Sentiment based analysis of social media data using fuzzy-rough set classifier for the prediction of the presidential election

Abstract

As an interdisciplinary research field, sentiment analysis is one of the momentous applications in Natural Language Processing, for quantifying the emotional value in vast data in the form of text available in social media networks to gain an understanding of the attitudes, opinions, and emotions expressed. There is a great deal of literature on the various ways to address sentiment analysis with social media and this project focuses on Machine Learning techniques with twitter data analysis. Special attention is drawn towards the classifiers based on the Fuzzy Set and Rough Set approach which are two powerful mathematical components of the computational intelligence with its new dimension involved in the field of sentiment analysis. However, there is a minimal number of review papers discussed about rough-fuzzy classifier involvement in sentiment analysis and there is a plethora of work that must be done with text mining in natural language processing. Sentiment Analysis, also called opinion mining, which is the field of computational study that analyzes people’s opinions, attitudes and emotions toward an entity. Decision-making behavior in an online community is predominant because many individuals now use community-based web services thus the opinions of others are readily available in online environments where people often rely on other individuals’ decisions for social validation to make their own. The power of Social Media Websites is rampant and growing a plethora of information and data convoluted with varying interests, opinions, and emotions with human generated baselines. The widespread use of the above media encourages positive and negative attitudes about people, organizations, places, events, and ideas. Sentiment Analysis, also called opinion mining, which is the field of computational study that analyzes people’s opinions, attitudes and emotions toward an entity. The mission of this project is to develop a sentiment based classifier using machine learning and fuzzy-rough set theory. Further, it carries automatic sentiment classification with twitter corpus collected during a certain time period with regard to the case study for the prediction of results at the presidential election 2019, Sri Lanka. The fuzzy rough classifier is developed using the Fuzzy Rough Nearest Neighbor algorithm. The performance of the classifier was evaluated with precision, recall, accuracy and F1 score against the Multinomial Naive Bayes and Support Vector Mechanism. The accuracy of the fuzzy rough set based classifier is high compared to other classifiers. The actual results of the presidential election of 2019 are tally with the predicted results of the classifier. Therefore, the current state of art for the prediction of political sentiment with microblogging which is probable with the social media data as witnessed with this case study and this can be used in the other cases as well.