||With the booming of social media, users generate a large number of texts, such as tweets, blogs, and comments, which are full of potential sentiment. Sentiment analysis aims to obtain people’s feelings and opinions from textual data. The most popular approach for sentiment analysis is to consult the sentiment lexicon. However, due to the diversity of the domain and the prior knowledge, the domain-specific sentiment lexicon plays an important role in sentiment analysis.|
Chinese sentiment lexicon resources, when compared to their English counterparts, are still limited and mostly for general-purpose. Therefore, this research proposes techniques to construct a domain-specific sentiment lexicon in order to obtain a more accurate sentiment analysis. In this thesis, we analyze 1,294,141 hotel reviews crawled from Booking.com, utilizing the vector space model to obtain the semantic meanings between words, and predicting the sentiment scores of the words. Finally, we combine the context and sentiment information with label propagation method to construct a domain-specific sentiment lexicon automatically in hotel domain. The method we proposed achieves 83% precision.