Emotion Detection from Text

Emotions are perceptions of changes in the human body such as heart rate, breathing rate, perspiration, and hormone levels. These conscious experiences are complex and studied extensively in different fields including computer science. Lack of facial expressions and voice modulations make detecting emotions from text a challenging problem. However, as humans are moving towards a digital era, with increasing mobile communication systems, it is essential that these digital agents are emotion aware, and respond accordingly. In this paper, we propose a novel approach to detect emotions like happy or sad in texts using an LSTM based Deep Learning model. Our approach consists of semi-automated techniques to gather training data for our model. We experiment with different embeddings and propose a solution using the best embedding for the task. Our work is evaluated on real-world tweets and significantly outperforms traditional Machine Learning baselines as well as other off-the-shelf Deep Learning models.