Ideogram Based Chinese Sentiment Word Orientation Computation

Abstract

This paper presents a novel algorithm to compute sentiment orientation of Chinese sentiment word. The algorithm uses ideograms which are a distinguishing feature of Chinese language. The proposed algorithm can be applied to any sentiment classification scheme. To compute a word's sentiment orientation using the proposed algorithm, only the word itself and a precomputed character ontology is required, rather than a corpus. The influence of three parameters over the algorithm performance is analyzed and verified by experiment. Experiment also shows that proposed algorithm achieves an F Measure of 85.02% outperforming existing ideogram based algorithm.