Prediction of election result by enhanced sentiment analysis on Twitter data using Word Sense Disambiguation

摘要

Sentiment analysis is the computational study of opinions, sentiments, evaluations, attitudes, views and emotions expressed in text. It refers to a classification problem where the main focus is to predict the polarity of words and then classify them into positive or negative sentiment. Sentiment analysis over Twitter offers people a fast and effective way to measure the public's feelings towards their party and politicians. The primary issues in previous sentiment analysis techniques are classification accuracy, as they incorrectly classify most of the tweets with the biasing towards the training data. In opinion texts, lexical content alone also can be misleading. Therefore, here we adopt a lexicon based sentiment analysis method, which will exploit the sense definitions, as semantic indicators of sentiment. Here we propose a novel approach for accurate sentiment classification of twitter messages using lexical resources SentiWordNet and WordNet along with Word Sense Disambiguation. Thus we applied the SentiWordNet lexical resource and Word Sense Disambiguation for finding political sentiment from real time tweets. Our method also uses a negation handling as a pre-processing step in order to achieve high accuracy.