Indian Journal of Education and Information Management

Abstract

Objective: To extract and categorize aspects based on Conditional Random Field to improve the sentiment classification accuracy and to determine the optimal time boundary for temporal sentiment analysis. Methods: There are several methods developed for sentiment analysis. In order to improve the sentiment classification accuracy and to identify sentiment variation Conditional Random Field model, firefly algorithm are proposed. Findings: Sentiment analysis is a part of data mining technique where we know users attitude, judgment, opinion and emotions about a particular product or event or a system. In an existing sentiment analysis technique the aspect terms were extracted using bag words. Then the polarities of aspects were determined through the Stanford parser; and lexicon based approach is used to classify the sentiments. In this approach spatial relationship among the aspect terms were ignored and it fails to concentrate on the temporal trends of sentiments. Application/improvements: To increase sentiment classification accuracy and to identify the sentiment variation conditional random field and firefly are proposed. 
Keywords: Conditional Random Field, sentiment analysis, temporal sentiment analysis, firefly