Attention-based Modeling for Emotion Detection and Classification in Textual Conversations

TL;DR

This paper introduces an attention-based deep transfer learning model for emotion detection in textual conversations, leveraging self-attention and turn-based modeling to improve classification without handcrafted features.

Contribution

It presents a novel approach combining deep transfer learning and self-attention mechanisms for emotion detection in conversations, outperforming traditional methods.

Findings

Achieved competitive results on SemEval-2019 dataset

Outperformed classical shallow methods

Demonstrated effectiveness of self-attention in emotion classification

Abstract

This paper addresses the problem of modeling textual conversations and detecting emotions. Our proposed model makes use of 1) deep transfer learning rather than the classical shallow methods of word embedding; 2) self-attention mechanisms to focus on the most important parts of the texts and 3) turn-based conversational modeling for classifying the emotions. The approach does not rely on any hand-crafted features or lexicons. Our model was evaluated on the data provided by the SemEval-2019 shared task on contextual emotion detection in text. The model shows very competitive results.