Lexicon-Based Sentiment Analysis

Abstract

The sentiment analysis is an emerging field of natural language processing which is based on human–computer interaction, information retrieval and distilling sentiments from the ever-increasing online social data. It involves identifying the words or phrases in the underlying text express positive, negative or neutral attitude. The objective of this paper is to extract the editorial text of a leading newspaper and classify the sentiments expressed at different levels, namely paragraph level, sentence level and word level into positive, negative or neutral.