Sentiment analysis for bank service quality: A rule-based classifier

Abstract

The paper considers the analysis of the subjective information from user-generated content. The purpose of this research is to develop a rule-based classifier for the sentiment analysis within the bank service quality domain. Our sentiment lexicon includes 286 positive and 385 negative words. Besides, three more lexicon classes are added; they are required to apply the rule-based algorithm. To test the algorithm, 200 reviews in Russian are analyzed. The experiment demonstrates that the efficiency of the rule-based classifier is higher as compared to the Naïve Bayes classifier. It is determined that the system generally detects positive reviews better than negative ones.