Exploring Deep Neural Networks and Transfer Learning for Analyzing Emotions in Tweets

TL;DR

This paper explores the use of combined deep learning models and transfer learning for emotion detection and intensity prediction in tweets, introducing visualization techniques for interpretability.

Contribution

It proposes a novel LSTM-CNN hybrid model for emotion analysis and extends it with transfer learning for emotion intensity prediction, along with interpretability methods.

Findings

Models outperform state-of-the-art in emotion classification

Achieve competitive results in emotion intensity prediction

Introduce visualization technique for model interpretability

Abstract

In this paper, we present an experiment on using deep learning and transfer learning techniques for emotion analysis in tweets and suggest a method to interpret our deep learning models. The proposed approach for emotion analysis combines a Long Short Term Memory (LSTM) network with a Convolutional Neural Network (CNN). Then we extend this approach for emotion intensity prediction using transfer learning technique. Furthermore, we propose a technique to visualize the importance of each word in a tweet to get a better understanding of the model. Experimentally, we show in our analysis that the proposed models outperform the state-of-the-art in emotion classification while maintaining competitive results in predicting emotion intensity.