A sentiment analysis approach based on exploiting Chinese linguistic features and classification

This paper proposes a novel approach to exploiting linguistic features and SVMperf algorithm based semantic classification, and this approach is applied into sentiment analysis. It uses the dependency relationship to do the linguistic feature extraction. This paper adopts chi(2) (chi-square) and pointwise mutual information (PMI) metrics for feature selection. Furthermore, as for the approach on sentiment analysis, this paper uses the SVMperf algorithm to implement the alternative structural formulation of the SVM optimisation problem for classification. E-commerce datasets are used to evaluate the experiment performance. Experiment results show the feasibility of the approach. Existing problems and further works are also presented.