EmoGraph: Capturing Emotion Correlations using Graph Networks

Abstract

Most emotion recognition methods tackle the emotion understanding task by considering individual emotion independently while ignoring their fuzziness nature and the interconnections among them. In this paper, we explore how emotion correlations can be captured and help different classification tasks. We propose EmoGraph that captures the dependencies among different emotions through graph networks. These graphs are constructed by leveraging the co-occurrence statistics among different emotion categories. Empirical results on two multi-label classification datasets demonstrate that EmoGraph outperforms strong baselines, especially for macro-F1. An additional experiment illustrates the captured emotion correlations can also benefit a single-label classification task.

The first two authors contributed equally

References in corpus (2)

• Unsupervised Machine Translation Using Monolingual Corpora Only
• Unsupervised Neural Machine Translation

Cited by in corpus (5)

• AdCOFE: Advanced Contextual Feature Extraction in Conversations for emotion classification
• Modality-Transferable Emotion Embeddings for Low-Resource Multimodal Emotion Recognition
• Multimodal End-to-End Sparse Model for Emotion Recognition
• Leveraging Label Correlations in a Multi-label Setting: A Case Study in Emotion
• Using Emotion Embeddings to Transfer Knowledge Between Emotions, Languages, and Annotation Formats