Developing a natural language-based AI-chatbot for social work training: an illustrative case study
Open accessAbstract
A chatbot is a computer program designed to simulate conversation with human users. In social services, many chatbots are retrieval based: they analyse users’ intents and retrieve preset answers based on decision tree logic. A major limitation of these earlier chatbots was that their conversations were rigid, unnatural, and sounded like a multiple-choice questionnaire. Recent achievements in large-scale generative pretrained transformers (LGPTs) (e.g. GPT-3, Yuan 1.0) have offered new possibilities for chatbot development. Such technology provides a high-quality natural language experience, requires much less resource input than earlier chatbot technologies, and is much more accessible to the public. However, the use of LGPT-based cfhatbots in social work, particularly in a Chinese context, is uncommon or even absent. Using an illustrative case study, this article illustrates the initial development of an LGPT-based chatbot to support social work training in a Chinese context and discusses the possibilities for further development.
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
Chatbots can maintain therapeutic conversations.
“maintain therapeutic conversations [14]”
From The Opportunities and Risks of Large Language Models in Mental Health (2024) · cites this paper as [14]
Compared with human psychiatrists, the chatbot displayed more empathy and asked more thorough questions about some symptoms (eg, sleep), but was less likely to rule out associated conditions.
“Compared with human psychiatrists, the chatbot displayed more empathy and asked more thorough questions about some symptoms (eg, sleep), but was less likely to rule out associated conditions.”
From The Opportunities and Risks of Large Language Models in Mental Health (2024) · cites this paper as [14]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Cites
Language Models are Few-Shot Learners
Brown, T. B., Mann, B., Ryder, N., Subbiah, M., Kaplan, J., Dhariwal, P., Neelakantan, A., Shyam, P., Sastry, G., Askell, A., et al. (2020) · arXiv · doi:10.48550/arxiv.2005.14165 · Cited by 23,372 · see citing works
Kaugeranna, R., Kaugeranna, E., & Aion, (. S. 4. 6. (2023) · DROPS (Schloss Dagstuhl – Leibniz Center for Informatics) · doi:10.4230/lipics.giscience.2023.43 · Cited by 13,695 · see citing works
Gibson, J. J. (1977) · Medical Entomology and Zoology · doi:10.4324/9781315740218-18 · Cited by 4,471 · see citing works
Affordance, conventions, and design
Norman, D. A. (1999) · Interactions · doi:10.1145/301153.301168 · Cited by 2,040 · see citing works
Natural language processing: an introduction
Nadkarni, P. M., Lucila Ohno-machado, A., & Chapman, W. W. (2011) · Journal of the American Medical Informatics Association · doi:10.1136/amiajnl-2011-000464 · Cited by 1,984 · see citing works
Perceiving, Acting, and Knowing: Toward an Ecological Psychology
Mayzner, M. S., Shaw, R. W., & Bransford, J. D. (1978) · The American Journal of Psychology · doi:10.2307/1421838 · Cited by 1,921 · see citing works
Leonardi, P. M. (2011) · MIS Quarterly · doi:10.2307/23043493 · Cited by 1,889 · see citing works
Finetuned Language Models Are Zero-Shot Learners
Wei, J., Bosma, M., Zhao, V. Y., Guu, K., Yu, A. W., Lester, B., Du, N., Dai, A. M., & Le, Q. V. (2021) · arXiv · doi:10.48550/arxiv.2109.01652 · Cited by 1,101 · see citing works
Chatbots: History, technology, and applications
Adamopoulou, E., & Moussiades, L. (2020) · Machine Learning with Applications · doi:10.1016/j.mlwa.2020.100006 · Cited by 1,090 · see citing works
The design and implementation of Xiaoice, an empathetic social chatbot
Zhou, L., Gao, J., Li, D., & Shum, H.-Y. (2020) · Computational Linguistics · doi:10.1162/coli_a_00368 · Cited by 777 · see citing works
Liu, H., Peng, H., Song, X., Xu, C., & Zhang, M. (2022) · Internet Interventions · doi:10.1016/j.invent.2022.100495 · Cited by 296 · see citing works
Affordance analysis – matching learning tasks with learning technologies
Bower, M. (2008) · Educational Media International · doi:10.1080/09523980701847115 · Cited by 295 · see citing works
Greer, S., Ramo, D., Chang, Y.-J., Fu, M., Moskowitz, J., & Haritatos, J. (2019) · JMIR mHealth and uHealth · doi:10.2196/15018 · Cited by 265 · see citing works
Bendig, E., Erb, B., Schulze-Thuesing, L., & Baumeister, H. (2022) · Verhaltenstherapie · doi:10.1159/000501812 · Cited by 214 · see citing works
The Application of Case Study Evaluations
Davey, L. (2020) · Scholarworks (University of Massachusetts Amherst) · doi:10.7275/02g8-bb93 · Cited by 185 · see citing works
User-centered design and usability testing of a web site: An illustrative case study
Corry, M. D., Frick, T. W., & Hansen, L. (1997) · Educational Technology Research and Development · doi:10.1007/bf02299683 · Cited by 156 · see citing works
What is an affordance and can it help us understand the use of ICT in education?
Hammond, M. (2009) · Education and Information Technologies · doi:10.1007/s10639-009-9106-z · Cited by 133 · see citing works
Quantifying the association between psychotherapy content and clinical outcomes using deep learning
Ewbank, M. P., Cummins, R., Tablan, V., Bateup, S., Catarino, A., Martin, A. J., & Blackwell, A. D. (2020) · JAMA Psychiatry · doi:10.1001/jamapsychiatry.2019.2664 · Cited by 108 · see citing works
A Review of Information and Communication Technology Enhanced Social Work Interventions
Chan, C., & Holosko, M. J. (2015) · Research on Social Work Practice · doi:10.1177/1049731515578884 · Cited by 106 · see citing works
Self-citationReview of Chatbots Design Techniques
Ahmad, N. A., Hafiz, M., Zainal, A., Fairuz, M., & Adnan, Z. (2018) · International Journal of Computer Applications · doi:10.5120/ijca2018917606 · Cited by 101 · see citing works
Tanana, M. J., Soma, C. S., Srikumar, V., Atkins, D. C., & Imel, Z. E. (2019) · Journal of Medical Internet Research · doi:10.2196/12529 · Cited by 100 · see citing works
Design of a chatbot as a distance learning assistant
Tamayo, P. A., Herrero, A., Martín, J., Navarro, C., & Tránchez, J. M. (2019) · Open Praxis · doi:10.5944/openpraxis.12.1.1063 · Cited by 83 · see citing works
A Scoping Review of Social Media Use in Social Work Practice
Chan, C. (2015) · Journal of Evidence-Informed Social Work · doi:10.1080/23761407.2015.1052908 · Cited by 82 · see citing works
Self-citationHe, L., Başar, E., Wiers, R. W. H. J., Antheunis, M. L., & Krahmer, E. (2022) · BMC Public Health · doi:10.1186/s12889-022-13115-x · Cited by 81 · see citing works
Response selection with topic clues for retrieval-based chatbots
Wu, Y., Li, Z., Wu, W., & Zhou, M. X. (2018) · Neurocomputing · doi:10.1016/j.neucom.2018.07.073 · Cited by 71 · see citing works
Survey on psychotherapy chatbots
Xu, B., & Zhuang, Z. (2020) · Concurrency and Computation Practice and Experience · doi:10.1002/cpe.6170 · Cited by 46 · see citing works
Ramanathan, K., & Samaranayake, P. (2021) · Journal of Manufacturing Technology Management · doi:10.1108/jmtm-09-2021-0339 · Cited by 43 · see citing works
Literature review of roles and issues within the social work profession in England
Moriarty, J., Baginsky, M., & Manthorpe, J. (2015) · Research Portal (King's College London) · Cited by 37 · see citing works
Utilizing social media for social work: insights from clients in online youth services
Chan, C., & Ngai, S. S. (2018) · Journal of Social Work Practice · doi:10.1080/02650533.2018.1504286 · Cited by 33 · see citing works
Self-citationAn intelligent chat-bot using natural language processing
Shah, R., Lahoti, S., & Lavanya, K., V (2017) · International Journal of Engineering Research · doi:10.5958/2319-6890.2017.00019.8 · Cited by 25 · see citing works
Technology for Social Work Interventions
Chan, C., & Holosko, M. J. (2018) · doi:10.1093/obo/9780195389678-0263 · Cited by 25 · see citing works
Self-citationEpler, P. L. (2019) · Advances in higher education and professional development book series · doi:10.4018/978-1-5225-9429-1.ch002 · Cited by 24 · see citing works
Yuan 1.0: Large-Scale Pre-trained Language Model in Zero-Shot and Few-Shot LearningPreprint
Wu, S., Zhao, X., Yu, T., Zhang, R., Shen, C., Liu, H., Li, F., Zhu, H. C., Luo, J., Xu, L. J., et al. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2110.04725 · Cited by 23 · see citing works
Self-citationDesigning and Implementing Conversational Intelligent Chat-bot Using Natural Language Processing
Nath, A., Sarkar, R., Mitra, S., & Pradhan, R. (2021) · International Journal of Scientific Research in Computer Science Engineering and Information Technology · doi:10.32628/cseit217351 · Cited by 6 · see citing works
Flagged first, then by citations
Cited by
Sorted by citations
The Opportunities and Risks of Large Language Models in Mental Health
Lawrence, H. R., Schneider, R. A., Rubin, S. B., Matarić, M. J., McDuff, D. J., & Jones Bell, M. (2024) · JMIR Mental Health · doi:10.2196/59479 · Cited by 235 · see citing works
“It’s Not Only Attention We Need”: Systematic Review of Large Language Models in Mental Health Care
Bucher, A. M., Egger, S., Vashkite, I., Wu, W., & Schwabe, G. (2025) · JMIR Mental Health · doi:10.2196/78410 · Cited by 37 · see citing works
Promoting Cognitive Health in Elder Care with Large Language Model-Powered Socially Assistive Robots
Lima, M. R. D., O'Connell, A., Zhou, F. B., Nagahara, A., Hulyalkar, A., Deshpande, A., Thomason, J., Vaidyanathan, R., & Matarić, M. J. (2025) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3706598.3713582 · Cited by 23 · see citing works
Artificial Intelligence in Social Work: An EPIC Model for Practice
Boetto, H. (2025) · Australian Social Work · doi:10.1080/0312407x.2025.2488345 · Cited by 31 · see citing works
Bowers, P. J., Graydon, K., Ryan, T., Lau, J. H., & Tomlin, D. (2024) · Australasian Journal of Educational Technology · doi:10.14742/ajet.9307 · Cited by 22 · see citing works
Abinaya, S., Ashwin, K. S., & Alphonse, A. S. (2025) · IEEE Access · doi:10.1109/access.2025.3534197 · Cited by 20 · see citing works
Lim, J., & Hwang, W. (2025) · International Journal of Human-Computer Interaction · doi:10.1080/10447318.2024.2446510 · Cited by 18 · see citing works
Our journey with an AI assistant offering narrative therapy on WhatsApp
Chan, C., Zhao, J., & Zhao, Y. (2024) · Journal of Social Work Practice · doi:10.1080/02650533.2024.2420314 · Cited by 7 · see citing works
Self-citationA Case Study on Assessing AI Assistant Competence in Narrative Interviews
Chan, C., Zhao, Y., & Zhao, J. (2024) · F1000Research · doi:10.12688/f1000research.151952.2 · Cited by 5 · see citing works
Self-citationDialogue with Avatars in Simulation-Based Social Work Education: A Scoping Review
Vidman, Å., & Tham, P. (2024) · Social Sciences · doi:10.3390/socsci13110628 · Cited by 5 · see citing works
An Exploratory Study of a Narrative Therapy Chatbot with Social Work Students
Chan, C. (2025) · Journal of Technology in Human Services · doi:10.1080/15228835.2025.2559342 · Cited by 6 · see citing works
Self-citationBowers, P. J., Ryan, T., Graydon, K., Lau, J. H., & Tomlin, D. (2025) · Interactive Technology and Smart Education · doi:10.1108/itse-02-2025-0036 · Cited by 3 · see citing works
Andrada, A. V., Martí-García, S., Rasco, T. G., & Fuentevilla, E. F. (2024) · methaodos revista de ciencias sociales · doi:10.17502/mrcs.v12i2.812 · Cited by 3 · see citing works
Exploring More-than-human Ethics of Large Language Models in Social Service Delivery
Seniutis, M., Sas, A., & Gružauskas, V. (2026) · Ethics and Social Welfare · doi:10.1080/17496535.2025.2593823 · Cited by 2 · see citing works
Empowering mental health professionals in asynchronous online psychotherapy with GenAI
Bucher, A. M., Vashkite, I., Staehelin, D., Dolata, M., & Schwabe, G. (2026) · International Journal of Mental Health Systems · doi:10.1186/s13033-026-00700-5 · Cited by 2 · see citing works
GenAI for Social Work Field Education: Client Simulation with Real-Time Feedback
Sungarda, J., Liu, H., Zhou, Z., Wu, T.-H., Cheung, J. C.-S., & Kao, B. (2025) · IEEE International Conference on Big Data (BigData) · doi:10.1109/bigdata66926.2025.11402062 · Cited by 1 · see citing works
Feasibility of an AI-Enhanced Platform for Training Beginners in Narrative Therapy
Chan, C., Adnan, M., & Wu, J. (2026) · Journal of Technology in Human Services · doi:10.1080/15228835.2026.2663553 · Cited by 1 · see citing works
Self-citationRelational learning in technology-mediated social work education in Asia: A scoping review
Gonsamo, D. D., Chui, W. H., & David, L. K. K. (2026) · The British Journal of Social Work · doi:10.1093/bjsw/bcag104 · Cited by 1 · see citing works
A Case Study on Assessing AI Assistant Competence in Narrative Interviews
Chan, C., Zhao, Y., & Zhao, J. (2024) · F1000Research · doi:10.12688/f1000research.151952.1 · Cited by 6 · see citing works
Self-citationالذكاء الاصطناعي كمدخل لتعليم الممارسة المهنية الرقمية لطريقة العمل مع الجماعات
عثمان, س. ط. ح. (2023) · مجلة کلية الخدمة الاجتماعية للدراسات والبحوث الاجتماعية · doi:10.21608/jfss.2023.361984
KURBAN, S. (2024) · Yönetim Bilimleri Dergisi · doi:10.35408/comuybd.1514386
Effects of a Customized Chatbot Intervention on Social Work Students’ Counseling Self-Efficacy
Mo, K. Y., Chow, L., Mok, L. W.-K., & Wang, C. J.-Y. (2025) · Research on Social Work Practice · doi:10.1177/10497315251394310
Enhancing AI Chatbot Responsiveness Through Design of a Multimodal Emotion Detection
Sah, Y., Padole, A., Dongre, M., Shinde, G., Bobhate, G., & Fatangare, S. (2026) · International Conference on Visual Analytics and Data Visualization (ICVADV) · doi:10.1109/icvadv67766.2026.11470356
Wallengren-Lynch, M. (2026) · Social Work Education · doi:10.1080/02615479.2026.2660786
Doğan, H. (2026) · Journal of Social Work Practice · doi:10.1080/02650533.2026.2683350
When social work meets AI: a philosophical look at adoption, context, and critical resistance
Ingram, R. D. (2026) · AI & Society · doi:10.1007/s00146-026-03230-3
Wu, Y., Wang, S. S.-C., & Liu, C. (2026) · China Journal of Social Work · doi:10.1080/17525098.2026.2723809
The opportunities and risks of large language models in mental health
Lawrence, H. R., Schneider, R. A., Rubin, S. B., Mataric, M. J., McDuff, D. J., & Bell, M. J. (2024) · arXiv · doi:10.48550/arxiv.2403.14814
- Authors
- Chan, C., & Li, F.
- Affiliations
- Hong Kong Baptist University (HK)
- Inspur (China) (CN)
- Corresponding author
- Chan, Chitat
- ORCID
- Venue
- China Journal of Social Work
- Publisher
- Informa UK Limited
- Published
- 2023-03-05
- Volume
- 16
- Issue
- 2
- Pages
- 121-136
- ISSN
- 1752-5098 (ISSN-L)
- 1752-5101
- OpenAlex
- W4323316263
- Cited by
- 27
- References
- 33
- Citations by year
- 2026: 9 · 2025: 9 · 2024: 8 · 2023: 1
- FWCI
- 2.54
- Type
- journal article
- Language
- en
- Open access
- hybrid
- doi.org
- Licence
- Locations
- China Journal of Social Work (publishedVersion, cc-by-nc-nd)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › AI in Service Interactions
- Physical Sciences › Computer Science › Artificial Intelligence › Speech and dialogue systems
- Physical Sciences › Computer Science › Information Systems › Artificial Intelligence in Education
- Keywords
- chatbots, large language models, generative pre-trained transformer, social work training, natural language interaction, Chinese context, chatbot development
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
