ARCHIVES

Abstract: With the growing quality of the social networking sites, usage of informal language, short cuts & emoticons is increasing speedily. The utilization of emoticons in text so as to precise sentiments is move a challenge to the automatic sentiment analysis tools to properly account for such graphical cues for sentiment. This paper aims at demonstrating however facial gestures usually convey sentiments and the way we are able to exploit emoticons by employing a manually created emoticon sentiment lexicon and so exploitation finite state machines to seek out the polarity of the sentence or paragraph. We measure our approach on 1250 Facebook status and 2050 Facebook comments, that all contain emoticons and are manually annotated for sentiment. We have a tendency to known the foremost usually and regularly used emoticons & classified them on the idea of the sentiment they strengthen that eventually decides the polarity of the sentence. In this paper we would like to introduce a technique to perform a sentiment analysis on text-based status updates & comments, regardless all verbal info and victimisation solely emoticons to observe each positive and negative sentiments.