Generation of nickname dictionary

Abstract

Methods, apparatuses and systems for generating a name-word dictionary that includes associations between names of users and candidate words (e.g., nicknames) based on statistical analysis of user communications observed at a network communications facility, such as a social network system, an email provider and the like.

What is claimed is: 
     
         1 . A method comprising:
 accessing, by one or more computing devices, one or more messages, each message being directed to a target user and comprising one or more words, each target user being associated with one or more names;   identifying, by the one or more computing devices, one or more name-word associations between at least one name associated with at least one of the target users and one or more words identified in the messages, the identifying being based on statistics comprising a number of occurrences of a candidate word in messages directed to target users sharing a same name; and   determining, by the one or more computing devices, a confidence score for each of the one or more name-word associations.   
     
     
         2 . The method of  claim 1 , the identifying being based on analysis of statistical attribute data relevant to associations between the names and the words in the messages. 
     
     
         3 . The method of  claim 2 , wherein the analysis comprises application of one or more thresholds to the statistical attribute data. 
     
     
         4 . The method of  claim 2 , wherein the analysis comprises application of the statistical attribute data to a statistical analysis module to identify, for each name-word association, a confidence of the association between the name and the words identified in the messages. 
     
     
         5 . The method of  claim 4 , wherein the statistical analysis module implements Fisher's exact test. 
     
     
         6 . The method of  claim 1 , the statistics further comprising a number of occurrences of words other than the candidate word in the messages directed to the target users sharing the same name. 
     
     
         7 . The method of  claim 1 , wherein the messages are of one message type. 
     
     
         8 . The method of  claim 7 , wherein the message type corresponds to birthdays of the target users of the respective messages, wall posts on profile pages of a social network system, or electronic mail messages directed to target users associated with a social network system. 
     
     
         9 . The method of  claim 7 , wherein the message type corresponds to a high density of name use in the messages. 
     
     
         10 . One or more computer-readable non-transitory storage media embodying software that is operable when executed to:
 access, by one or more computing devices, one or more messages, each message being directed to a target user and comprising one or more words, each target user being associated with one or more names;   identify, by the one or more computing devices, one or more name-word associations between at least one name associated with at least one of the target users and one or more words identified in the messages, the identifying being based on statistics comprising a number of occurrences of a candidate word in messages directed to target users sharing a same name; and   determine, by the one or more computing devices, a confidence score for each of the one or more name-word associations.   
     
     
         11 . The media of  claim 10 , the identifying being based on analysis of statistical attribute data relevant to associations between the names and the words in the messages. 
     
     
         12 . The media of  claim 11 , wherein the analysis comprises application of one or more thresholds to the statistical attribute data. 
     
     
         13 . The media of  claim 11 , wherein the analysis comprises application of the statistical attribute data to a statistical analysis module to identify, for each name-word association, a confidence of the association between the name and the words identified in the messages. 
     
     
         14 . The media of  claim 13 , wherein the statistical analysis module implements Fisher's exact test. 
     
     
         15 . A system comprising:
 one or more processors; and   a memory coupled to the processors comprising instructions executable by the processors, the processors being operable when executing the instructions to:
 access one or more messages, each message being directed to a target user and comprising one or more words, each target user being associated with one or more names; 
 identify one or more name-word associations between at least one name associated with at least one of the target users and one or more words identified in the messages, the identifying being based on statistics comprising a number of occurrences of a candidate word in messages directed to target users sharing a same name; and 
 determine a confidence score for each of the one or more name-word associations. 
   
     
     
         16 . The system of  claim 15 , the statistics further comprising a number of occurrences of words other than the candidate word in the messages directed to the target users sharing the same name. 
     
     
         17 . The system of  claim 15 , wherein the messages are of one message type. 
     
     
         18 . The system of  claim 17 , wherein the message type corresponds to birthdays of the target users of the respective messages, wall posts on profile pages of a social network system, or electronic mail messages directed to target users associated with a social network system. 
     
     
         19 . The system of  claim 17 , wherein the message type corresponds to a high density of name use in the messages. 
     
     
         20 . The system of  claim 15 , the identification being based on analysis of statistical attribute data relevant to associations between the names and the words in the messages, wherein one or more thresholds are applied to the statistical attribute data.