Appraisal Expression Recognition with Syntactic Path for Sentence Sentiment Classification

Experimental results show that the proposed appraisal expression based method outperforms other sentence sentiment classification methods, and a composite classifier is presented to integrate the proposed syntactic path based feature set and the common-used feature set.

Abstract

An appraisal expression is described as a collocation of the polarity word and its modified target, which can be considered as an atomic unit expressing an evaluative stance towards a target. Recognizing appraisal expressions is essential for sentence sentiment classification. However, the relevant research is far from enough. This paper proposes a novel method that uses syntactic paths to recognize appraisal expressions. Compared with the previous work, the proposed syntactic path based method has two advantages: 1) it automatically explores syntactic knowledge, and 2) it covers more syntactic relationships between polarity words and targets. Based on these, this paper applies appraisal expressions to sentence sentiment classification. Some novel features based on appraisal expressions, including semantic features, syntactic features, lexical features and polarity features, are designed to classify sentiment sentences as positive or negative. Experimental results on the camera and MP3 player domains show that the proposed appraisal expression based method outperforms other sentence sentiment classification methods. Moreover, we present a composite classifier to integrate our appraisal expression based feature set and the common-used feature set. Experimental results show that our composite classifier can get a better performance than each of them.