Perspective data analysis and management

Abstract

A system and computer implemented method for managing perspective data is disclosed. The method may include collecting a first lot of perspective data for an item. The method may include introducing a variant feature to the item to constitute a modified item. The method may include collecting a second lot of perspective data for the modified item. The method may also include evaluating the first and second lots of perspective data to ascertain a sentiment fluctuation based on information relevant to the variant feature.

What is claimed is: 
     
         1 . A system for managing perspective data, the system comprising:
 a first collecting module configured to collect a first lot of perspective data for an item;   an introducing module configured to introduce a variant feature to the item to constitute a modified item;   a second collecting module configured to collect a second lot of perspective data for the modified item; and   an evaluating module configured to evaluate the first and second lots of perspective data to ascertain a sentiment fluctuation based on information relevant to the variant feature.   
     
     
         2 . The system of  claim 1 , wherein evaluating the first and second lots of perspective data to ascertain a sentiment fluctuation includes:
 an analyzing module configured to analyze, using a natural language processing technique configured to parse semantic and syntactic content, the first and second lots of perspective data;   a computing module configured to compute, based on semantic and syntactic content of the first and second lots of perspective data, a first sentiment score for the first lot of perspective data and a second sentiment score for the second lot of perspective data; and   a generating module configured to generate, based on comparing the first sentiment score with the second sentiment score, a first evaluation output including an assessment of the relative effect of the variant feature.   
     
     
         3 . The system of  claim 2 , wherein:
 the analyzing module is configured to analyze, using a natural language processing technique configured to parse semantic and syntactic content, the first lot of perspective data for an item; and   a first determining module is configured to determine that a first element of the first lot of perspective data for the item is characterized by a sentiment score above a sentiment threshold.   
     
     
         4 . The system of  claim 2 , wherein:
 the analyzing module is configured to analyze, using a natural language processing technique configured to parse semantic and syntactic content, the first lot of perspective data for an item; and   a second determining module is configured to determine that a second element of the first lot of perspective data for the item is characterized by a sentiment score below a sentiment threshold.   
     
     
         5 . The system of  claim 2 , wherein:
 the analyzing module is configured to analyze, using a natural language processing technique configured to parse semantic and syntactic content, the first lot of perspective data;   an extracting module is configured to extract, in response to analyzing the first lot of perspective data, revision candidate data for the item; and   a third determining module is configured to determine, based on the revision candidate data for the item, a variant feature for the item.   
     
     
         6 . A computer program product comprising a computer readable storage medium having a computer readable program stored therein, wherein the computer readable program, when executed on a first computing device, causes the first computing device to:
 collect a first lot of perspective data for an item;   introduce a variant feature to the item to constitute a modified item;   collect a second lot of perspective data for the modified item; and   evaluate the first and second lots of perspective data to ascertain a sentiment fluctuation based on information relevant to the variant feature.   
     
     
         7 . The computer program product of  claim 6 , further comprising computer readable program code configured to:
 analyze, using a natural language processing technique configured to parse semantic and syntactic content, the first and second lots of perspective data;   compute, based on semantic and syntactic content of the first and second lots of perspective data, a first sentiment score for the first lot of perspective data and a second sentiment score for the second lot of perspective data; and   generate, based on comparing the first sentiment score with the second sentiment score, a first evaluation output including an assessment of the relative effect of the variant feature.   
     
     
         8 . The computer program product of  claim 7 , wherein the variant feature includes a first variable element and a second variable element, the first and second variable elements corresponding to a predetermined fixed criterion. 
     
     
         9 . The computer program product of  claim 8 , further comprising computer readable program code configured to:
 instantiate the first variable element for a first item and the second variable element for a second item;   collect a third lot of perspective data for the first item and a fourth lot of perspective data for the second item;   analyze, using a natural language processing technique configured to parse semantic and syntactic content, the third and fourth lots of perspective data;   compute, based on semantic and syntactic content of the third and fourth lots of perspective data, a third sentiment score for the third lot of perspective data and a fourth sentiment score for the fourth lot of perspective data; and   generate, based on comparing the third sentiment score with the fourth sentiment score, an second evaluation output including an assessment of the relative effect of the first variable element and the second variable element.   
     
     
         10 . The computer program product of  claim 6 , further comprising computer readable program code configured to:
 collect the first lot of perspective data for the item from a first community of users;   collect, the second lot of perspective data for the modified item from a second community of users;   determine, by comparing the first community of users with the second community of users, a sub-community of users included in both the first community of users and the second community of users;   collect a subset of perspective data from the sub-community of users; and   assign, to the subset of perspective data collected from the sub-community of users, a weighting value.