Systems and Methods for Clustering User Reviews

Abstract

Systems and methods for clustering user reviews are disclosed in which a plurality of user reviews are extracted from electronic documents. The electronic documents contain user reviews of a plurality of items of interest. A set of user reviews is identified in the plurality of user reviews as being associated with the same item of interest in the plurality of items of interest. Item identifying information included in the electronic documents is used for this identification. The set of user reviews is then associated with the same item of interest. Examples of item identifying information include unique product identifiers, brand names, model numbers, and category information. In some instances, the item identifying information is extracted from metadata included in the electronic document. In some instances, the electronic documents are obtained from e-commerce websites or product-review websites.

What is claimed is: 
     
         1 . A method comprising:
 at a computer system:
 extracting a plurality of user reviews from one or more electronic documents, wherein the electronic documents contain user reviews of a plurality of items of interest; 
 identifying a set of user reviews in the plurality of user reviews as being associated with the same item of interest in the plurality of items of interest, using item identifying information included in the one or more electronic documents; and 
 associating the set of user reviews with the same item of interest. 
   
     
     
         2 . The method of  claim 1 , wherein the item identifying information includes one of: a unique product identifier, brand name, model number, or category information. 
     
     
         3 . The method of  claim 1 , wherein the item identifying information is extracted from metadata included in the one or more electronic documents. 
     
     
         4 . The method of  claim 1 , wherein the item identifying information is extracted from a URL associated with an electronic document in the one or more electronic documents. 
     
     
         5 . The method of  claim 1 , wherein the one or more electronic documents are obtained from e-commerce websites or product-review websites. 
     
     
         6 . The method of  claim 1 , further comprising:
 in response to a user search,
 formatting for display a snippet of a user review in the set of user reviews. 
   
     
     
         7 . The method of  claim 1 , further comprising:
 in response to a user search,
 formatting for display a representation of a count of user reviews included in the set of user reviews. 
   
     
     
         8 . The method of  claim 1 , further comprising:
 in response to a user search,
 formatting for display one or more user reviews, in the plurality of user reviews, associated with the same review source. 
   
     
     
         9 . A system comprising:
 one or more processors;   memory; and   one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, the one or more programs including instructions for:
 extracting a plurality of user reviews from one or more electronic documents, wherein the electronic documents contain user reviews of a plurality of items of interest; 
 identifying a set of user reviews in the plurality of user reviews as being associated with the same item of interest in the plurality of items of interest, using item identifying information included in the one or more electronic documents; and 
 associating the set of user reviews with the same item of interest. 
   
     
     
         10 . The system of  claim 9 , wherein the item identifying information includes one of: a unique product identifier, brand name, model number, or category information. 
     
     
         11 . The system of  claim 9 , wherein the item identifying information is extracted from metadata included in the one or more electronic documents. 
     
     
         12 . The system of  claim 9 , wherein the item identifying information is extracted from a URL associated with an electronic document in the one or more electronic documents. 
     
     
         13 . The system of  claim 9 , wherein the one or more electronic documents are obtained from e-commerce websites or product-review websites. 
     
     
         14 . The system of  claim 9 , wherein the one or more programs further comprise instructions for:
 in response to a user search,
 formatting for display a snippet of a user review in the set of user reviews. 
   
     
     
         15 . The system of  claim 9 , wherein the one or more programs further comprise instructions for:
 in response to a user search,
 formatting for display a representation of a count of user reviews in the set of user reviews. 
   
     
     
         16 . The system of  claim 9 , wherein the one or more programs further comprise instructions for:
 in response to a user search,
 formatting for display one or more user reviews, in the plurality of user reviews, associated with the same review source. 
   
     
     
         17 . A non-transitory computer readable storage medium having stored thereon one or more programs, wherein the one or more programs including instructions for:
 extracting a plurality of user reviews from one or more electronic documents, wherein the electronic documents contain user reviews of a plurality of items of interest;   identifying a set of user reviews in the plurality of user reviews as being associated with the same item of interest in the plurality of items of interest, using item identifying information included in the one or more electronic documents; and   associating the set of user reviews with the same item of interest.   
     
     
         18 . The non-transitory computer readable storage medium of  claim 17 , wherein the item identifying information includes one of: a unique product identifier, brand name, model number, or category information. 
     
     
         19 . The non-transitory computer readable storage medium of  claim 17 , wherein the item identifying information is extracted from metadata included in the one or more electronic documents. 
     
     
         20 . The non-transitory computer readable storage medium of  claim 17 , wherein the one or more electronic documents are obtained from e-commerce websites or product-review websites.