mlsanityData to 7 Oct 2026

Towards an Online Empathetic Chatbot with Emotion Causes

arXiv 2105.11903 ↗First posted 11 May 2021cs.CL cs.AIcited by 16

Not on the map. Why?

Abstract (arXiv)

Existing emotion-aware conversational models usually focus on controlling the response contents to align with a specific emotion class, whereas empathy is the ability to understand and concern the feelings and experience of others. Hence, it is critical to learn the causes that evoke the users' emotion for empathetic responding, a.k.a. emotion causes. To gather emotion causes in online environments, we leverage counseling strategies and develop an empathetic chatbot to utilize the causal emotion information. On a real-world online dataset, we verify the effectiveness of the proposed approach by comparing our chatbot with several SOTA methods using automatic metrics, expert-based human judgements as well as user-based online evaluation.

Key facts. Cited by 16 papers in the map (data through 7 Oct 2026). Builds on 20 of its 35 references that are in the map. First posted on arXiv 11 May 2021.

Builds on

20 of 35 references.

References · 20

  1. 2017Attention Is All You Needcited by 59,932
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  3. 2016SQuAD: 100,000+ Questions for Machine Comprehension of Textcited by 4,115
  4. 2017Decoupled Weight Decay Regularizationcited by 1,722
  5. 2015A Diversity-Promoting Objective Function for Neural Conversation Modelscited by 1,068
  6. 2019DialoGPT: Large-Scale Generative Pre-training for Conversational Response Generationcited by 842
  7. 2019Unified Language Model Pre-training for Natural Language Understanding and Generationcited by 668
  8. 2019TransferTransfo: A Transfer Learning Approach for Neural Network Based Conversational Agentscited by 188
  9. 2017Emotional Chatting Machine: Emotional Conversation Generation with Internal and External Memorycited by 167
  10. 2019PLATO: Pre-trained Dialogue Generation Model with Discrete Latent Variablecited by 145
  11. 2019Emotion Recognition in Conversation: Research Challenges, Datasets, and Recent Advancescited by 118
  12. 2020MIME: MIMicking Emotions for Empathetic Response Generationcited by 114
8 more
  1. 2019Emotion-Cause Pair Extraction: A New Task to Emotion Analysis in Textscited by 82
  2. 2020A Large-Scale Chinese Short-Text Conversation Datasetcited by 77
  3. 2021Towards Facilitating Empathic Conversations in Online Mental Health Support: A Reinforcement Learning Approachcited by 75
  4. 2020Recognizing Emotion Cause in Conversationscited by 66
  5. 2020A Taxonomy of Empathetic Response Intents in Human Social Conversationscited by 51
  6. 2020CDL: Curriculum Dual Learning for Emotion-Controllable Response Generationcited by 43
  7. 2018A Syntactically Constrained Bidirectional-Asynchronous Approach for Emotional Conversation Generationcited by 11
  8. 2020An Empirical Investigation of Pre-Trained Transformer Language Models for Open-Domain Dialogue Generationcited by 7

Built on by

Cited by year

Citing papers per year: 2022: 4; 2023: 7; 2024: 4; 2025: 1.

16 papers.

Sort:

By area:

  1. 2022MISC: A MIxed Strategy-Aware Model Integrating COMET for Emotional Support Conversationcited by 84
  2. 2023Building Emotional Support Chatbots in the Era of LLMscited by 62
  3. 2023Knowledge-enhanced Mixed-initiative Dialogue System for Emotional Support Conversationscited by 41
  4. 2023ChaCha: Leveraging Large Language Models to Prompt Children to Share Their Emotions about Personal Eventscited by 31
  5. 2023Rethinking Large Language Models in Mental Health Applicationscited by 16
  6. 2022Empathetic Conversational Systems: A Review of Current Advances, Gaps, and Opportunitiescited by 14
  7. 2023BERT-ERC: Fine-tuning BERT is Enough for Emotion Recognition in Conversationcited by 9
  8. 2022C3KG: A Chinese Commonsense Conversation Knowledge Graphcited by 8
  9. 2022Wish I Can Feel What You Feel: A Neural Approach for Empathetic Response Generationcited by 5
  10. 2025Exploring Emotion-Sensitive LLM-Based Conversational AIcited by 4
  11. 2023ECQED: Emotion-Cause Quadruple Extraction in Dialogscited by 2
  12. 2023Development and Evaluation of Three Chatbots for Postpartum Mood and Anxiety Disorderscited by 2
4 more
  1. 2024"You tell me": A Dataset of GPT-4-Based Behaviour Change Support Conversationscited by 2
  2. 2024Improving Emotional Support Delivery in Text-Based Community Safety Reporting Using Large Language Modelscited by 0
  3. 2024Generative Emotion Cause Explanation in Multimodal Conversationscited by 0
  4. 2024Socio-Emotional Response Generation: A Human Evaluation Protocol for LLM-Based Conversational Systemscited by 0