Chinese subjectivity detection using a sentiment density-based naive Bayesian classifier

Xin Wang, Guohong Fu

Abstract: Subjectivity detection plays an important role in many opinion mining systems such as sentiment classifiers and opinion summarization systems. In this paper we present a sentiment density-based naive Bayesian classifier for Chinese subjectivity classification. In this study, we first employ the chi-square technique to automatically extract subjective cues from training data. To represent sentence subjectivity, we calculate sentiment density using the extracted subjective cues and thus construct a set of sentiment density subintervals. Finally, we implement a naive Bayesian classifier with sentiment density subintervals as features for subjectivity classification. We also conduct several experiments on the NTCIR-6 Chinese opinion data, showing the feasibility of the proposed method.