Emotion Detection on TV Show Transcripts with Sequence-based Convolutional Neural Networks

TL;DR

This paper introduces a new dataset and deep neural models for emotion detection in TV show dialogues, achieving promising accuracy in classifying seven emotions from multiparty conversations.

Contribution

It presents a novel corpus with emotion annotations in dialogues and proposes sequence-based CNN models with attention for improved emotion recognition.

Findings

Best model achieves 37.9% accuracy for fine-grained emotions.

Achieves 54% accuracy for coarse-grained emotions.

Demonstrates the effectiveness of sequence-based CNNs with attention.

Abstract

While there have been significant advances in detecting emotions from speech and image recognition, emotion detection on text is still under-explored and remained as an active research field. This paper introduces a corpus for text-based emotion detection on multiparty dialogue as well as deep neural models that outperform the existing approaches for document classification. We first present a new corpus that provides annotation of seven emotions on consecutive utterances in dialogues extracted from the show, Friends. We then suggest four types of sequence-based convolutional neural network models with attention that leverage the sequence information encapsulated in dialogue. Our best model shows the accuracies of 37.9% and 54% for fine- and coarse-grained emotions, respectively. Given the difficulty of this task, this is promising.