Abstract
Tourists satisfaction has become more and more an indicator of tourism development. Sentiment analysis on data of comments and hot discussion on travel site and Weibo can help judge real-time satisfaction trend of tourists with scenic spots according to the intensity of sentimental tendency. Considering the deficiencies in current sentiment analysis, in this paper, firstly the polarity value and strength value are used to calculate the sentimental intensity of the sentimental words. HIT-CIR Tongyici Cilin (extended) is used to expand the synonyms of the sentimental words in order to reduce the impact of words not in HowNet and some sentimental words with low frequency in the corpus. Then we improved the traditional semantic similarity method based on HowNet according to the characteristics of sentiment analysis, combining it with the method based on Point Mutual Information (PMI) and syntactic dependency relations. High accuracy is shown by the experimental results.
Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
