Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
102 tokens/sec
GPT-4o
59 tokens/sec
Gemini 2.5 Pro Pro
43 tokens/sec
o3 Pro
6 tokens/sec
GPT-4.1 Pro
50 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Can an LLM-Powered Socially Assistive Robot Effectively and Safely Deliver Cognitive Behavioral Therapy? A Study With University Students (2402.17937v1)

Published 27 Feb 2024 in cs.RO

Abstract: Cognitive behavioral therapy (CBT) is a widely used therapeutic method for guiding individuals toward restructuring their thinking patterns as a means of addressing anxiety, depression, and other challenges. We developed a LLM-powered prompt-engineered socially assistive robot (SAR) that guides participants through interactive CBT at-home exercises. We evaluated the performance of the SAR through a 15-day study with 38 university students randomly assigned to interact daily with the robot or a chatbot (using the same LLM), or complete traditional CBT worksheets throughout the duration of the study. We measured weekly therapeutic outcomes, changes in pre-/post-session anxiety measures, and adherence to completing CBT exercises. We found that self-reported measures of general psychological distress significantly decreased over the study period in the robot and worksheet conditions but not the chatbot condition. Furthermore, the SAR enabled significant single-session improvements for more sessions than the other two conditions combined. Our findings suggest that SAR-guided LLM-powered CBT may be as effective as traditional worksheet methods in supporting therapeutic progress from the beginning to the end of the study and superior in decreasing user anxiety immediately after completing the CBT exercise.

PDF HTML Abstract
Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Bookmark Chat Bubble Oval Streamline Icon: https://streamlinehq.com Chat (Pro)
Definition Search Book Streamline Icon: https://streamlinehq.com
References (73)
  1. An overview of the features of chatbots in mental health: A scoping review. International Journal of Medical Informatics 132 (2019), 103978.
  2. Courtney E Ackerman. 2017. CBT Techniques: 25 Cognitive Behavioral Therapy Worksheets. https://positivepsychology.com/cbt-cognitive-behavioral-therapy-techniques-worksheets/
  3. Therapist Aid. 2017. Cognitive Restructuring: Socratic Questions. https://www.therapistaid.com/therapy-worksheet/socratic-questioning/cbt/none
  4. Effectiveness of Reminiscence Therapy and Deep Breath Relaxation Therapy on Stress Levels of Elderly During the Covid-19 Pandemic. Jurnal Keperawatan Terpadu (Integrated Nursing Journal) 5, 2 (2023), 38–47.
  5. Palm 2 technical report. arXiv preprint arXiv:2305.10403 (2023).
  6. Earl R Babbie. 2020. The practice of social research. Cengage learning.
  7. The effect of presence on human-robot interaction. In RO-MAN 2008-The 17th IEEE International Symposium on Robot and Human Interactive Communication. IEEE, 701–706.
  8. Child–robot interaction: Social bonding, learning and ethics. In Workshop proceedings of Interaction Design and Children Conference IDC14.
  9. Overview and categorization of robots supporting independent living of elderly people: What activities do they support and how far have they developed. Assistive Technology 27, 2 (2015), 88–100.
  10. Secret-sharing: Interactions between a child, robot, and adult. In 2011 IEEE International Conference on systems, man, and cybernetics. IEEE, 2489–2494.
  11. Kuldhir S Bhati. 2014. Effect of client-therapist gender match on the therapeutic relationship: An exploratory analysis. Psychological reports 115, 2 (2014), 565–583.
  12. Behavioral activation strategies in cognitive-behavioral therapy for anxiety disorders. Psychotherapy 54, 3 (2017), 231.
  13. Virginia Braun and Victoria Clarke. 2017. Using thematic analysis in psychology. Qual Res Psychol. 2006; 3 (2): 77–101.
  14. John Brooke. 1996. Sus: a “quick and dirty’usability. Usability evaluation in industry 189, 3 (1996), 189–194.
  15. Simulation versus embodied agents: Does either induce better human adherence to physical therapy exercise?. In 2012 4th IEEE RAS & EMBS International Conference on Biomedical Robotics and Biomechatronics (BioRob). IEEE, 1715–1720.
  16. Language models are few-shot learners. Advances in neural information processing systems 33 (2020), 1877–1901.
  17. Pilot randomised controlled trial of Help4Mood, an embodied virtual agent-based system to support treatment of depression. Journal of telemedicine and telecare 22, 6 (2016), 348–355.
  18. Social assistive robot for cardiac rehabilitation: A pilot study with patients with angioplasty. In Companion of the 2018 ACM/IEEE International Conference on Human-Robot Interaction. 79–80.
  19. A socially assistive robot for long-term cardiac rehabilitation in the real world. Frontiers in Neurorobotics 15 (2021), 633248.
  20. A mental health chatbot for regulating emotions (SERMO)-concept and usability test. IEEE Transactions on Emerging Topics in Computing 9, 3 (2020), 1170–1182.
  21. Embodiment in socially interactive robots. Foundations and Trends® in Robotics 7, 4 (2019), 251–356.
  22. Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018).
  23. Delivering cognitive behavioral therapy using a conversational social robot. In 2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). IEEE, 2089–2095.
  24. Juan Fasola and Maja J Mataric. 2012. Using socially assistive human–robot interaction to motivate physical exercise for older adults. Proc. IEEE 100, 8 (2012), 2512–2526.
  25. David Feil-Seifer and Maja J Mataric. 2005. A multi-modal approach to selective interaction in assistive domains. In ROMAN 2005. IEEE International Workshop on Robot and Human Interactive Communication, 2005. IEEE, 416–421.
  26. David Feil-Seifer and Maja J Matarić. 2011. Socially assistive robotics. IEEE Robotics & Automation Magazine 18, 1 (2011), 24–31.
  27. Ronit Feingold Polak and Shelly Levy Tzedek. 2020. Social robot for rehabilitation: expert clinicians and post-stroke patients’ evaluation following a long-term intervention. In Proceedings of the 2020 ACM/IEEE international conference on human-robot interaction. 151–160.
  28. Julia Fink. 2012. Anthropomorphism and human likeness in the design of robots and human-robot interaction. In Social Robotics: 4th International Conference, ICSR 2012, Chengdu, China, October 29-31, 2012. Proceedings 4. Springer, 199–208.
  29. Delivering cognitive behavior therapy to young adults with symptoms of depression and anxiety using a fully automated conversational agent (Woebot): a randomized controlled trial. JMIR mental health 4, 2 (2017), e7785.
  30. Using psychological artificial intelligence (Tess) to relieve symptoms of depression and anxiety: randomized controlled trial. JMIR mental health 5, 4 (2018), e9782.
  31. Robot authority in human-robot teaming: Effects of human-likeness and physical embodiment on compliance. Frontiers in Psychology 12 (2021), 625713.
  32. Sylvia Helbig and Lydia Fehm. 2004. Problems with homework in CBT: Rare exception or rather frequent? Behavioural and cognitive psychotherapy 32, 3 (2004), 291–301.
  33. Measuring massive multitask language understanding. arXiv preprint arXiv:2009.03300 (2020).
  34. The relationship between use of CBT skills and depression treatment outcome: A theoretical and methodological review of the literature. Behavior therapy 44, 1 (2013), 12–26.
  35. What is Cognitive Behavioral Therapy. 2017. What is Cognitive Behavioral Therapy? https://www.apa.org/ptsd-guideline/patients-and-families/cognitive-behavioral
  36. Mobile app-based chatbot to deliver cognitive behavioral therapy and psychoeducation for adults with attention deficit: A development and feasibility/usability study. International journal of medical informatics 150 (2021), 104440.
  37. Younbo Jung and Kwan Min Lee. 2004. Effects of physical embodiment on social presence of social robots. Proceedings of PRESENCE 2004 (2004), 80–87.
  38. Nathaniel J Jungbluth and Stephen R Shirk. 2013. Promoting homework adherence in cognitive-behavioral therapy for adolescent depression. Journal of Clinical Child & Adolescent Psychology 42, 4 (2013), 545–553.
  39. Meta-analysis of homework effects in cognitive and behavioral therapy: A replication and extension. Clinical Psychology: Science and Practice 17, 2 (2010), 144.
  40. Patient health questionnaire-9. Cultural Diversity and Ethnic Minority Psychology (1999).
  41. Exploring the design of prompts for applying gpt-3 based chatbots: A mental wellbeing case study on mechanical turk. arXiv preprint arXiv:2209.11344 (2022).
  42. Sanative chatbot for health seekers. International Journal Of Engineering And Computer Science 5, 03 (2016), 16022–16025.
  43. Cognitive distortions in patients with social anxiety disorder: Comparison of a clinical group and healthy controls. The European Journal of Psychiatry 32, 2 (2018), 97–104.
  44. The Outcome Questionnaire-45. (2004).
  45. Homework compliance counts in cognitive-behavioral therapy. Cognitive behaviour therapy 42, 3 (2013), 171–179.
  46. The prevalence and predictors of mental health diagnoses and suicide among US college students: Implications for addressing disparities in service use. Depression and anxiety 36, 1 (2019), 8–17.
  47. Emergence of socially assistive robotics in rehabilitation for children with cerebral palsy: a review. International Journal of Advanced Robotic Systems 13, 3 (2016), 135.
  48. Shadd Maruna and Ruth E Mann. 2006. A fundamental attribution error? Rethinking cognitive distortions. Legal and Criminological Psychology 11, 2 (2006), 155–177.
  49. Socially assistive robotics for post-stroke rehabilitation. Journal of neuroengineering and rehabilitation 4 (2007), 1–9.
  50. Maja J Matarić and Brian Scassellati. 2016. Socially assistive robotics. Springer handbook of robotics (2016), 1973–1994.
  51. Bilge Mutlu. 2011. Designing embodied cues for dialog with robots. AI Magazine 32, 4 (2011), 17–30.
  52. Experimental investigation into influence of negative attitudes toward robots on human–robot interaction. Ai & Society 20 (2006), 138–150.
  53. Openai. 2023. GPT-4 Technical Report. https://arxiv.org/pdf/2303.08774.pdf
  54. Combining qualitative and quantitative research within mixed method research designs: a methodological review. International journal of nursing studies 48, 3 (2011), 369–383.
  55. Autism and social robotics: A systematic review. Autism Research 9, 2 (2016), 165–183.
  56. Deep contextualized word representations. CoRR abs/1802.05365 (2018). arXiv preprint arXiv:1802.05365 (1802).
  57. Item banks for measuring emotional distress from the Patient-Reported Outcomes Measurement Information System (PROMIS®): depression, anxiety, and anger. Assessment 18, 3 (2011), 263–283.
  58. Service robots, agency and embarrassing service encounters. Journal of service management 33, 2 (2021), 389–414.
  59. Homework in Cognitive Behavioral Supervision: Theoretical Background and Clinical Application. Psychology Research and Behavior Management (2022), 3809–3824.
  60. Multitask prompted training enables zero-shot task generalization. arXiv preprint arXiv:2110.08207 (2021).
  61. Robots for use in autism research. Annual review of biomedical engineering 14 (2012), 275–294.
  62. Stephen M Schueller and Robert R Morris. 2023. Clinical science and practice in the age of large language models and generative artificial intelligence. Journal of Consulting and Clinical Psychology 91, 10 (2023), 559–561. https://doi.org/10.1037/ccp0000848
  63. Use of social robots in mental health and well-being research: systematic review. Journal of medical Internet research 21, 7 (2019), e13322.
  64. How do you like me in this: User embodiment preferences for companion agents. In Intelligent Virtual Agents: 12th International Conference, IVA 2012, Santa Cruz, CA, USA, September, 12-14, 2012. Proceedings 12. Springer, 112–125.
  65. Beyond the imitation game: Quantifying and extrapolating the capabilities of language models. arXiv preprint arXiv:2206.04615 (2022).
  66. Michael Suguitan and Guy Hoffman. 2019. Blossom: A handcrafted open-source robot. ACM Transactions on Human-Robot Interaction (THRI) 8, 1 (2019), 1–27.
  67. Katelyn Swift-Spong. 2019. Towards socially assistive robot support methods for physical activity behavior change. Ph. D. Dissertation. University of Southern California.
  68. Effects of comparative feedback from a socially assistive robot on self-efficacy in post-stroke rehabilitation. In 2015 IEEE International Conference on Rehabilitation Robotics (ICORR). IEEE, 764–769.
  69. Attention is all you need. Advances in neural information processing systems 30 (2017).
  70. Chain-of-thought prompting elicits reasoning in large language models. Advances in Neural Information Processing Systems 35 (2022), 24824–24837.
  71. Lilian Weng. 2023. Just had a quite emotional, personal conversation w/ ChatGPT in voice mode, talking about stress, work-life balance. Interestingly I felt… X(formerly Twitter). https://twitter.com/lilianweng/status/1706544602906530000 Accessed: September 29, 2023.
  72. A short survey of pre-trained language models for conversational ai-a new age in nlp. In Proceedings of the Australasian computer science week multiconference. 1–4.
  73. Inducing positive perspectives with text reframing. arXiv preprint arXiv:2204.02952 (2022).
User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (13)
  1. Mina J. Kian (1 paper)
  2. Mingyu Zong (5 papers)
  3. Katrin Fischer (4 papers)
  4. Abhyuday Singh (2 papers)
  5. Anna-Maria Velentza (7 papers)
  6. Pau Sang (2 papers)
  7. Shriya Upadhyay (2 papers)
  8. Anika Gupta (1 paper)
  9. Misha A. Faruki (1 paper)
  10. Wallace Browning (2 papers)
  11. Bhaskar Krishnamachari (107 papers)
  12. Sebastien M. R. Arnold (3 papers)
  13. Maja J. Mataric (3 papers)
Citations (3)
View on Semantic Scholar
Youtube Logo Streamline Icon: https://streamlinehq.com

YouTube