Abstract: Social Media sites like twitter have billions of peopleshare their opinions day by day as tweets. As tweet is characteristic short andbasic way of human emotions. So in this paper we focused on sentiment analysisof Twitter data. Most of Twitter's existing sentiment analysis solutionsbasically consider only the textual information of Twitter messages and strivesto work well in the face of short and ambiguous Twitter messages. Recentstudies show that patterns of spreading feelings on Twitter have closerelationships with the polarities of Twitter messages. In this paper focus onhow to combine the textual information of Twitter messages and sentimentdissemination models to get a better performance of sentiment analysis inTwitter data. To this end, proposed system first analyses the diffusion offeelings by studying a phenomenon called inversion of feelings and find someinteresting properties of the reversal of feelings. Therefore we consider theinterrelations between the textual information of Twitter messages and thepatterns of diffusion of feelings, and propose random forest machine learningto predict the polarities of the feelings expressed in Twitter messages. As faras we know, this work is the first to use sentiment dissemination models toimprove Twitter's sentiment analysis. Numerous experiments in the real-worlddataset show that, compared to state-of-the-art text-based analysis algorithms.
Keywords: TextMining, Machine learning, Sentiment analysis, sentiment diffusion, Twitter.