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

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.

References in corpus (6)

• Convolutional Sequence to Sequence Learning
• Dialogue Act Modeling for Automatic Tagging and Recognition of Conversational Speech
• Convolutional Neural Networks for Sentence Classification
• Recurrent Neural Network for Text Classification with Multi-Task Learning
• Attentive Pooling Networks
• Deep Heterogeneous Feature Fusion for Template-Based Face Recognition

Cited by in corpus (10)

• Towards Interpretable Mental Health Analysis with Large Language Models
• EmotionX-KU: BERT-Max based Contextual Emotion Classifier
• Multi-Task Learning with Auxiliary Speaker Identification for Conversational Emotion Recognition
• Directed Acyclic Graph Network for Conversational Emotion Recognition
• A Dual-Stream Recurrence-Attention Network With Global-Local Awareness for Emotion Recognition in Textual Dialog
• EmoTwiCS: A Corpus for Modelling Emotion Trajectories in Dutch Customer Service Dialogues on Twitter
• Whose Emotion Matters? Speaking Activity Localisation without Prior Knowledge
• Exploiting Unsupervised Data for Emotion Recognition in Conversations
• CRAB: Class Representation Attentive BERT for Hate Speech Identification in Social Media
• HUMBO: Bridging Response Generation and Facial Expression Synthesis