• Rajat Jain
• Sawan Kshatriya
• Arun Dubey
• Pratyush Shukla
• Prof. K Jayamalini

Many micro blogging sites have millions of people sharing their thoughts daily. We propose and investigate the sentiment from a popular real-time micro blogging service, Twitter, where real time reactions are posted by the user and we find their opinions for almost about “everything”. Social networking sites like twitter, Facebook, Instagram, Orkut etc. are the great source of communication for internet users. So this becomes an important source for understanding the opinions, views or emotions of people. We extract data, i.e. tweets from Twitter in real time and apply machine learning techniques to convert them into a useful form and then use it for building sentiment classifier. Given a piece of written text, the problem is to categorize the text into one specific sentiment polarity i.e. positive, negative. With the increase use of Internet and big explosion of text data, it has been a very significant research subject to extract valuable information from Text Ocean. To realize multi-classification for text sentiment and emoticons sentiments, this paper promotes a RNN language model based on Long Short Term Memory (LSTM). LSTM is far better than the traditional RNN. And as a language model, LSTM is applied to achieve multi-classification for text and emoticon emotional attributes.

RNN, LSTM, Twitter, Sentiment analysis, Opinion mining.

"Emotion Detection from Tweets and Emoticons Using Rnn-Lstm", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.6, Issue 4, page no.257-262, April-2019, Available :http://www.jetir.org/papers/JETIR1904F44.pdf

"Emotion Detection from Tweets and Emoticons Using Rnn-Lstm", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.6, Issue 4, page no. pp257-262, April-2019, Available at : http://www.jetir.org/papers/JETIR1904F44.pdf