System, method and computer program product for identifying products associated with polarized sentiments

Abstract

A content intelligence module implementing a unique polarization algorithm may operate to identify products with polarized sentiments in user-generated content. The module may be configured to, at a first computer: calculate an overall average rating on a product across segments in a dimension; for each segment in the dimension, calculate a segment average rating, a total number of ratings, a segment distance, and a weighted variation score; calculate a total weighted variation score for the dimension; analyze a distribution of overall sentiment variation in the dimension; set a polarization score for the dimension utilizing the total weighted variation score; and repeat the above steps for each feature, each product, and each dimension to produce polarization scores. Visual representations corresponding to the polarization scores may be presented through a browser application running on a second computer communicatively connected to the first computer over a network connection.

1 - 20 . (canceled) 
     
     
         21 . A method, comprising:
 receiving, by a computing system, ratings information for a product or service, wherein various elements of the ratings information are associated with users having different values for at least one user trait; and   determining, by the computing system, a polarization level for the product or service according to the at least one user trait.   
     
     
         22 . The method of  claim 21 , wherein the at least one user trait includes at least one trait selected from the group consisting of age, gender, income, and marital status. 
     
     
         23 . The method of  claim 21 , further comprising:
 the computing system receiving the various elements of ratings information from the associated users.   
     
     
         24 . The method of  claim 21 , wherein the ratings information includes star ratings. 
     
     
         25 . The method of  claim 21 , further comprising determining a targeted marketing strategy based on the polarization level. 
     
     
         26 . The method of  claim 21 , further comprising:
 the computing system determining an average rating for the users having the different values for the at least one user trait.   
     
     
         27 . The method of  claim 26 , further comprising:
 the computing system determining a plurality of average ratings for users having a corresponding plurality of values for the at least one user trait.   
     
     
         28 . The method of  claim 27 , wherein the polarization level is based on distances between the average rating for the users having the different values for the at least one user trait and the plurality of average ratings for the users having the corresponding plurality of values for the at least one user trait. 
     
     
         29 . The method of  claim 28 , further comprising:
 the computing system determining a p-value for the at least one user trait based on the distances.   
     
     
         30 . A non-transitory, computer-readable medium having instructions stored thereon that, when executed by a computing system, cause the computing system to carry out operations comprising:
 receiving ratings information for one or more products or services, wherein various elements of the ratings information are associated with users having different values for at least one characteristic; and   determining a polarization level for the one or more products or services according to the at least one characteristic.   
     
     
         31 . The medium of  claim 30 , wherein the operations further comprise:
 transmitting information indicative of the polarization level to a remote computer via a communications interface.   
     
     
         32 . The medium of  claim 30 , wherein the operations further comprise:
 in response to a total number of elements of ratings information being below a threshold, discarding the at least one user trait as a candidate for polarization.   
     
     
         33 . The medium of  claim 30 , wherein the at least one characteristic includes a first characteristic as a subset of a second characteristic. 
     
     
         34 . A system, comprising:
 at least one processor; and   a memory containing instructions executable by the at least one processor to cause the system to carry out operations comprising:
 receiving information indicative of user sentiments relating to one or more products or services, wherein various ones of the user sentiments are associated with users having different values for at least one user trait; and 
 determining a degree to which the user sentiments relating to the one or more products or services are polarized with respect to the at least one user trait. 
   
     
     
         35 . The system of  claim 34 , wherein the operations further comprise:
 determining whether or not the degree to which the user sentiments are polarized is greater than a threshold polarization level.   
     
     
         36 . The system of  claim 34 , further comprising a communications interface. 
     
     
         37 . The system of  claim 36 , wherein the operations further comprise:
 transmitting, to a remote computing system, via the communications interface, information that is usable by the remote computing system to display a graphical user interface based on the degree to which the user sentiments are polarized.   
     
     
         38 . The system of  claim 37 , wherein the graphical user interface is displayable via a browser application executable on the remote computing device. 
     
     
         39 . The system of  claim 37 , wherein the operations further comprise:
 in response to a request from the remote computing system, transmitting a filtered version of the information usable to display the graphical user interface.   
     
     
         40 . The method of  claim 37 , wherein the graphical user interface is configured to sort the one or more products or services according to the degree to which the user sentiments are polarized.