Sentiment analysis for the news data based on the social media

Now social Data are increases very fast, in every area social data play an important role in every angle, social media big data mining area welcomed by researchers from both government, academic and industry. A computing sentiment of news data is a significant component of the social media big data. The computing sentiment of news information may be a major factor of the social media massive information. In current web word range of user use social media and social network to browse and read news connected information. Everyday range of issue area unit occurring and social media influence the news associated with this news. Existing sentiment computing ways area unit primarily supported the feeling wordbook or supervised ways, that aren't climbable to the social media massive information. As a result of once bid information suggests that information size increases this methodology result on potency. Therefore we tend to propose a replacement methodology to try and do the sentiment analysis for news data a lot of specially, supported the social media information and social news (i.e.text and emotions text) of a happening, a Levenshtein algorithm is made to together categorical its linguistics and emotions, that lays the muse for the happening sentiment analysis. The word feeling computation algorithmic rule is planned to get the beginning word feeling that area unit more refined through the quality emotion wordbook. With the word emotions in hand, we are able to reason each sentence sentiments. The proposed method uses Naïve Bayes and Levenshtein algorithm to determine the emotion into different categories from given social media news data. This method provides the excellent performance for real time news data on social media and also provides the better result in terms of accuracy.