Polarity shift detection approaches in sentiment analysis: A survey

Abstract

Sentiment analysis is a process of identifying and categorizing opinions expressed in a piece of text. It classifies the text into positive, negative or neutral. Lexicon-based and Supervised Machine Learning-based are the two main approaches in sentiment analysis. Bag-of-words model is used to represent the text as a vector of independent words and machine learning algorithms are used for classification. Polarity shift is the major problem in the Bag-of-words model. Polarity shift is a sentiment classification problem. It can reverse the sentiment polarity of the text. Classification performance of machine learning based systems can get affected by polarity shift. Negation is the type of polarity shift. Negative words can change the polarity of the sentimental words. Polarity shift detection methods are used to detect the polarity shift in the sentences. It helps to improve the performance of machine learning classification algorithms. Natural Language Processing can be used for feature extraction and classification. Sentiment analysis uses Natural Language Processing for extraction of opinion words from the text. Sentiment analysis plays an important role in identifying the opinion of the people about a specific topic or entity. This survey paper reviews the sentiment analysis approaches and highlight the need to address polarity shift problem in sentiment analysis. The different polarity shift detection techniques are discussed in this paper.