EMNLP Findings2024
DetectiveNN: Imitating Human Emotional Reasoning with a Recall-Detect-Predict Framework for Emotion Recognition in Conversations
Simin Hong, Jun Sun, Taihao Li
Abstract
Emotion Recognition in conversations (ERC) involves an internal cognitive process that interprets emotional cues by using a collection of past emotional experiences. However, many existing methods struggle to decipher emotional cues in dialogues since they are insufficient in understanding the rich historical emotional context. In this work, we introduce an innovative Detective Network (DetectiveNN), a novel model that is grounded in the cognitive theory of emotion and utilizes a "recall-detect-predict" framework to imitate human emotional reasoning. This process begins by 'recalling' past interactions of a specific speaker to collect emotional cues. It then 'detects' relevant emotional patterns by interpreting these cues in the context of the ongoing conversation. Finally, it 'predicts' the speaker's current emotional state. Tested on three benchmark datasets, our approach significantly outperforms existing methods. This highlights the advantages of incorporating cognitive factors into deep learning for ERC, enhancing task efficacy and prediction accuracy 1 .
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
Lineage
- EmoCaps: Emotion Capsule based Model for Conversational Emotion Recognition cites DialogXL: All-in-One XLNet for Multi-Party Conversation Emotion Recognition
- EmoCaps: Emotion Capsule based Model for Conversational Emotion Recognition cites COSMIC: COmmonSense knowledge for eMotion Identification in Conversations
- Revisiting Disentanglement and Fusion on Modality and Context in Conversational Multimodal Emotion Recognition cites COSMIC: COmmonSense knowledge for eMotion Identification in Conversations
Builds on8
- COSMIC: COmmonSense knowledge for eMotion Identification in ConversationsDeepanway Ghosal, Navonil Majumder, Alexander F. Gelbukh, Rada Mihalcea et al.EMNLP Findings 2020 · 390 citations
- DialogXL: All-in-One XLNet for Multi-Party Conversation Emotion RecognitionWeizhou Shen, Junqing Chen, Xiaojun Quan, Zhixian XieAAAI 2021 · 251 citations
- Real-Time Emotion Recognition via Attention Gated Hierarchical Memory NetworkWenxiang Jiao, Michael R. Lyu, Irwin KingAAAI 2020 · 149 citations
- EmoCaps: Emotion Capsule based Model for Conversational Emotion RecognitionZaijing Li, Fengxiao Tang, Ming Zhao, Yusen ZhuACL Findings 2022 · 117 citations
- Revisiting Disentanglement and Fusion on Modality and Context in Conversational Multimodal Emotion RecognitionBobo Li, Hao Fei, Lizi Liao, Yu Zhao et al.ACM MM 2023 · 76 citations
Related papers
- DialogueCRN: Contextual Reasoning Networks for Emotion Recognition in ConversationsDou Hu, Lingwei Wei, Xiaoyong HuaiACL 2021
- ERCThinker: Fast-Slow Thinking for Emotion Recognition in ConversationYumeng Fu, Weitao Huang, Junjie Wu, Hao Teng et al.ACL 2026
- ECERC: Evidence-Cause Attention Network for Multi-Modal Emotion Recognition in ConversationTao Zhang, Zhenhua TanACL 2025 · 4 citations
- Directed Acyclic Graph Network for Conversational Emotion RecognitionWeizhou Shen, Siyue Wu, Yunyi Yang, Xiaojun QuanACL 2021
- Graph Based Network with Contextualized Representations of Turns in DialogueBongseok Lee, Yong Suk ChoiEMNLP 2021 · 42 citations
