Using Morphological and Syntactic Structures for Chinese Opinion Analysis

Proceedings of the 2009 Conference on Empirical Methods in Natural Language Processing, pages 1260–1269, Singapore, 6-7 August 2009. c⃝2009 ACL and AFNLP Using Morphological and Syntactic Structures for Chinese Opinion Analysis Lun-Wei Ku Ting-Hao Huang Hsin-Hsi Chen Department of Computer Science and Information Engineering National Taiwan University No. 1, Sec. 4, Roosevelt Road, Taipei, 10617 Taiwan {lwku,thhuang}@nlg.csie.ntu.edu.tw;hhchen@ntu.edu.tw Abstract This paper employs morphological struc- tures and relations between sentence seg- ments for opinion analysis on words and sentences. Chinese words are classified into eight morphological types by two proposed classifiers, CRF classifier and SVM classifier. Experiments show that the injection of morphological information improves the performance of the word po- larity detection. To utilize syntactic struc- tures, we annotate structural trios to repre- sent relations between sentence segments. Experiments show that considering struc- tural trios is useful for sentence opinion analysis. The best f-score achieves 0.77 for opinion word extraction, 0.62 for opin- ion word polarity detection, 0.80 for opin- ion sentence extraction, and 0.54 for opin- ion sentence polarity detection. 1 Introduction Sentiment analysis has attracted much attention in recent years because a large scale of subjective information is disseminated through various plat- forms on the web. Sentiment information can be applied to a wide variety of fields, including product recommendation, review summarization, public polling, and so on. Opinion dictionaries are important resources for identifying subjective information. Several approaches were proposed to collect such re- sources. Wiebe (2000) learned subjective adjec- tives from corpora. Takamura et al. (2005) ex- tracted semantic orientations of words. Ku et al. (2007) measured sentiment degrees of Chinese words by averaging the sentiment scores of the composing characters. When the opinion words are available, the polarities of sentences and documents can be determined by them. Riloff and Wiebe (2003) learned the extraction patterns for subjective expressions. Kim and Hovy (2004) found the polarity of subjective expressions. Pang et al. (2002) and Dave et al. (2003) ex- plored various techniques at document level. Morphological information has been widely used in classifying words, telling the meanings, and doing other in-depth analysis (Tzeng and Chen, 2002). However, morphological informa- tion was seldom applied either in Chinese opin- ion extraction, or in solving the coverage prob- lem of opinion dictionary. Instead of bag-of- characters approach (Ku et al., 2007), this paper employs morphological structures of words to extract opinion words. Relations between sentence segments are also defined by linguistics in the Chinese language. These are similar to morphological structures between Chinese characters. Based on parsing trees of sentences, we identify these relations and utilize them for opinion analysis on sentences. As the experimental corpus, some researchers managed to generate annotated materials and gold standards under many constraints. Ku set a standard for generating final answers from anno- tations of multiple annotators (Ku et al., 2007), and Somasundaran annotated discourse informa- tion from meeting dialogs to train a sentiment model (Somasundaran et al., 2007). For multi- lingual issues, researchers concerned mainly about the applicability of corpus and algorithms from the …

Content truncated to 500 words