Temporal clustering of social networking content

Abstract

The present disclosure is directed towards systems and methods for efficiently identifying periodic trends of user-defined annotations among users of a social networking system. For example, systems and methods described herein involve grouping a set of digital content items into subsets of digital content items and performing one or more iterations of a clustering algorithm on the grouped set of digital content items to identify one or more temporal clusters of the user-defined annotation. Additionally, the systems and methods described herein involve performing one or more additional iterations of the clustering algorithm on one or more reduced sets of digital content items to identify one or more additional temporal clusters of the user-defined annotation. Further, the systems and methods involve determining that the user-defined annotation is periodic based on a time period between identified temporal clusters.

1 . A method, comprising:
 receiving, by a messaging server, a plurality of posts by users that are shared with other users of a social networking system;   selecting one or more annotations from a plurality of annotations, the plurality of annotations excluding annotations that have been determined to be regularly occurring;   correlating, by the messaging server, a subset of the plurality of posts that are associated with the one or more annotations;   calculating, by the messaging server, whether occurrences of a particular annotation among the one or more annotations are below a periodic threshold during a first time period;   based on a calculation that the occurrences of the particular annotation are below the periodic threshold:
 calculating, by the messaging server, that a number of the occurrences of the particular annotation occur within a second time period, wherein the second time period is less than the first time period and at least a portion of the second time period is included in the first time period; 
 selecting a set of users of the social networking system that the particular annotation is of interest to; 
 based on the number of the occurrences reaching a trending threshold amount, sending, by the messaging server, a message indication over a network to one or more client devices of the set of users that the particular annotation is trending. 
   
     
     
         2 . The method as recited in  claim 1 , further comprising:
 predicting, by the messaging server, that an annotation will be trending at a particular time period among users of the social networking system.   
     
     
         3 . The method as recited in  claim 1 , further comprising:
 pre-emptively identifying, by the messaging server, one or more annotations as trending at particular time periods across different time zones.   
     
     
         4 . The method as recited in  claim 1 , further comprising:
 maintaining, by the messaging server, a blacklist of annotations that is used to prevent one or more annotations from trending too early for one or more time zones.   
     
     
         5 . The method as recited in  claim 1 , further comprising:
 maintaining, by the messaging server, a blacklist of annotations that is used to prevent one or more annotations from trending too late for one or more time zones.   
     
     
         6 . The method as recited in  claim 1 , further comprising:
 maintaining, by the messaging server, a whitelist of annotations that is used to select one or more annotations as trending to users in one or more time zones.   
     
     
         7 . The method as recited in  claim 1 , further comprising:
 maintaining, by the messaging server, a whitelist of annotations that is used to select one or more annotations as trending to users in certain regions according to geolocation information.   
     
     
         8 . The method as recited in  claim 1 , wherein the particular annotation includes a hashtag. 
     
     
         9 . One or more non-transitory computer-readable storage media, storing one or more sequences of instructions, which when executed by one or more processors cause performance of:
 receiving, by a messaging server, a plurality of posts by users that are shared with other users of a social networking system;   selecting one or more annotations from a plurality of annotations, the plurality of annotations excluding annotations that have been determined to be regularly occurring;   correlating, by the messaging server, a subset of the plurality of posts that are associated with the one or more annotations;   calculating, by the messaging server, whether occurrences of a particular annotation among the one or more annotations are below a periodic threshold during a first time period;   based on a calculation that the occurrences of the particular annotation are below the periodic threshold:
 calculating, by the messaging server, that a number of the occurrences of the particular annotation occur within a second time period, wherein the second time period is less than the first time period and at least a portion of the second time period is included in the first time period; 
 selecting a set of users of the social networking system that the particular annotation is of interest to; 
 based on the number of the occurrences reaching a trending threshold amount, sending, by the messaging server, a message indication over a network to one or more client devices of the set of users that the particular annotation is trending. 
   
     
     
         10 . The one or more non-transitory computer-readable storage media as recited in  claim 9 , further comprising:
 predicting, by the messaging server, that an annotation will be trending at a particular time period among users of the social networking system.   
     
     
         11 . The one or more non-transitory computer-readable storage media as recited in  claim 9 , further comprising:
 pre-emptively identifying, by the messaging server, one or more annotations as trending at particular time periods across different time zones.   
     
     
         12 . The one or more non-transitory computer-readable storage media as recited in  claim 9 , further comprising:
 maintaining, by the messaging server, a blacklist of annotations that is used to prevent one or more annotations from trending too early for one or more time zones.   
     
     
         13 . The one or more non-transitory computer-readable storage media as recited in  claim 9 , further comprising:
 maintaining, by the messaging server, a blacklist of annotations that is used to prevent one or more annotations from trending too late for one or more time zones.   
     
     
         14 . The one or more non-transitory computer-readable storage media as recited in  claim 9 , further comprising:
 maintaining, by the messaging server, a whitelist of annotations that is used to select one or more annotations as trending to users in one or more time zones.   
     
     
         15 . The one or more non-transitory computer-readable storage media as recited in  claim 9 , further comprising:
 maintaining, by the messaging server, a whitelist of annotations that is used to select one or more annotations as trending to users in certain regions according to geolocation information.   
     
     
         16 . The one or more non-transitory computer-readable storage media as recited in  claim 9 , wherein the particular annotation includes a hashtag. 
     
     
         17 . An apparatus, comprising:
 one or more hardware processors; and   a memory storing instructions, which when executed by the one or more processors, cause the one or more processors to:
 receive a plurality of posts by users that are shared with other users of a social networking system; 
 select one or more annotations from a plurality of annotations, the plurality of annotations excluding annotations that have been determined to be regularly occurring; 
 correlate a subset of the plurality of posts that are associated with the one or more annotations; 
 calculate whether occurrences of a particular annotation among the one or more annotations are below a periodic threshold during a first time period; 
 based on a calculation that the occurrences of the particular annotation are below the periodic threshold:
 calculate that a number of the occurrences of the particular annotation occur within a second time period, wherein the second time period is less than the first time period and at least a portion of the second time period is included in the first time period; 
 select a set of users of the social networking system that the particular annotation is of interest to; 
 based on the number of the occurrences reaching a trending threshold amount, send a message indication over a network to one or more client devices of the set of users that the particular annotation is trending. 
 
   
     
     
         18 . The apparatus as recited in  claim 17 , wherein the instructions, which when executed by the one or more processors, further cause the one or more processors to:
 predict that an annotation will be trending at a particular time period among users of the social networking system.   
     
     
         19 . The apparatus as recited in  claim 17 , wherein the instructions, which when executed by the one or more processors, further cause the one or more processors to:
 pre-emptively identify one or more annotations as trending at particular time periods across different time zones.   
     
     
         20 . The apparatus as recited in  claim 17 , wherein the instructions, which when executed by the one or more processors, further cause the one or more processors to:
 maintain a whitelist of annotations that is used to select one or more annotations as trending to users in certain regions according to geolocation information.