mlsanityData to 7 Oct 2026

COSMIC: COmmonSense knowledge for eMotion Identification in Conversations

arXiv 2010.02795 ↗First posted 6 Oct 2020cs.CLcited by 135

Not on the map. Why?

Abstract (arXiv)

In this paper, we address the task of utterance level emotion recognition in conversations using commonsense knowledge. We propose COSMIC, a new framework that incorporates different elements of commonsense such as mental states, events, and causal relations, and build upon them to learn interactions between interlocutors participating in a conversation. Current state-of-the-art methods often encounter difficulties in context propagation, emotion shift detection, and differentiating between related emotion classes. By learning distinct commonsense representations, COSMIC addresses these challenges and achieves new state-of-the-art results for emotion recognition on four different benchmark conversational datasets. Our code is available at https://github.com/declare-lab/conv-emotion.

Key facts. Cited by 135 papers in the map (data through 7 Oct 2026). First posted on arXiv 6 Oct 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 18; 2022: 24; 2023: 43; 2024: 24; 2025: 8; 2026: 18.

135 papers.

Sort:

By area:

  1. 2021Directed Acyclic Graph Network for Conversational Emotion Recognitioncited by 97
  2. 2023Cue-CoT: Chain-of-thought Prompting for Responding to In-depth Dialogue Questions with LLMscited by 62
  3. 2022UniMSE: Towards Unified Multimodal Sentiment Analysis and Emotion Recognitioncited by 61
  4. 2021EmoBERTa: Speaker-Aware Emotion Recognition in Conversation with RoBERTacited by 59
  5. 2021Topic-Driven and Knowledge-Aware Transformer for Dialogue Emotion Detectioncited by 56
  6. 2023Is ChatGPT Equipped with Emotional Dialogue Capabilities?cited by 54
  7. 2022EmoCaps: Emotion Capsule based Model for Conversational Emotion Recognitioncited by 48
  8. 2022M2FNet: Multi-modal Fusion Network for Emotion Recognition in Conversationcited by 47
  9. 2022CICERO: A Dataset for Contextualized Commonsense Inference in Dialoguescited by 38
  10. 2023A Transformer-Based Model With Self-Distillation for Multimodal Emotion Recognition in Conversationscited by 37
  11. 2021CoMPM: Context Modeling with Speaker's Pre-trained Memory Tracking for Emotion Recognition in Conversationcited by 35
  12. 2021Contrast and Generation Make BART a Good Dialogue Emotion Recognizercited by 35
38 more
  1. 2021ValueNet: A New Dataset for Human Value Driven Dialogue Systemcited by 34
  2. 2023A Comprehensive Survey on Multi-modal Conversational Emotion Recognition with Deep Learningcited by 32
  3. 2022Supervised Prototypical Contrastive Learning for Emotion Recognition in Conversationcited by 31
  4. 2021Graph Based Network with Contextualized Representations of Turns in Dialoguecited by 26
  5. 2024Emotion Analysis in NLP: Trends, Gaps and Roadmap for Future Directionscited by 26
  6. 2021Hybrid Curriculum Learning for Emotion Recognition in Conversationcited by 25
  7. 2024MIntRec2.0: A Large-scale Benchmark Dataset for Multimodal Intent Recognition and Out-of-scope Detection in Conversationscited by 25
  8. 2021EmoWOZ: A Large-Scale Corpus and Labelling Scheme for Emotion Recognition in Task-Oriented Dialogue Systemscited by 20
  9. 2022GraphCFC: A Directed Graph Based Cross-Modal Feature Complementation Approach for Multimodal Conversational Emotion Recognitioncited by 20
  10. 2023Supervised Adversarial Contrastive Learning for Emotion Recognition in Conversationscited by 19
  11. 2023Conversation Understanding using Relational Temporal Graph Neural Networks with Auxiliary Cross-Modality Interactioncited by 18
  12. 2023UniSA: Unified Generative Framework for Sentiment Analysiscited by 17
  13. 2021Dyadformer: A Multi-modal Transformer for Long-Range Modeling of Dyadic Interactionscited by 16
  14. 2022Don't Lose Yourself! Empathetic Response Generation via Explicit Self-Other Awarenesscited by 16
  15. 2022Knowledge-Bridged Causal Interaction Network for Causal Emotion Entailmentcited by 16
  16. 2021Automatically Select Emotion for Response via Personality-affected Emotion Transitioncited by 15
  17. 2023Think Twice: A Human-like Two-stage Conversational Agent for Emotional Response Generationcited by 14
  18. 2023Cluster-Level Contrastive Learning for Emotion Recognition in Conversationscited by 14
  19. 2023CFN-ESA: A Cross-Modal Fusion Network with Emotion-Shift Awareness for Dialogue Emotion Recognitioncited by 14
  20. 2023Joyful: Joint Modality Fusion and Graph Contrastive Learning for Multimodal Emotion Recognitioncited by 14
  21. 2022Neutral Utterances are Also Causes: Enhancing Conversational Causal Emotion Entailment with Social Commonsense Knowledgecited by 13
  22. 2023Revisiting Disentanglement and Fusion on Modality and Context in Conversational Multimodal Emotion Recognitioncited by 13
  23. 2024LaERC-S: Improving LLM-based Emotion Recognition in Conversation with Speaker Characteristicscited by 13
  24. 2022Deep Emotion Recognition in Textual Conversations: A Surveycited by 12
  25. 2023Improving Empathetic Dialogue Generation by Dynamically Infusing Commonsense Knowledgecited by 12
  26. 2024TelME: Teacher-leading Multimodal Fusion Network for Emotion Recognition in Conversationcited by 12
  27. 2026HEART: A Unified Benchmark for Assessing Humans and LLMs in Emotional Support Dialoguecited by 12
  28. 2024BiosERC: Integrating Biography Speakers Supported by LLMs for ERC Taskscited by 11
  29. 2024Synth-Empathy: Towards High-Quality Synthetic Empathy Datacited by 10
  30. 2025Multimodal Emotion Recognition in Conversations: A Survey of Methods, Trends, Challenges and Prospectscited by 10
  31. 2021Retrieve, Caption, Generate: Visual Grounding for Enhancing Commonsense in Text Generation Modelscited by 9
  32. 2021Shapes of Emotions: Multimodal Emotion Recognition in Conversations via Emotion Shiftscited by 9
  33. 2023BERT-ERC: Fine-tuning BERT is Enough for Emotion Recognition in Conversationcited by 9
  34. 2025A Desideratum for Conversational Agents: Capabilities, Challenges, and Future Directionscited by 9
  35. 2021Multi-Task Learning and Adapted Knowledge Models for Emotion-Cause Extractioncited by 8
  36. 2021SAPPHIRE: Approaches for Enhanced Concept-to-Text Generationcited by 8
  37. 2022C3KG: A Chinese Commonsense Conversation Knowledge Graphcited by 8
  38. 2022M2R2: Missing-Modality Robust emotion Recognition framework with iterative data augmentationcited by 8

50 most cited of 135 All 135 (JSON)