A Semantic Orientation Distinction Method for Opinion Mining in Tibetan Language

Opinion mining of social network is shown significant and indispensable status in hot topic, public-opinion poll, knowledge acquiring and recommended goods fields, which is the fundamental work for natural language processing. This paper proposes a systematic approach to determine sentiment orientation of the subjective Tibetan sentences by combining the sentiment dictionary and the statistical method, and considers different context environment to improve the algorithm adaptability. We test our approach on a bilingual corpus crawled from bilingual website and perform manual evaluation extracted from Tibetan corpora and the experimental results demonstrate good performance on Tibetan language.