Sentiment Analysis on Twitter using Multiple Emoji and Sarcasm Detection

Millions of users share opinions on different aspects of life every day on social media. User can give their gist regarding the recent events in their surrounding and give suggestions to improve surroundings in text-based format while conveying their emotions which they are not able to easily verbalize using emoticons and Emoji. Spurred by that growth, companies and media organizations are increasingly seeking way to mine information. For better understanding of people’s opinion, it is important to analyze different semiotics as well as sentence. We propose a method Multiple Emoji Identification and Sarcasm Detection (MEISD) to provide an approach to determine sentiment score of a tweet with semiotics with multi-dimensional sentiment analysis and sarcasm detection. We have created semiotic dictionary which have sentiment score for each semiotic with sentiment expressed by it most frequently. Also, we identify multiple emoji on tweet that will helpful in sentiment analysis and work when user use multiple emoji on single tweet and find tweet that contain sarcasm or not, also classify given tweet.