skip to main content
10.1145/3442381.3450097acmconferencesArticle/Chapter ViewAbstractPublication PageswwwConference Proceedingsconference-collections
research-article

Towards Facilitating Empathic Conversations in Online Mental Health Support: A Reinforcement Learning Approach

Published:03 June 2021Publication History

ABSTRACT

Online peer-to-peer support platforms enable conversations between millions of people who seek and provide mental health support. If successful, web-based mental health conversations could improve access to treatment and reduce the global disease burden. Psychologists have repeatedly demonstrated that empathy, the ability to understand and feel the emotions and experiences of others, is a key component leading to positive outcomes in supportive conversations. However, recent studies have shown that highly empathic conversations are rare in online mental health platforms.

In this paper, we work towards improving empathy in online mental health support conversations. We introduce a new task of empathic rewriting which aims to transform low-empathy conversational posts to higher empathy. Learning such transformations is challenging and requires a deep understanding of empathy while maintaining conversation quality through text fluency and specificity to the conversational context. Here we propose Partner, a deep reinforcement learning (RL) agent that learns to make sentence-level edits to posts in order to increase the expressed level of empathy while maintaining conversation quality. Our RL agent leverages a policy network, based on a transformer language model adapted from GPT-2, which performs the dual task of generating candidate empathic sentences and adding those sentences at appropriate positions. During training, we reward transformations that increase empathy in posts while maintaining text fluency, context specificity, and diversity. Through a combination of automatic and human evaluation, we demonstrate that Partner successfully generates more empathic, specific, and diverse responses and outperforms NLP methods from related tasks such as style transfer and empathic dialogue generation. This work has direct implications for facilitating empathic conversations on web-based platforms.

References

  1. Tim Althoff, Kevin Clark, and Jure Leskovec. 2016. Large-scale analysis of counseling conversations: An application of natural language processing to mental health. TACL (2016).Google ScholarGoogle Scholar
  2. C Daniel Batson. 2009. These things called empathy: eight related but distinct phenomena.(2009).Google ScholarGoogle Scholar
  3. Arthur C Bohart, Robert Elliott, Leslie S Greenberg, and Jeanne C Watson. 2002. Empathy.J. C. Norcross (Ed.), Psychotherapy relationships that work: Therapist contributions and responsiveness to patients (2002).Google ScholarGoogle Scholar
  4. Arthur C Bohart and Leslie S Greenberg. 1997. Empathy reconsidered: New directions in psychotherapy.American Psychological Association.Google ScholarGoogle Scholar
  5. Tom B Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared Kaplan, Prafulla Dhariwal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, Amanda Askell, 2020. Language models are few-shot learners. arXiv preprint arXiv:2005.14165(2020).Google ScholarGoogle Scholar
  6. Sven Buechel, Anneke Buffone, Barry Slaff, Lyle Ungar, and João Sedoc. 2018. Modeling Empathy and Distress in Reaction to News Stories. In EMNLP.Google ScholarGoogle Scholar
  7. Louis G Castonguay and Clara E Hill. 2017. How and why are some therapists better than others?: Understanding therapist effects.American Psychological Association.Google ScholarGoogle Scholar
  8. Mia Xu Chen, Benjamin N Lee, Gagan Bansal, Yuan Cao, Shuyuan Zhang, Justin Lu, Jackie Tsay, Yinan Wang, Andrew M Dai, Zhifeng Chen, 2019. Gmail smart compose: Real-time assisted writing. In SIGKDD.Google ScholarGoogle Scholar
  9. Elizabeth Clark, Anne Spencer Ross, Chenhao Tan, Yangfeng Ji, and Noah A Smith. 2018. Creative writing with a machine in the loop: Case studies on slogans and stories. In IUI.Google ScholarGoogle Scholar
  10. Sunny Collings and Thomas Niederkrotenthaler. 2012. Suicide prevention and emergent media: surfing the opportunity.Google ScholarGoogle Scholar
  11. Pamela Y Collins, Vikram Patel, Sarah S Joestl, Dana March, Thomas R Insel, Abdallah S Daar, Isabel A Bordin, E Jane Costello, Maureen Durkin, Christopher Fairburn, 2011. Grand challenges in global mental health. Nature (2011).Google ScholarGoogle Scholar
  12. Ning Dai, Jianze Liang, Xipeng Qiu, and Xuanjing Huang. 2019. Style transformer: Unpaired text style transfer without disentangled latent representation. ACL.Google ScholarGoogle Scholar
  13. Sumanth Dathathri, Andrea Madotto, Janice Lan, Jane Hung, Eric Frank, Piero Molino, Jason Yosinski, and Rosanne Liu. 2020. Plug and Play Language Models: A Simple Approach to Controlled Text Generation. In ICLR.Google ScholarGoogle Scholar
  14. Mark H Davis 1980. A multidimensional approach to individual differences in empathy. Journal of Personality and Social Psychology (1980).Google ScholarGoogle Scholar
  15. Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. Bert: Pre-training of deep bidirectional transformers for language understanding. In NAACL-HLT.Google ScholarGoogle Scholar
  16. Changming Duan and Clara E Hill. 1996. The current state of empathy research.Journal of counseling psychology(1996).Google ScholarGoogle Scholar
  17. Robert Elliott, Arthur C Bohart, Jeanne C Watson, and Leslie S Greenberg. 2011. Empathy.Psychotherapy (2011).Google ScholarGoogle Scholar
  18. Robert Elliott, Arthur C Bohart, Jeanne C Watson, and David Murphy. 2018. Therapist empathy and client outcome: An updated meta-analysis.Psychotherapy (2018).Google ScholarGoogle Scholar
  19. Liye Fu, Susan R. Fussell, and Cristian Danescu-Niculescu-Mizil. 2020. Facilitating the Communication of Politeness through Fine-Grained Paraphrasing. In EMNLP.Google ScholarGoogle Scholar
  20. James Gibson, Doğan Can, Bo Xiao, Zac E Imel, David C Atkins, Panayiotis Georgiou, and Shrikanth S Narayanan. 2016. A Deep Learning Approach to Modeling Empathy in Addiction Counseling. Interspeech (2016).Google ScholarGoogle Scholar
  21. Lizabeth A Goldstein, Abby D Adler Mandel, Robert J DeRubeis, and Daniel R Strunk. 2020. Outcomes, skill acquisition, and the alliance: Similarities and differences between clinical trial and student therapists. Behaviour research and therapy(2020).Google ScholarGoogle Scholar
  22. Junxian He, Xinyi Wang, Graham Neubig, and Taylor Berg-Kirkpatrick. 2019. A Probabilistic Formulation of Unsupervised Text Style Transfer. In ICLR.Google ScholarGoogle Scholar
  23. Ari Holtzman, Jan Buys, Li Du, Maxwell Forbes, and Yejin Choi. 2020. The curious case of neural text degeneration. In ICLR.Google ScholarGoogle Scholar
  24. Zhiting Hu, Zichao Yang, Xiaodan Liang, Ruslan Salakhutdinov, and Eric P Xing. 2017. Toward controlled generation of text. In ICML.Google ScholarGoogle Scholar
  25. Minlie Huang, Xiaoyan Zhu, and Jianfeng Gao. 2020. Challenges in Building Intelligent Open-domain Dialog Systems. ACM Transactions on Information Systems (TOIS) (2020).Google ScholarGoogle Scholar
  26. Zac E Imel, Mark Steyvers, and David C Atkins. 2015. Computational psychotherapy research: Scaling up the evaluation of patient–provider interactions.Psychotherapy (2015).Google ScholarGoogle Scholar
  27. Hamed Khanpour, Cornelia Caragea, and Prakhar Biyani. 2017. Identifying empathetic messages in online health communities. In IJCNLP.Google ScholarGoogle Scholar
  28. Fei-Tzin Lee, Derrick Hull, Jacob Levine, Bonnie Ray, and Kathleen McKeown. 2019. Identifying therapist conversational actions across diverse psychotherapeutic approaches. In Proceedings of the Sixth Workshop on Computational Linguistics and Clinical Psychology.Google ScholarGoogle ScholarCross RefCross Ref
  29. Mike Lewis, Yinhan Liu, Naman Goyal, Marjan Ghazvininejad, Abdelrahman Mohamed, Omer Levy, Ves Stoyanov, and Luke Zettlemoyer. 2019. Bart: Denoising sequence-to-sequence pre-training for natural language generation, translation, and comprehension. arXiv preprint arXiv:1910.13461(2019).Google ScholarGoogle Scholar
  30. Jiwei Li, Michel Galley, Chris Brockett, Jianfeng Gao, and Bill Dolan. 2016. A Diversity-Promoting Objective Function for Neural Conversation Models. In NAACL-HLT.Google ScholarGoogle Scholar
  31. Juncen Li, Robin Jia, He He, and Percy Liang. 2018. Delete, Retrieve, Generate: a Simple Approach to Sentiment and Style Transfer. In ACL.Google ScholarGoogle Scholar
  32. Jiwei Li, Will Monroe, Alan Ritter, Dan Jurafsky, Michel Galley, and Jianfeng Gao. 2016. Deep Reinforcement Learning for Dialogue Generation. In EMNLP.Google ScholarGoogle Scholar
  33. Ron C Li, Steven M Asch, and Nigam H Shah. 2020. Developing a delivery science for artificial intelligence in healthcare. NPJ Digital Medicine(2020).Google ScholarGoogle Scholar
  34. Zhaojiang Lin, Andrea Madotto, Jamin Shin, Peng Xu, and Pascale Fung. 2019. Moel: Mixture of empathetic listeners. In EMNLP.Google ScholarGoogle Scholar
  35. Chia-Wei Liu, Ryan Lowe, Iulian Vlad Serban, Mike Noseworthy, Laurent Charlin, and Joelle Pineau. 2016. How NOT To Evaluate Your Dialogue System: An Empirical Study of Unsupervised Evaluation Metrics for Dialogue Response Generation. In EMNLP.Google ScholarGoogle Scholar
  36. Yinhan Liu, Myle Ott, Naman Goyal, Jingfei Du, Mandar Joshi, Danqi Chen, Omer Levy, Mike Lewis, Luke Zettlemoyer, and Veselin Stoyanov. 2019. Roberta: A robustly optimized bert pretraining approach. arXiv preprint arXiv:1907.11692(2019).Google ScholarGoogle Scholar
  37. Fuli Luo, Peng Li, Jie Zhou, Pengcheng Yang, Baobao Chang, Xu Sun, and Zhifang Sui. 2019. A dual reinforcement learning framework for unsupervised text style transfer. In IJCAI.Google ScholarGoogle Scholar
  38. David D Luxton, Jennifer D June, and Jonathan M Fairall. 2012. Social media and suicide: a public health perspective. American journal of public health(2012).Google ScholarGoogle Scholar
  39. Xinyao Ma, Maarten Sap, Hannah Rashkin, and Yejin Choi. 2020. PowerTransformer: Unsupervised controllable revision for biased language correction. EMNLP.Google ScholarGoogle Scholar
  40. Florian Mai, Nikolaos Pappas, Ivan Montero, Noah A Smith, and James Henderson. 2020. Plug and Play Autoencoders for Conditional Text Generation. In EMNLP.Google ScholarGoogle Scholar
  41. Navonil Majumder, Pengfei Hong, Shanshan Peng, Jiankun Lu, Deepanway Ghosal, Alexander Gelbukh, Rada Mihalcea, and Soujanya Poria. 2020. MIME: MIMicking Emotions for Empathetic Response Generation. In EMNLP.Google ScholarGoogle Scholar
  42. Tara Matthews, Kathleen O’Leary, Anna Turner, Manya Sleeper, Jill Palzkill Woelfer, Martin Shelton, Cori Manthorne, Elizabeth F Churchill, and Sunny Consolvo. 2017. Stories from survivors: Privacy & security practices when coping with intimate partner abuse. In CHI.Google ScholarGoogle Scholar
  43. Adam S Miner, Albert Haque, Jason A Fries, Scott L Fleming, Denise E Wilfley, G Terence Wilson, Arnold Milstein, Dan Jurafsky, Bruce A Arnow, W Stewart Agras, 2020. Assessing the accuracy of automatic speech recognition for psychotherapy. NPJ Digital Medicine(2020).Google ScholarGoogle Scholar
  44. Adam S Miner, Nigam Shah, Kim D Bullock, Bruce A Arnow, Jeremy Bailenson, and Jeff Hancock. 2019. Key considerations for incorporating conversational AI in psychotherapy. Frontiers in psychiatry 10 (2019).Google ScholarGoogle Scholar
  45. Mark Olfson. 2016. Building the mental health workforce capacity needed to treat adults with serious mental illnesses. Health Affairs (2016).Google ScholarGoogle Scholar
  46. Lars-Göran Öst, Anna Karlstedt, and Sara Widén. 2012. The effects of cognitive behavior therapy delivered by students in a psychologist training program: An effectiveness study. Behavior Therapy (2012).Google ScholarGoogle Scholar
  47. Kishore Papineni, Salim Roukos, Todd Ward, and Wei-Jing Zhu. 2002. BLEU: a method for automatic evaluation of machine translation. In ACL.Google ScholarGoogle Scholar
  48. Verónica Pérez-Rosas, Rada Mihalcea, Kenneth Resnicow, Satinder Singh, and Lawrence An. 2017. Understanding and predicting empathic behavior in counseling therapy. In ACL.Google ScholarGoogle Scholar
  49. Verónica Pérez-Rosas, Xinyi Wu, Kenneth Resnicow, and Rada Mihalcea. 2019. What Makes a Good Counselor? Learning to Distinguish between High-quality and Low-quality Counseling Conversations. In ACL.Google ScholarGoogle Scholar
  50. Yada Pruksachatkun, Sachin R Pendse, and Amit Sharma. 2019. Moments of Change: Analyzing Peer-Based Cognitive Support in Online Mental Health Forums. In CHI.Google ScholarGoogle Scholar
  51. Reid Pryzant, Richard Diehl Martinez, Nathan Dass, Sadao Kurohashi, Dan Jurafsky, and Diyi Yang. 2020. Automatically neutralizing subjective bias in text. In AAAI.Google ScholarGoogle Scholar
  52. Alec Radford, Jeffrey Wu, Rewon Child, David Luan, Dario Amodei, and Ilya Sutskever. 2019. Language models are unsupervised multitask learners. OpenAI Blog 1, 8 (2019), 9.Google ScholarGoogle Scholar
  53. Hannah Rashkin, Eric Michael Smith, Margaret Li, and Y-Lan Boureau. 2019. Towards Empathetic Open-domain Conversation Models: A New Benchmark and Dataset. In ACL.Google ScholarGoogle Scholar
  54. Elliot Robert, Arthur C Bohart, JC Watson, and LS Greenberg. 2011. Empathy. Psychotherapy (2011).Google ScholarGoogle Scholar
  55. Sebastin Santy, Sandipan Dandapat, Monojit Choudhury, and Kalika Bali. 2019. INMT: Interactive Neural Machine Translation Prediction. In EMNLP (System Demonstrations).Google ScholarGoogle Scholar
  56. Abigail See, Stephen Roller, Douwe Kiela, and Jason Weston. 2019. What makes a good conversation? How controllable attributes affect human judgments. In NAACL-HLT.Google ScholarGoogle Scholar
  57. Robert L Selman. 1980. Growth of interpersonal understanding. Academic Press.Google ScholarGoogle Scholar
  58. Ashish Sharma, Monojit Choudhury, Tim Althoff, and Amit Sharma. 2020. Engagement Patterns of Peer-to-Peer Interactions on Mental Health Platforms. In ICWSM.Google ScholarGoogle Scholar
  59. Ashish Sharma, Adam S Miner, David C Atkins, and Tim Althoff. 2020. A Computational Approach to Understanding Empathy Expressed in Text-Based Mental Health Support. In EMNLP.Google ScholarGoogle Scholar
  60. Eva Sharma and Munmun De Choudhury. 2018. Mental Health Support and its Relationship to Linguistic Accommodation in Online Communities. In CHI.Google ScholarGoogle Scholar
  61. Tianxiao Shen, Tao Lei, Regina Barzilay, and Tommi Jaakkola. 2017. Style transfer from non-parallel text by cross-alignment. In NeurIPS.Google ScholarGoogle Scholar
  62. Matthew Snover, Bonnie Dorr, Richard Schwartz, Linnea Micciulla, and John Makhoul. 2006. A study of translation edit rate with targeted human annotation. In Proceedings of association for machine translation in the Americas, Vol. 200. Cambridge, MA.Google ScholarGoogle Scholar
  63. Richard S Sutton and Andrew G Barto. 2018. Reinforcement learning: An introduction. MIT press.Google ScholarGoogle ScholarDigital LibraryDigital Library
  64. Michael J Tanana, Christina S Soma, Vivek Srikumar, David C Atkins, and Zac E Imel. 2019. Development and Evaluation of ClientBot: Patient-Like Conversational Agent to Train Basic Counseling Skills. JMIR (2019).Google ScholarGoogle Scholar
  65. CB Truax and RR Carkhuff. 1967. Modern applications in psychology. Toward effective counseling and psychotherapy: Training and practice. Hawthorne, NY, US: Aldine Publishing Co (1967).Google ScholarGoogle Scholar
  66. Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, Łukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. In NeurIPS.Google ScholarGoogle Scholar
  67. David Wadden, Tal August, Qisheng Li, and Tim Althoff. 2021. The Effect of Moderation on Online Mental Health Conversations. In ICWSM.Google ScholarGoogle Scholar
  68. Robert West and Eric Horvitz. 2019. Reverse-engineering satire, or “paper on computational humor accepted despite making serious advances”. In AAAI.Google ScholarGoogle Scholar
  69. Marsha White and Steve M Dorman. 2001. Receiving social support online: implications for health education. Health education research(2001).Google ScholarGoogle Scholar
  70. Ronald J Williams. 1992. Simple statistical gradient-following algorithms for connectionist reinforcement learning. Machine learning (1992).Google ScholarGoogle ScholarDigital LibraryDigital Library
  71. Xinnuo Xu, Ondřej Dušek, Ioannis Konstas, and Verena Rieser. 2018. Better conversations by modeling, filtering, and optimizing for coherence and diversity. ACL.Google ScholarGoogle Scholar
  72. Diyi Yang, Zheng Yao, Joseph Seering, and Robert Kraut. 2019. The Channel Matters: Self-disclosure, Reciprocity and Social Support in Online Cancer Support Groups. In CHI.Google ScholarGoogle Scholar
  73. Justine Zhang and Cristian Danescu-Niculescu-Mizil. 2020. Balancing Objectives in Counseling Conversations: Advancing Forwards or Looking Backwards. In ACL.Google ScholarGoogle Scholar
  74. Justine Zhang, Robert Filbin, Christine Morrison, Jaclyn Weiser, and Cristian Danescu-Niculescu-Mizil. 2019. Finding Your Voice: The Linguistic Development of Mental Health Counselors. In ACL.Google ScholarGoogle Scholar
  75. Yizhe Zhang, Siqi Sun, Michel Galley, Yen-Chun Chen, Chris Brockett, Xiang Gao, Jianfeng Gao, Jingjing Liu, and Bill Dolan. 2020. DialoGPT: Large-Scale Generative Pre-training for Conversational Response Generation. In ACL, system demonstration.Google ScholarGoogle Scholar
  76. Yiheng Zhou, He He, Alan W Black, and Yulia Tsvetkov. 2019. A Dynamic Strategy Coach for Effective Negotiation. In SIGdial.Google ScholarGoogle Scholar
  1. Towards Facilitating Empathic Conversations in Online Mental Health Support: A Reinforcement Learning Approach

    Recommendations

    Comments

    Login options

    Check if you have access through your login credentials or your institution to get full access on this article.

    Sign in
    • Published in

      cover image ACM Conferences
      WWW '21: Proceedings of the Web Conference 2021
      April 2021
      4054 pages
      ISBN:9781450383127
      DOI:10.1145/3442381

      Copyright © 2021 ACM

      Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected]

      Publisher

      Association for Computing Machinery

      New York, NY, United States

      Publication History

      • Published: 3 June 2021

      Permissions

      Request permissions about this article.

      Request Permissions

      Check for updates

      Qualifiers

      • research-article
      • Research
      • Refereed limited

      Acceptance Rates

      Overall Acceptance Rate1,899of8,196submissions,23%

    PDF Format

    View or Download as a PDF file.

    PDF

    eReader

    View online with eReader.

    eReader

    HTML Format

    View this article in HTML Format .

    View HTML Format