Emotion Estimation of Comments on Web News by SVM and Naive Bayes Based Classifiers
Tajima Yasuhiro, Genichiro Kikui · 2014
Social communication tools such as Twitter or Facebook spread the web service ability. Using their APIs, we can gather many users’ comments easily. Such comments are usually short sentences but they also have many emotional comments. In this paper, we propose emotion estimation methods for multilabeled short comments of web news. Our methods can be applied to sentiment analysis and opinion mining. At first, we show the performance evaluation of a naive Bayes classifier and an SVM classifier. Then, we propose two improved methods. The first is an improved naive Bayes method which classifies each emotion label into two opposite emotions and uses their weights. We call this the weighting method. The second method consists of two stages of classifiers. The first stage distinguishes these oppositely classes, and the second stage selects one emotion from the opposite emotions. From our evaluation, we conclude that the weighting method is better among the naive Bayes classifiers and its performance is as good as SVM’s.