interactions associated with the hashtag. 
     
     
         20 . The non-transitory computer-readable storage medium of  claim 17 , wherein the social engagement metric for a hashtag is based on a quantity of distinct users who have utilized the hashtag.