Sentiment Analysis using Few Short Learning
Daksh Jain, Archit Garg, Mukesh Saraswat · 2019
Many social websites and android applications whether being Facebook, WhatsApp or Twitter, in this highly advanced and modernized world is flooded with views and data. One of the most popular social platform is Twitter which has been observed as the main source of sentiments where almost every enthusiastic or social person tends to express his or her views in the form of comments. This research aims to analyze the problem of sentiments on small datasets, namely Sentiment Strength-Tweet, Health Care Reform, airline and Whatsapp dataset. In this work, a Convolutional neural networks-Bidirectional long short term memory based model is presented which uses four conv1d and two maxpool layers along with Bidirectional long short term memory. The proposed method has been compared with various machine learning based methods. The experimental results show that the proposed method outperforms the existing methods over the considered datasets.