Using crowdsourcing to improve sentiment analytics

Abstract

A computer and computer program product for managing analysis of sentiment is disclosed. A computer retrieves data used to perform the analysis of sentiment. The computer analyzes the data and the analysis of sentiment to determine if a gap exists requiring further processing to improve the analysis of sentiment. Responsive to a determination that the gap exists requiring further processing to improve the analysis of sentiment, the computer generates a task to address the gap. The computer then uses crowdsourcing to submit the generated task for processing.

What is claimed is: 
     
         1 . A data processing system for managing analysis of sentiment, the data processing system comprising:
 one or more processors, one or more memories, and one or more computer readable storage devices;   first program instructions to retrieve data used to perform the analysis of sentiment; and   second program instructions to analyze the data and the analysis of sentiment to determine if a gap exists requiring further processing to improve the analysis of sentiment, and in response, generate a task to address the gap and use crowdsourcing to submit the task for processing, wherein the first program instructions and the second program instructions are stored on at least one of the one or more computer readable storage devices for execution by at least one of the one or more processors via at least one of the one or more memories.   
     
     
         2 . The data processing system of  claim 1 , further comprising:
 third program instructions to re-calculate the analysis of sentiment based on a result of the processing of the task to address the gap, wherein the third program instructions are stored on at least one of the one or more computer readable storage devices for execution by at least one of the one or more processors via at least one of the one or more memories.   
     
     
         3 . The data processing system of  claim 1 , wherein the analysis of sentiment is for aspects of an entity corresponding to an activity and the gap requiring further processing corresponds to a topic about a particular aspect of the entity. 
     
     
         4 . The data processing system of  claim 3 , further comprising:
 third program instructions to identify the topic about the particular aspect of the entity based on sentiment information about the topic in the data, wherein the third program instructions are stored on at least one of the one or more computer readable storage devices for execution by at least one of the one or more processors via at least one of the one or more memories.   
     
     
         5 . The data processing system of  claim 4 , wherein the third program instructions to identify the topic about the particular aspect of the entity based on sentiment information about the topic in the data comprises:
 program instructions to determine a quality of sentiment information in the data for each topic in the set of topics; and   program instructions to select the topic based on the quality of sentiment information for the topic not meeting a threshold for quality of sentiment information.   
     
     
         6 . The data processing system of  claim 4 , wherein the third program instructions to identify the topic about the particular aspect of the entity based on sentiment information about the topic in the data comprises:
 program instructions to determine a distribution of positive sentiment in the data and negative sentiment in the data for each topic in the set of topics; and   program instructions to select the topic based on the distribution not meeting a threshold for distribution of positive and negative sentiment.   
     
     
         7 . The data processing system of  claim 3 , further comprising:
 third program instructions to identify the topic about the particular aspect of the entity based on an absence of information about the particular aspect of the entity in the data, wherein the third program instructions are stored on at least one of the one or more computer readable storage devices for execution by at least one of the one or more processors via at least one of the one or more memories.   
     
     
         8 . The data processing system of  claim 1 , wherein the task comprises a specification for addressing the gap based on a template corresponding to a type of gap of the gap. 
     
     
         9 . The data processing system of  claim 3 , further comprising:
 third program instructions to identify the aspects of the entity corresponding to the activity by using an ontology that describes the entities and activities associated with the activity.   
     
     
         10 . A computer program product for managing analysis of sentiment, the computer program product comprising:
 a computer readable storage device;   program instructions, stored on the computer readable storage device, for retrieving data used to perform the analysis of sentiment; and   program instructions, stored on the computer readable storage device, for analyzing the data and the analysis of sentiment to determine if a gap exists requiring further processing to improve the analysis of sentiment, and in response, generate a task to address the gap and use crowdsourcing to submit the task for processing.   
     
     
         11 . The computer program product of  claim 10 , further comprising:
 program instructions, stored on the computer readable storage device, for re-calculating the analysis of sentiment based on a result of the processing of the task to address the gap.   
     
     
         12 . The computer program product of  claim 10 , wherein the analysis of sentiment is for aspects of an entity corresponding to an activity and the gap requiring further processing corresponds to a topic about a particular aspect of the entity, and further comprising:
 program instructions, stored on the computer readable storage device, for identifying the topic about the particular aspect of the entity based on one of sentiment information about the topic in the data and an absence of information about the particular aspect of the entity in the data.   
     
     
         13 . The computer program product of  claim 12 , wherein the program instructions for identifying the topic about the particular aspect of the entity based on sentiment information about the topic in the data comprise:
 program instructions, stored on the computer readable storage device, for selecting the topic based on one of a quality of sentiment information for the topic not meeting a threshold for quality of sentiment information and a distribution of positive sentiment in the data and negative sentiment in the data not meeting a threshold for distribution of positive and negative sentiment.   
     
     
         14 . The computer program product of  claim 10 , wherein the task generated by the computer comprises a specification for addressing the gap based on a template corresponding to a type of gap of the gap.