查看文章

Twitter is a microblogging site where clients read and compose short messages on different points each day. Political investigation using social media is getting the consideration of numerous scientists to understand the general assessment and pattern, particularly at the time of elections. In this paper, a proficient approach with respect to fuzzy rules to dissect the general assessment and further anticipated poll results. The system contains mainly three modules in particular Data extraction, Pre-processing and characterization of sentiment. The initial two stages have undertakings, namely social media information extraction and data pre-processing in order to, expel all Uniform Resource Locator (URL) frame separated tweet. The last stage is a grouping stage where a strategy called Adaptive Neuro-Fuzzy Inference System (ANFIS) where the fuzzy based ontology is designed by actualizing Non-Linear Support Vector Machine (SVM) classifier analysis to improve the fuzzy principles. The result showed that the ANFIS-NonLinearSVM based Sentiment analysis of social network data is less complex and gives the high rate of accuracy compared to the existing methodologies.