Expert Detection in Social Networks

Abstract

Aspects of the technology described herein detect experts in social networks. Experts may be identified within social networks using social network data. A collection of topics may be compiled based on search engine behavioral data. A combination of the social network data and search engine behavioral data is utilized to score each topic within potential topics for a user. When a topic score is over a predetermined threshold, a user may be classified as an expert for that topic. Expert search interfaces may be generated for use in browsing or searching for experts within a topic.

The invention claimed is: 
     
         1 . An expert detection system comprising:
 at least one processor; and   memory having computer-executable instructions stored thereon which, when executed by the at least one processor, cause the at least one processor to:
 identify a user account within a social network; 
 determine whether the user account should be designated as an expert on one or more topics based on both social network data and search engine data; 
 assign a score to each topic of the one or more topics based on the social network data and search engine data; and 
 designate the user as an expert when the score for a topic is higher than a predetermined threshold. 
   
     
     
         2 . The system of  claim 1 , wherein the search engine data includes click-through data. 
     
     
         3 . The system of  claim 1 , wherein the social network data includes activity of the user account for a predetermined period of time. 
     
     
         4 . The system of  claim 1 , wherein the search engine data includes one or more terms from query logs. 
     
     
         5 . The system of  claim 1 , wherein the processor is further configured to identify a user account type of the user account, wherein the user account type is a person-type or a company-type. 
     
     
         6 . The system of  claim 5 , wherein the user account type is identified utilizing one or more type-features including pronoun usage within the user account. 
     
     
         7 . The system of  claim 1 , wherein the one or more topics are extracted from the user account upon being identified as potential areas of expertise. 
     
     
         8 . The system of  claim 7 , wherein the one or more topics are mapped to a group of related topics. 
     
     
         9 . A method for detecting topical experts, the method comprising:
 identifying a user account within a social network;   determining whether the user account should be designated as an expert on one or more topics based on both social network data and search engine data;   assigning a score to each topic of the one or more topics based on the social network data and search engine data; and   designating the user as an expert when the score for a topic is higher than a predetermined threshold.   
     
     
         10 . The method of  claim 9 , wherein the search engine data includes click-through data. 
     
     
         11 . The method of  claim 9 , wherein the search engine data includes one or more terms from query logs. 
     
     
         12 . The method of  claim 9 , wherein the social network data includes activity of the user account for a predetermined period of time. 
     
     
         13 . The method of  claim 9 , further comprising identifying a user account type of the user account, wherein the user account type is a person-type or a company-type based on evaluation of one or more type-features including pronoun usage. 
     
     
         14 . The method of  claim 9 , further comprising extracting the one or more topics from the user account upon being identified as potential areas of expertise. 
     
     
         15 . The method of  claim 14 , wherein the one or more topics are mapped to a group of related topics. 
     
     
         16 . A method for detecting topical experts, the method comprising:
 identifying a user account within a social network;   monitoring the user account for a first predetermined period of time to identify social network data for the user account;   extracting one or more topics from the user account upon identifying the one or more topics as potential areas of expertise;   identifying search engine data for a second predetermined period of time including query log data and behavioral data;   identifying a collection of linked topics from the query log data and the behavioral data, wherein the linked topics are indicated as related to the one or more topics upon evaluation of one or more of the behavioral data and the query log data;   augmenting the one or more topics with the collection of linked topics;   assigning a score to each of the one or more topics; and   designating the user account as an expert on a topic when the score is higher than a predetermined threshold.   
     
     
         17 . The system of  claim 16 , wherein the social network data includes activity of the user account during the predetermined period of time. 
     
     
         18 . The system of  claim 16 , wherein the behavioral data includes click-through data. 
     
     
         19 . The system of  claim 16 , further comprising identifying a user account type of the user account, wherein the user account type is a person-type or a company-type based on evaluation of one or more type-features including pronoun usage. 
     
     
         20 . The system of  claim 16 , wherein the one or more topics are identified as potential areas of expertise using social network data.