Abstract: This paper presents an extraction method based on pattern matching and semi-supervised learning on product comment targets. This method gets seed rules set through making statistics on a large number samples to extract the effective evaluation sentences, and extracts accurate opinion targets through the combination of syntactic structures and the Part of Speech(POS)-distance Correlation Algorithm(PCA). Seed rules and opinion targets are stored in the corresponding pattern libraries, the training and expansion of the learning of rules and opinion targets is carried out by the semi-supervised learning methods and rules of dynamic replacement. Experimental results exhibit measurable improvement, and prove the feasibility of this method.
combination of Part of Speech(POS),
Part of Speech(POS)-distance Correlation Algorithm (PCA),
effective evaluation sentence