COGMEN: COntextualized GNN based Multimodal Emotion recognitioN

Emotions are an inherent part of human interactions, and consequently, it is imperative to develop AI systems that understand and recognize human emotions. During a conversation involving various people, a person's emotions are influenced by the other speaker's utterances and their own emotional state over the utterances. In this paper, we propose COntextualized Graph Neural Network based Multimodal Emotion recognitioN (COGMEN) system that leverages local information (i.e., inter/intra dependency between speakers) and global information (context). The proposed model uses Graph Neural Network (GNN) based architecture to model the complex dependencies (local and global information) in a conversation. Our model gives state-of-the-art (SOTA) results on IEMOCAP and MOSEI datasets, and detailed ablation experiments show the importance of modeling information at both levels.

PDF Abstract NAACL 2022 PDF NAACL 2022 Abstract
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Multimodal Emotion Recognition IEMOCAP COGMEN (4-class) F1 0.845 # 2
Multimodal Emotion Recognition IEMOCAP COGMEN (6-class) Unweighted Accuracy (UA) 0.682 # 6
F1 0.676 # 10