Thailand -- Tourism and Conflict: Modeling Sentiment from Twitter Tweets Using Naïve Bayes and Unsupervised Artificial Neural Nets

In this paper we mine over 80 million twitter micro logs in order to explore whether data from this social media initiative can be used to identify sentiment about tourism and Thailand amid the unrest in that country during the early part of 2010 and further whether analysis of tweets can be used to discern the effect of that unrest on Phuket's tourism environment. It is proposed that this analysis can provide measurable insights through summarization, keyword analysis and clustering. We measure sentiment using a binary choice keyword algorithm. A multi-knowledge based approach is proposed using, Self-Organizing Maps along with sentiment polarity in order to model sentiment. We develop a visual model to express a sentiment concept vocabulary and then apply this model to maximums and minimums in the time series sentiment data. The results show actionable knowledge can be extracted in real time.