A Critical Reflection and Forward Perspective on Empathy and Natural Language Processing
Not on the map. Why?
Abstract (arXiv)
We review the state of research on empathy in natural language processing and identify the following issues: (1) empathy definitions are absent or abstract, which (2) leads to low construct validity and reproducibility. Moreover, (3) emotional empathy is overemphasized, skewing our focus to a narrow subset of simplified tasks. We believe these issues hinder research progress and argue that current directions will benefit from a clear conceptualization that includes operationalizing cognitive empathy components. Our main objectives are to provide insight and guidance on empathy conceptualization for NLP research objectives and to encourage researchers to pursue the overlooked opportunities in this area, highly relevant, e.g., for clinical and educational sectors.
Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 43 of its 183 references that are in the map. First posted on arXiv 29 Oct 2022.
Builds on
43 of 183 references.
References · 43
- 2020Recipes for building an open-domain chatbotcited by 593
- 2020GoEmotions: A Dataset of Fine-Grained Emotionscited by 479
- 2019Abductive Commonsense Reasoningcited by 300
- 2020A Computational Approach to Understanding Empathy Expressed in Text-Based Mental Health Supportcited by 182
- 2018The Design and Implementation of XiaoIce, an Empathetic Social Chatbotcited by 172
- 2020Can You Put it All Together: Evaluating Conversational Agents' Ability to Blend Skillscited by 130
- 2020MIME: MIMicking Emotions for Empathetic Response Generationcited by 114
- 2021MMGCN: Multimodal Fusion via Deep Graph Convolution Network for Emotion Recognition in Conversationcited by 99
- 2021PsyQA: A Chinese Dataset for Generating Long Counseling Text for Mental Health Supportcited by 92
- 2019MoEL: Mixture of Empathetic Listenerscited by 91
- 2021CEM: Commonsense-aware Empathetic Response Generationcited by 89
- 2022MISC: A MIxed Strategy-Aware Model Integrating COMET for Emotional Support Conversationcited by 84
31 more
- 2021Towards Facilitating Empathic Conversations in Online Mental Health Support: A Reinforcement Learning Approachcited by 75
- 2021DialogueCRN: Contextual Reasoning Networks for Emotion Recognition in Conversationscited by 71
- 2017MojiTalk: Generating Emotional Responses at Scalecited by 64
- 2020Towards Persona-Based Empathetic Conversational Modelscited by 53
- 2018Modeling Empathy and Distress in Reaction to News Storiescited by 52
- 2020A Taxonomy of Empathetic Response Intents in Human Social Conversationscited by 51
- 2020Deconstruct to Reconstruct a Configurable Evaluation Metric for Open-Domain Dialogue Systemscited by 47
- 2019The Dialogue Dodecathlon: Open-Domain Knowledge and Image Grounded Conversational Agentscited by 45
- 2020CDL: Curriculum Dual Learning for Emotion-Controllable Response Generationcited by 43
- 2021Perspective-taking and Pragmatics for Generating Empathetic Responses Focused on Emotion Causescited by 43
- 2021CoMAE: A Multi-factor Hierarchical Framework for Empathetic Response Generationcited by 42
- 2020Balancing Objectives in Counseling Conversations: Advancing Forwards or Looking Backwardscited by 18
- 2021EmpathBERT: A BERT-based Framework for Demographic-aware Empathy Predictioncited by 17
- 2020Quantifying the Causal Effects of Conversational Tendenciescited by 12
- 2017Annotating and Modeling Empathy in Spoken Conversationscited by 10
- 2019Learning Word Ratings for Empathy and Distress from Document-Level User Responsescited by 10
- 2021Transferable Persona-Grounded Dialogues via Grounded Minimal Editscited by 10
- 2021Style Control for Schema-Guided Natural Language Generationcited by 10
- 2021Supporting Cognitive and Emotional Empathic Writing of Studentscited by 8
- 2021ERICA: An Empathetic Android Companion for Covid-19 Quarantinecited by 8
- 2019Evaluating Empathy in Artificial Agentscited by 7
- 2021PVG at WASSA 2021: A Multi-Input, Multi-Task, Transformer-Based Architecture for Empathy and Distress Predictioncited by 7
- 2021Empathetic BERT2BERT Conversational Model: Learning Arabic Language Generation with Little Datacited by 7
- 2021Empathetic Dialog Generation with Fine-Grained Intentscited by 7
- 2021WASSA@IITK at WASSA 2021: Multi-task Learning and Transformer Finetuning for Emotion Classification and Empathy Predictioncited by 6
- 2021Team Phoenix at WASSA 2021: Emotion Analysis on News Stories with Pre-Trained Language Modelscited by 5
- 2021Empathy and Hope: Resource Transfer to Model Inter-country Social Media Dynamicscited by 4
- 2021Affective Decoding for Empathetic Response Generationcited by 4
- 2022Building a Dialogue Corpus Annotated with Expressed and Experienced Emotionscited by 4
- 2021Enhancing Cognitive Models of Emotions with Representation Learningcited by 3
- 2022bitsa_nlp@LT-EDI-ACL2022: Leveraging Pretrained Language Models for Detecting Homophobia and Transphobia in Social Media Commentscited by 3
Built on by
Citing papers per year: 2022: 1; 2023: 2; 2024: 0; 2025: 0; 2026: 1.
4 papers.
- 2022Computer says "No": The Case Against Empathetic Conversational AIcited by 9
- 2023Empathy Detection from Text, Audiovisual, Audio or Physiological Signals: A Systematic Review of Task Formulations and Machine Learning Methodscited by 5
- 2023Challenges of GPT-3-based Conversational Agents for Healthcarecited by 3
- 2026From Generation to Collaboration: Using LLMs to Edit for Empathy in Healthcarecited by 0
- 2026From Generation to Collaboration: Using LLMs to Edit for Empathy in Healthcare22 Jan 2026
- 2023Empathy Detection from Text, Audiovisual, Audio or Physiological Signals: A Systematic Review of Task Formulations and Machine Learning Methods30 Oct 2023
- 2023Challenges of GPT-3-based Conversational Agents for Healthcare28 Aug 2023
- 2022Computer says "No": The Case Against Empathetic Conversational AI21 Dec 2022