Extracting topics from customer review search queries

Abstract

Disclosed are various embodiments for identifying relevant topics for an item from search queries. Search queries are obtained from users to search a collection of user reviews for a specific item. Relevant topics for the specific item are identified by analyzing the queries. A user interface is generated based at least in part on at least some of the relevant topics.

Therefore, the following is claimed: 
     
         1 . A system, comprising:
 at least one computing device;   a data store comprising a plurality of search queries related to a collection of user reviews; and   at least one application executable in the at least one computing device, wherein, when executed, the at least one application causes the at least one computing device to at least:
 identify a plurality of relevant topics from the plurality of search queries associated with a specific item; and 
 generate a user interface comprising at least one of the plurality of relevant topics. 
   
     
     
         2 . The system of  claim 1 , wherein, when executed, the at least one application further causes the at least one computing device to at least:
 receive the plurality of search queries from a plurality of client devices requesting a search of the collection of user reviews; and   store the plurality of search queries in the data store.   
     
     
         3 . The system of  claim 2 , wherein the data store further comprises the collection of user reviews. 
     
     
         4 . The system of  claim 1 , wherein the plurality of relevant topics are identified based at least in part on a frequency of occurrence in the plurality of search queries. 
     
     
         5 . The system of  claim 1 , wherein identifying the plurality of relevant topics comprises decomposing the plurality of search queries into a set of terms. 
     
     
         6 . The system of  claim 5 , wherein the set of terms comprise a set of unigrams. 
     
     
         7 . The system of  claim 5 , wherein the set of terms comprise a set of bigrams. 
     
     
         8 . The system of  claim 5 , wherein identifying the plurality of relevant topics further comprises:
 determining a respective frequency of occurrence of individual terms in the set of terms; and   ranking the individual terms according to the respective frequency.   
     
     
         9 . A method, comprising:
 storing, via at least one computing device, a plurality of search queries of a collection of user reviews in a data store;   identifying, via the at least one computing device, at least one relevant topic for a specific item based at least in part on the plurality of search queries; and   generating, via the at least one computing device, a user interface based at least in part on the at least one relevant topic.   
     
     
         10 . The method of  claim 9 , further comprising receiving the plurality of search queries from a plurality of client devices requesting a search of the collection of user reviews. 
     
     
         11 . The method of  claim 9 , wherein the at least one relevant topic is identified according to a frequency of occurrence of a subset of terms within the plurality of search queries. 
     
     
         12 . The method of  claim 11 , further comprising identifying, via the at least one computing device, one or more synonymous terms of the subset of terms within the plurality of search queries based at least in part on synonym identification data, wherein the frequency of occurrence includes the one or more synonymous terms. 
     
     
         13 . The method of  claim 11 , further comprising ranking, via the at least one computing device, the subset of terms based at least in part on the frequency of occurrence. 
     
     
         14 . The method of  claim 9 , wherein the user interface comprises a corresponding selectable component for individual ones of the at least one relevant topic, and wherein the user interface is configured to present a subset of the collection of user reviews associated with a respective relevant topic in response to selection of the corresponding selectable component. 
     
     
         15 . The method of  claim 9 , wherein the user interface comprises a subset of collection reviews grouped according to the at least one relevant topic. 
     
     
         16 . A system, comprising:
 at least one computing device; and   at least one application executable in the at least one computing device, wherein, when executed, the at least one application causes the at least one computing device to at least:
 identify a relevant topic for an item from a plurality of search queries received from a plurality of clients requesting a search of a collection of user reviews; and 
 generate a user interface comprising a selectable component associated with the relevant topic. 
   
     
     
         17 . The system of  claim 16 , wherein the user interface is configured to present a subset of the collection of user reviews associated with the relevant topic in response to a selection of the selectable component. 
     
     
         18 . The system of  claim 16 , wherein the user interface comprises one or more groupings of items that are grouped according to the relevant topic. 
     
     
         19 . The system of  claim 16 , further comprising a data store, and wherein, when executed, the at least one application causes the at least one computing device to at least store the plurality of search queries in the data store. 
     
     
         20 . The system of  claim 16 , wherein the relevant topic is one of a plurality of relevant topics identified from the plurality of search queries, the user interface comprises a listing of the plurality of relevant topics for the item, and the listing comprises at least one of: a number of user reviews associated with the respective relevant topic, a rating summary for the respective relevant topic, a description of the respective relevant topic, or a component for viewing the collection of user reviews associated with the respective relevant topic.