A Survey on Various Sentiment Analysis Approaches and Its Challenges

Abstract

Sentiment analysis is a broad research area in academic as well as business field. The term sentiment refers to the feelings or opinion of the person towards some particular domain. Hence it is also known as opinion mining. It leads to the subjective impressions towards the domain, not facts. It can be expressed in terms of polarity, reviews or previously by thumbs up and down to denote positive and negative sentiments respectively. Sentiments can be analyzed using NLP, statistics or machine learning techniques. Sentiment analysis may ask questions regarding “customer satisfaction and dissatisfaction, “public opinion towards new iPhone series launched” etc. In real world, public or consumer opinions about some product or brand are very important for its sell. Hence sentiment analysis is a very important research area for real life applications i.e. decision making.

However various methods were introduced for performing sentiment analysis, still that are not efficient in extracting the sentiment features from the given content of text. Naïve Bayes, Support Vector Machine, Maximum Entropy are the machine learning algorithms used for sentiment analysis which has only a limited sentiment classification category ranging between positive and negative. Especially supervised and unsupervised algorithms have only limited accuracy in handling polarity shift and binary classification problem. Even though the advancement in sentiment Analysis technique there are various issues still to be noticed and make the analysis not accurately and efficiently. So this paper presents the survey on various sentiment Analysis methodologies and approaches in detailed. This will be helpful to earn clear knowledge about sentiment analysis methodologies. This Paper describes different applications of sentiment analysis, techniques and challenges of sentiment analysis.

Keywords: Sentiment Analysis, Decision Making, Opinion Mining, Machine Learning, NLP