Engagement and Disclosures in LLM-Powered Cognitive Behavioral Therapy Exercises: A Factorial Design Comparing the Influence of a Robot vs. Chatbot Over Time
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908416128057344 |
|---|---|
| author | Kian, Mina Zong, Mingyu Fischer, Katrin Velentza, Anna-Maria Singh, Abhyuday Shrestha, Kaleen Sang, Pau Upadhyay, Shriya Browning, Wallace Faruki, Misha Arif Arnold, Sébastien M. R. Krishnamachari, Bhaskar Matarić, Maja |
| author_facet | Kian, Mina Zong, Mingyu Fischer, Katrin Velentza, Anna-Maria Singh, Abhyuday Shrestha, Kaleen Sang, Pau Upadhyay, Shriya Browning, Wallace Faruki, Misha Arif Arnold, Sébastien M. R. Krishnamachari, Bhaskar Matarić, Maja |
| contents | Many researchers are working to address the worldwide mental health crisis by developing therapeutic technologies that increase the accessibility of care, including leveraging large language model (LLM) capabilities in chatbots and socially assistive robots (SARs) used for therapeutic applications. Yet, the effects of these technologies over time remain unexplored. In this study, we use a factorial design to assess the impact of embodiment and time spent engaging in therapeutic exercises on participant disclosures. We assessed transcripts gathered from a two-week study in which 26 university student participants completed daily interactive Cognitive Behavioral Therapy (CBT) exercises in their residences using either an LLM-powered SAR or a disembodied chatbot. We evaluated the levels of active engagement and high intimacy of their disclosures (opinions, judgments, and emotions) during each session and over time. Our findings show significant interactions between time and embodiment for both outcome measures: participant engagement and intimacy increased over time in the physical robot condition, while both measures decreased in the chatbot condition. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_17831 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Engagement and Disclosures in LLM-Powered Cognitive Behavioral Therapy Exercises: A Factorial Design Comparing the Influence of a Robot vs. Chatbot Over Time Kian, Mina Zong, Mingyu Fischer, Katrin Velentza, Anna-Maria Singh, Abhyuday Shrestha, Kaleen Sang, Pau Upadhyay, Shriya Browning, Wallace Faruki, Misha Arif Arnold, Sébastien M. R. Krishnamachari, Bhaskar Matarić, Maja Robotics Many researchers are working to address the worldwide mental health crisis by developing therapeutic technologies that increase the accessibility of care, including leveraging large language model (LLM) capabilities in chatbots and socially assistive robots (SARs) used for therapeutic applications. Yet, the effects of these technologies over time remain unexplored. In this study, we use a factorial design to assess the impact of embodiment and time spent engaging in therapeutic exercises on participant disclosures. We assessed transcripts gathered from a two-week study in which 26 university student participants completed daily interactive Cognitive Behavioral Therapy (CBT) exercises in their residences using either an LLM-powered SAR or a disembodied chatbot. We evaluated the levels of active engagement and high intimacy of their disclosures (opinions, judgments, and emotions) during each session and over time. Our findings show significant interactions between time and embodiment for both outcome measures: participant engagement and intimacy increased over time in the physical robot condition, while both measures decreased in the chatbot condition. |
| title | Engagement and Disclosures in LLM-Powered Cognitive Behavioral Therapy Exercises: A Factorial Design Comparing the Influence of a Robot vs. Chatbot Over Time |
| topic | Robotics |
| url | https://arxiv.org/abs/2506.17831 |