Research map / Label-efficient and robust learning / Recognition and long-tail
DialogueRNN: An Attentive RNN for Emotion Detection in Conversations
Navonil Majumder, Soujanya Poria, Devamanyu Hazarika, Rada Mihalcea, Alexander Gelbukh, Erik Cambria
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| model speaker-specific party states and global dialogue context | DialogueRNN · IEMOCAP test | weighted F1: 56.13 -> 59.89 | Improved |
| model party states and emotion flow with an Emotion GRU (ablation) | DialogueRNN · IEMOCAP test | F1: 55.56 -> 59.89 | Improved |
| add an Emotion GRU linking preceding parties' states (ablation) | DialogueRNN · IEMOCAP test | F1: 57.38 -> 59.89 | Improved |
| add explicit listener-state updates (ablation) | DialogueRNN · IEMOCAP test | weighted F1: 59.89 -> 58.76 | Hurt |
| add a backward DialogueRNN pass to use future utterances (ablation) | DialogueRNN · IEMOCAP test | weighted F1: 59.89 -> 60.28 | Improved |
| add attention over past and future emotion representations (ablation) | DialogueRNN · IEMOCAP test | weighted F1: 59.89 -> 61.51 | Improved |
| combine bidirectional processing with attention over emotion representations (ablation) | DialogueRNN · IEMOCAP test | weighted F1: 59.89 -> 62.75 | Improved |
| add explicit listener-state updates (ablation) | DialogueRNN · IEMOCAP happy class | F1: +1.71% | Improved |
| add explicit listener-state updates (ablation) | DialogueRNN · AVEC | MAE and Pearson r | Hurt |
Later papers that compared with this method
4 later accepted papers report DialogueRNN as a baseline in their results tables; 4 of them report a better number on most of the results they share with it.
- Beyond Single Emotion: Multi-label Approach to Conversational Emotion Recognition (AAAI 2025 · better on 1 of 1 shared result)
- Time to Transfer: Predicting and Evaluating Machine-Human Chatting Handoff (AAAI 2021 · better on 1 of 1 shared result)
- DCR-Net: A Deep Co-Interactive Relation Network for Joint Dialog Act Recognition and Sentiment Classification (AAAI 2020 · better on 1 of 1 shared result)
- Sentiment Classification in Customer Service Dialogue with Topic-Aware Multi-Task Learning (AAAI 2020 · better on 1 of 1 shared result)
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Utterance-level Emotion Recognition in Conversation with Conversation-level Supervision (AAAI 2025 · similarity 0.86)
- Real-Time Emotion Recognition via Attention Gated Hierarchical Memory Network (AAAI 2020 · similarity 0.86)
- DialogXL: All-in-One XLNet for Multi-Party Conversation Emotion Recognition (AAAI 2021 · similarity 0.86)
- Adaptive Graph Learning for Multimodal Conversational Emotion Detection (AAAI 2024 · similarity 0.85)
- Dynamic Interactive Bimodal Hypergraph Networks for Emotion Recognition in Conversations (AAAI 2025 · similarity 0.84)
- Dual-View Learning for Conversational Emotion Recognition Through Context and Emotion-Shift Modeling (AAAI 2025 · similarity 0.84)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
