Publication

Abstract : With the advent of technological advancements in the recent times, people, and Internet have become inseparable. People belonging to all categories access the internet. Micro blogs from twitter has real time information as on how the general audience feel. Extracting this information and finding out the intent of the general audience can be of great help for business and political organizations. Sentimental analysis is a sub-branch of Natural Language Processing which intends in finding out the polarity of contextual information. Tamil Tweets are collected and they are being manually tagged to develop a system that can identify the polarity. We have used word embedding and unsupervised methodology to identify the polarity of Tamil tweets. We have also evaluated our system using SAIL-2015 data set available for Tamil language and we were able to obtain state-of-art accuracy. © International Science Press.