Medical Analysis and Visualisation of Diseases using Tweet data Sivasankari S.*, Kavitha M.**, Saranya G.*** Department of Information Technology, SRM University *Corresponding Author E-mail: sivasankari.s@ktr.srmuniv.ac.in
**E-mail: kavitha.mu@ktr.srmuniv.ac.in
***E-mail: saranya.g@ktr.srmuniv.ac.in
Online published on 26 March, 2018. Abstract In this technological era, social media is used as an expressing platform that ease respective feelings outto public, monitoring of social media is useful for improving the communication policies and around the world aiming to preserve knowledge and help government and CDC's. The data obtained from online social media provides the depth of the opinions among the public, which enables CDC's and health institutes to respond immediately and precisely to public concerns. Initially comparison among all sorts of social media was analysed with respect to stability and relativity where twitter was considered to be the most stabilized social media platform over other option's with` micro-blogging service which includes millions of users to send and read tweets. Tweets are 140-character messages used to express their opinion on issue whether it's political, economical, social etc. With the service of more than million's registered users and useful information about news and geopolitical events it helps to understand users perspectives and behaviour of user. In this paper, use of information embedded in the Twitter stream to track the rapidly-evolving public sentiment with respect epidermal and valuating over tableau also for the classification method for tweets entered by user. The result include stabilized classificationand sentiment analysis along withplotting of graph using tableau determining whether the corresponding tweet with respect to epidermal is neutral, positive or negative depending upon the values also use of Naive Bayes for the classifying the tweet entered by the user. Hence our movie includes data from twitter that is raw into output that is used for valuation, classification and to analyze the sentiment of tweet with respect to epidemic Top Keywords Twitter API, Tableau, Tweepy, Python, Textblob, Naive Bayes, Keyword, NLTK package, Spyder. Top |