• A. SHUNMUGA SUNDARI
• Dr. R. SHENBAGAVALLI

Sentiment Analysis is a field of Natural Language Processing (NLP) that develops the system that tries to automatically identify and extract the emotions depicted by the text. Nowadays people can generate their opinion, views, and attitude about a product, person or issue in social media whenever and wherever possible. This opinionative and user-generated content occupies the major source of information on the World Wide Web. Identifying the emotion depicted by this text is very useful in many applications such as marketing analysis, public relations, product reviews, net promoter scoring, product feedback, and customer service. Generally, it identifies sentiment like joy, sadness, fear, anger and the like. And also the attributes of the expression such as its Polarity, Subject and the Opinion holder who express the sentiment. Ciphering of emotion and emotion intensity portrait by a text is a very challenging task. The crucial step of emotion analysis is feature extraction from the text because it defines the accuracy of emotion prediction. In this paper, emotion prediction is computed by using Convolutional Neural Network (CNN), Long Short Term Memory (Conv - LSTM) and Bidirectional Long Short Term Memory (BI-LSTM). As a result, BI-LSTM outperforms all the models with high accuracy.

Sentiment analysis, CNN, LSTM, BI-LSTM

"A COMPARATIVE ANALYSIS OF EMOTION PREDICTION ON A TEXT BY CNN, LSTM AND BI-LSTM", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.7, Issue 3, page no.35-39, March-2020, Available :http://www.jetir.org/papers/JETIRDP06008.pdf

"A COMPARATIVE ANALYSIS OF EMOTION PREDICTION ON A TEXT BY CNN, LSTM AND BI-LSTM", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.7, Issue 3, page no. pp35-39, March-2020, Available at : http://www.jetir.org/papers/JETIRDP06008.pdf