Pranav Manjunath

Summary

Multi-class Emotion Detection in Text has been a conventionally difficult task given the presence of subjectivity, subtleties and stylizations used in text. While a number of conventional and deep learning techniques have been used, the project found the BERT Model to be the best perform- ing so far, and developed an application to classify text from an external dataset into the seven basic emotion classes. We also created a Tkinter Application (Python) that loads Facebook Comments and detects the emotion of the comment.