Predicting Consumer Intention using Logistic regression by analyzing Social media data

With the headway of web innovation and its development, there is a colossal of data out there and numerous information created for web clients. The Internet has become a stage for web based getting the hang of trading thoughts and imparting insights. Twitter, the mainstream microblogging webpage, has gotten expanding consideration as a special specialized instrument that encourages electronic verbal (e-verbal). This expansive reach of e-verbal gives purchasers colossal clout to impact brand picture and discernments regarding brand the board. We present computational models to foresee Twitter clients' mentality towards a particular brand through their own and social attributes. We likewise foresee their probability of making various moves dependent on their perspectives. This work considers the popular long range interpersonal communication site, Twitter, where individuals express contemplations and thoughts and either energetically or reluctantly uncover data about themselves, including their own advantages, different preferences. This work considers the popular long range interpersonal communication site, Twitter, where individuals express musings and thoughts and either enthusiastically or reluctantly uncover data about themselves, including their own advantages, different preferences. This work, consequently, focuses on a novel directed AI based characterization method. To accomplish high order exactness, the proposed framework presents preprocessing and the k-means grouping approach. The test results show that the proposed framework performs in a way that is better than existing methodologies regarding exactness, accuracy, review, and F-measure.