Applications of AI-powered Conversational Chatbot for Mental Health
DOI:
https://doi.org/10.54097/4vcjj296Keywords:
Conversational chatbot, mental health, artificial intelligence.Abstract
Psychological issues have become a pervasive problem affecting the quality of life for many individuals. However, the scarcity of professional psychotherapists and the high threshold for receiving human psychological counselling prevent most people from obtaining timely, high-quality psychological help. To address this issue, chatbots have been developed to participate in the promotion of public mental health. Empowered by Artificial Intelligence (AI), especially Large Language Models (LLMs), chatbots have the potential to revolutionize the field of mental health by offering personalized and full-time support. Moreover, AI-powered chatbots can assist researchers in collecting more data to understand mental health better and develop more effective treatments. This paper categorizes and summarizes the recent applications of conversational chatbot technology in the mental health field, including human-robot relationships, the use of conversational chatbots with mental health tasks in counselling and online settings, the generation of counselling dialogue data, and the evaluation of datasets and models. The advantages and disadvantages of these technologies are explored, along with the current technical shortcomings of conversational chatbots. Additionally, the challenges to their widespread adoption and use, as well as future directions for development, are discussed.
Downloads
References
[1] World Health Organization. Depressive Disorder (Depression). URL: www.who.int/news-room/fact-sheets/detail/mental-disorders. Last Accessed: 2024/08/07.
[2] Lin Chien-Chang, Anna YQ Huang, Stephen JH Yang. A review of ai-driven conversational chatbots implementation methodologies and challenges (1999–2022). Sustainability, 2023, 15 (5): 4012.
[3] Lo Andrew W, Singh Manish, Musumeci Jim, et al. From ELIZA to ChatGPT: The Evolution of Natural Language Processing and Financial Applications. The Journal of Portfolio Management, 2023, 49 (7): 201-235.
[4] Go Eun, S. Shyam Sundar. Humanizing chatbots: The effects of visual, identity and conversational cues on humanness perceptions. Computers in human behavior, 2019, 97: 304-316.
[5] Skjuve Marita, Folstad Asbjorn, Fostervold Knut Inge, et al. My chatbot companion-a study of human-chatbot relationships. International Journal of Human-Computer Studies, 2021, 149: 102601.
[6] Kung Tiffany H, Cheatham Morgan, Medenilla Arielle, et al. Performance of ChatGPT on USMLE: potential for AI-assisted medical education using large language models. PLoS digital health, 2023, 2 (2): e0000198.
[7] Hu Yanni, Hu Ziyang, Liu Wenjing, et al. Exploring the potential of ChatGPT as an adjunct for generating diagnosis based on chief complaint and cone beam CT radiologic findings. BMC Medical Informatics and Decision Making, 2024, 24 (1): 55.
[8] Maurya Rakesh K. Using AI Based Chatbot ChatGPT for Practicing Counseling Skills through Role-play. Journal of Creativity in Mental Health, 2023: 1-16.
[9] Eshghie Mahshid, Mojtaba Eshghie. ChatGPT as a therapist assistant: a suitability study. arXiv preprint, 2023: 2304.09873.
[10] Adhikary Prottay Kumar, Srivastava Aseem, Kumar Shivani, et al. Exploring the Efficacy of Large Language Models in Summarizing Mental Health Counseling Sessions: Benchmark Study. JMIR Mental Health, 2024, 11: e57306.
[11] Omarov Batyrkhan, Zhumanov Zhandos, Gumar Aidana, et al. Artificial intelligence enabled mobile chatbot psychologist using AIML and cognitive behavioral therapy. International Journal of Advanced Computer Science and Applications, 2023, 14 (6): 137-146.
[12] Fu Guanghui, Zhao Qing, Li Jianqiang, et al. Enhancing psychological counseling with large language model: A multifaceted decision-support system for non-professionals. arXiv preprint, 2023: 2308.15192.
[13] Lai Tin, Shi Yukun, Du Zicong, et al. Psy-llm: Scaling up global mental health psychological services with ai-based large language models. arXiv preprint, 2023: 2307.11991.
[14] Sun Hao, Lin Zhenru, Zheng Chujie, et al. Psyqa: A chinese dataset for generating long counseling text for mental health support. arXiv preprint, 2021: 2106.01702.
[15] Qiu Huachuan, He Hongliang, Zhang Shuai et al. Smile: Single-turn to multi-turn inclusive language expansion via chatgpt for mental health support. arXiv preprint, 2023: 2305.00450 (2023).
[16] Zhang Chenhao, Li Renhao, Tan Minghuan, et al. CPsyCoun: A Report-based Multi-turn Dialogue Reconstruction and Evaluation Framework for Chinese Psychological Counseling. arXiv preprint, 2024: 2405.16433.
[17] Jin Haoan, Chen Siyuan, Wu Mengyue, et al. PsyEval: A Comprehensive Large Language Model Evaluation Benchmark for Mental Health. arXiv preprint, 2023: 2311.09189.
[18] Laestadius Linnea, Bishop Andrea, Gonzalez Michael, et al. Too human and not human enough: A grounded theory analysis of mental health harms from emotional dependence on the social chatbot Replika. New Media & Society, 2022: 14614448221142007.
[19] Dosovitsky Gilly, Eduardo Bunge. Development of a chatbot for depression: adolescent perceptions and recommendations. Child and adolescent mental health, 2023, 28 (1): 124-127.
[20] Klos Maria Carolina, Escoredo Milagros, Joerin Angela, et al. Artificial intelligence–based chatbot for anxiety and depression in university students: pilot randomized controlled trial. JMIR formative research, 2021, 5 (8): e20678.
[21] Fitzpatrick Kathleen Kara, Alison Darcy, Molly Vierhile. 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, 2017, 4 (2): e7785.
[22] Fulmer Russell, Joerin Angela, Gentile Breanna, et al. Using psychological artificial intelligence (Tess) to relieve symptoms of depression and anxiety: randomized controlled trial. JMIR mental health, 2018, 5 (4): e9782.
Downloads
Published
Issue
Section
License
Copyright (c) 2024 Highlights in Science, Engineering and Technology

This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.







