Using Morphological and Syntactic Structures for Chinese Opinion Analysis

This paper employs morphological structures and relations between sentence segments 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 polarity detection. To utilize syntactic structures, we annotate structural trios to represent relations between sentence segments. Experiments show that considering structural trios is useful for sentence opinion analysis. The best f-score achieves 0.77 for opinion word extraction, 0.62 for opinion word polarity detection, 0.80 for opinion sentence extraction, and 0.54 for opinion sentence polarity detection.

• Type: Journal
• Year: 2009
• Where: EMNLP
• Authors: Lun-Wei Ku, Ting-Hao Huang, Hsin-Hsi Chen
• Keywords: EMNLP 2009, Natural Language Processing, Polarity Detection, Sentence Segments, Word Polarity Detection