A scoping review of culturally sensitive large language models-based cognitive behavioural therapy for anxiety and depression: Global lessons for African implementation
DOI:
https://doi.org/10.38140/ijss-2025.vol5.1.06Keywords:
Anxiety, depression, cognitive behavioural therapy, large language model, mental healthAbstract
Anxiety and depression are significant global mental health challenges. In Africa, these conditions are critical social issues deeply connected to factors such as socio-economic disparities, cultural stigma, and limited healthcare resources. These factors create substantial barriers to effective care, highlighting the need for innovative approaches to mental health treatment. Large Language Model-based (LLM-based) Cognitive Behavioural Therapy (CBT) addresses this need by leveraging CBT’s structured and effective interventions while allowing for innovative approaches to scale the intervention for these conditions. However, existing research predominantly explores LLM integration in Western contexts, with minimal focus on African cultural dynamics. This scoping review investigates the integration of culturally sensitive elements in LLM-based CBT interventions for anxiety and depression, focusing on addressing the unique considerations for African implementation. Scopus, Web of Science (WOS), EBSCO, and Google Scholar were searched to identify studies published between 2019 and 2024. The review examines global practices of integrating cultural elements into LLM-based CBT and specific considerations for implementing these interventions in Africa. Findings reveal key challenges, including limited culturally representative datasets, diverse norms, traditional beliefs, and ethical concerns. Collaboration with African researchers and communities is crucial for addressing these gaps and ensuring culturally appropriate solutions. LLM-based CBT can address Africa’s mental health needs if culturally sensitive practices are prioritised. This review offers guidance for ethical, accessible, and effective interventions, combining global best practices with local insights.
References
Abubakar, A. M., Gupta, D., & Parida, S. (2024). A Reinforcement Learning Approach for Intelligent Conversational Chatbot For Enhancing Mental Health Therapy. Procedia Computer Science, 235, 916-925. https://doi.org/10.1016/j.procs.2024.04.087
Adhikary, P. K., Srivastava, A., Kumar, S., Singh, S. M., Manuja, P., Gopinath, J. K., Krishnan, V., Gupta, S. K., Deb, K. S., & Chakraborty, T. (2024). Exploring the efficacy of large language models in summarising mental health counselling sessions: Benchmark study. JMIR Mental Health, 11, e57306. https://doi.org/10.2196/57306
Agrawal, A., & Gupta, N. (2024). Illuminate: Depression diagnosis, explanation, and proactive therapy using prompt engineering. Journal of Student Research, 13(2). https://doi.org/10.47611/jsrhs.v13i2.6718
Ahmed, A., Hassan, A., Aziz, S., Abd-Alrazaq, A. A., Ali, N., Alzubaidi, M., Al-Thani, D., Elhusein, B., Siddig, M. A., & Ahmed, M. (2023). Chatbot features for anxiety and depression: A scoping review. Health Informatics Journal, 29(1), 1-17. https://doi.org/10.1177/14604582221146719
Aleem, M., Zahoor, I., & Naseem, M. (2024, November). Towards culturally adaptive large language models in mental health: Using ChatGPT as a case study. In Companion publication of the 2024 Conference on Computer-Supported Cooperative Work and Social Computing (pp. 240–247). ACM Digital Library.
Althoff, T., Clark, K., & Leskovec, J. (2016). Large-scale analysis of counselling conversations: An application of natural language processing to mental health. Transactions of the Association for Computational Linguistics, 4, 463–476. https://doi.org/10.1162/tacl_a_00111
Anakwenze, O. (2022). The cultural sensitivity continuum of mental health interventions in Sub-Saharan Africa: A systematic review. Social Science & Medicine, 306, 115124. https://doi.org/10.1016/j.socscimed.2022.115124
Ando, M., Kao, Y.-C., Lee, Y.-C., Tai, S.-A., Mendez, S. R., Sasaki, K., Tang, W., & Papatheodorou, S. (2024). Remote cognitive behavioural therapy for older adults with anxiety symptoms: A systematic review and meta-analysis. Journal of Telemedicine and Telecare, 30(9), 1376–1385. https://doi.org/10.1177/1357633X231151
Anisuzzaman, D., Malins, J. G., Friedman, P. A., & Attia, Z. I. (2024). Fine-tuning LLMs for specialised use cases. Mayo Clinic Proceedings: Digital Health. https://doi.org/10.1177/1357633X231151788
Anisuzzaman, D., Malins, J. G., Friedman, P. A., & Attia, Z. I. (2025). Fine-tuning large language models for specialised use cases. Mayo Clinic Proceedings: Digital Health, 3(1), 1-13. https://doi.org/10.1016/j.mcpdig.2024.11.005
Baguma, R., Namuwaya, H., Nakatumba-Nabende, J., & Rashid, Q. M. (2023). Examining potential harms of large language models (LLMs) in Africa. International Conference on Safe, Secure, Ethical, Responsible Technologies and Emerging Applications, 3-19. https://doi.org/10.1007/978-3-031-56396-6_1
Caloudas, A. B., Frosio, K. E., Torous, J., Goss, C. W., Novins, D. K., Lindsay, J. A., & Shore, J. H. (2024). Mobile mental health applications for American Indian and Alaska Native communities: Review and recommendations. Journal of Technology in Behavioural Science, 9(3), 474–485. https://doi.org/10.1007/s41347-023-00348-9
Chiu, Y. Y., Sharma, A., Lin, I. W., & Althoff, T. (2024). A computational framework for behavioural assessment of LLM therapists. arXiv preprint arXiv:2401.00820. https://arxiv.org/abs/2401.00820
Coplan, J. D., Aaronson, C. J., Panthangi, V., & Kim, Y. (2015). Treating comorbid anxiety and depression: Psychosocial and pharmacological approaches. World Journal of Psychiatry, 5(4), 366. https://doi.org/10.5498/wjp.v5.i4.366
De Choudhury, M., Pendse, S. R., & Kumar, N. (2023). Benefits and harms of large language models in digital mental health. arXiv preprint arXiv:2311.14693. https://arxiv.org/abs/2311.14693
Devlin, J. (2018). BERT: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805.
Gabriel, S., Puri, I., Xu, X., Malgaroli, M., & Ghassemi, M. (2024). Can AI relate: Testing large language model response for mental health support. arXiv preprint arXiv:2405.12021. https://doi.org/10.48550/arXiv.2405.12021
Guo, Z., Lai, A., Thygesen, J. H., Farrington, J., Keen, T., & Li, K. (2024). Large language model for mental health: A systematic review. arXiv preprint arXiv:2403.15401. https://doi.org/10.48550/arXiv.2403.15401
Hays, P. A. (2009). Integrating evidence-based practice, cognitive–behaviour therapy, and multicultural therapy: Ten steps for culturally competent practice. Professional Psychology: Research and Practice, 40(4), 354. https://doi.org/10.1037/a0016250
Hinton, D. E., & Patel, A. (2017). Cultural adaptations of cognitive behavioural therapy. Psychiatric Clinics, 40(4), 701-714. https://doi.org/10.1016/j.psc.2017.08.006
Hua, Y., Liu, F., Yang, K., Li, Z., Sheu, Y.-h., Zhou, P., Moran, L. V., Ananiadou, S., & Beam, A. (2024). Large language models in mental health care: A scoping review. arXiv preprint arXiv:2401.02984. https://doi.org/10.48550/arXiv.2401.02984
Huey Jr, S. J., Park, A. L., Galán, C. A., & Wang, C. X. (2023). Culturally responsive cognitive behavioural therapy for ethnically diverse populations. Annual Review of Clinical Psychology, 19(1), 51–78. https://doi.org/10.1146/annurev-clinpsy-080921-072750
Izumi, K., Tanaka, H., Shidara, K., Adachi, H., Kanayama, D., Kudo, T., & Nakamura, S. (2024). Response generation for cognitive behavioural therapy with large language models: Comparative study with Socratic questioning. arXiv preprint arXiv:2401.15966. https://doi.org/10.48550/arXiv.2401.15966
Jalal, B., Kruger, Q., & Hinton, D. E. (2020). Culturally adapted CBT (CA-CBT) for traumatised indigenous South Africans (Sepedi): A randomised pilot trial comparing CA-CBT to applied muscle relaxation. Intervention Journal of Mental Health and Psychosocial Support in Conflict Affected Areas, 18(1), 61–65. https://doi.org/10.4103/INTV.INTV_68_18
Jameel, S., Munivenkatappa, M., Arumugham, S. S., & Thennarasu, K. (2022). Cultural adaptation of cognitive behaviour therapy for depression: A qualitative study exploring views of patients and practitioners from India. The Cognitive Behaviour Therapist, 15, e16. https://doi.org/10.1017/S1754470X22000137
Jiang, M., Yu, Y. J., Zhao, Q., Li, J., Song, C., Qi, H., Zhai, W., Luo, D., Wang, X., & Fu, G. (2024). AI-enhanced cognitive behavioural therapy: Deep learning and large language models for extracting cognitive pathways from social media texts. arXiv preprint arXiv:2404.11449. https://doi.org/10.48550/arXiv.2404.11449
Kenton, J. D. M. W. C., & Toutanova, L. K. (2019, June). Bert: Pre-training of deep bidirectional transformers for language understanding. In Proceedings of the NAACL-HLT (Vol. 1, No. 2).
Kian, M. J., Zong, M., Fischer, K., Singh, A., Velentza, A.-M., Sang, P., Upadhyay, S., Gupta, A., Faruki, M. A., Browning, W., Arnold, S. M. R., Krishnamachari, B., & Mataric, M. J. (2024). Can an LLM-powered socially assistive robot effectively and safely deliver cognitive behavioural therapy? A study with university students. arXiv preprint arXiv:2402.17937. https://doi.org/10.48550/arXiv.2402.17937
Kunorubwe, T. (2023). Cultural adaptations of group CBT for depressed clients from diverse backgrounds: A systematic review. The Cognitive Behaviour Therapist, 16, e35. https://doi.org/10.1017/S1754470X23000302
Lee, S., Kim, S., Kim, M., Kang, D., Yang, D., Kim, H., Kang, M., Jung, D., Kim, M. H., & Lee, S. (2024). Cactus: Towards psychological counselling conversations using cognitive behavioural theory. arXiv preprint arXiv:2407.03103. https://doi.org/10.48550/arXiv.2407.03103
Lee, Y. K., Suh, J., Zhan, H., Li, J. J., & Ong, D. C. (2024). Large language models produce responses perceived to be empathic. arXiv preprint arXiv:2403.18148. https://doi.org/10.48550/arXiv.2403.18148
Ling, C., Zhao, X., Lu, J., Deng, C., Zheng, C., Wang, J., Chowdhury, T., Li, Y., Cui, H., & Zhang, X. (2023). Domain specialization as the key to making large language models disruptive: A comprehensive survey. arXiv preprint arXiv:2305.18703. https://arxiv.org/abs/2305.18703
Liu, J. M., Li, D., Cao, H., Ren, T., Liao, Z., & Wu, J. (2023). Chatcounselor: A large language model for mental health support. arXiv preprint arXiv:2309.15461. https://doi.org/10.48550/arXiv.2309.15461
Manvi, R., Khanna, S., Burke, M., Lobell, D., & Ermon, S. (2024). Large language models are geographically biased. arXiv preprint arXiv:2402.02680. https://doi.org/10.48550/arXiv.2402.02680
Na, H. (2024). CBT-LLM: A Chinese large language model for cognitive behavioural therapy-based mental health question answering. arXiv preprint arXiv:2403.16008. https://doi.org/10.48550/arXiv.2403.16008
Nie, J., Shao, H., Fan, Y., Shao, Q., You, H., Preindl, M., & Jiang, X. (2024). LLM-based conversational AI therapist for daily functioning screening and psychotherapeutic intervention via everyday smart devices. arXiv preprint arXiv:2403.10779. https://doi.org/10.48550/arXiv.2403.10779
Nozizwe, N. (2024). The effectiveness of cognitive-behavioural therapy for treating anxiety disorders in low-resource settings in South Africa. International Journal of Psychology, 9(1), 47–59. https://doi.org/10.47604/ijp.2361
Obasa, A. E. (2024). Large language models through the lens of Ubuntu for health research in sub-Saharan Africa. South African Journal of Science, 120(5/6).
Ouzzani, M., Hammady, H., Fedorowicz, Z., & Elmagarmid, A. (2016). Rayyan—a web and mobile app for systematic reviews. Systematic Reviews, 5, 1-10. https://doi.org/10.1186/s13643-016-0384-4
Patil, R., & Gudivada, V. (2024). A review of current trends, techniques, and challenges in large language models (LLMs). Applied Sciences, 14(5), 2074. https://doi.org/10.3390/app14052074
Phiri, M., & Munoriyarwa, A. (2023). Health chatbots in Africa: Scoping review. Journal of Medical Internet Research, 25, e35573. https://doi.org/10.2196/35573
Raiaan, M. A. K., Mukta, M. S. H., Fatema, K., Fahad, N. M., Sakib, S., Mim, M. M. J., ... & Azam, S. (2024). A review on large language models: Architectures, applications, taxonomies, open issues and challenges. IEEE access, 12, 26839-26874. https://doi.org/10.1109/ACCESS.2024.3365742
Schiff, D. (2024). CBTLlama: Fine tuning large language models for identifying thought distortions. file:///C:/Users/omoda/Downloads/CBT_LLM.pdf
Shah, K., Xu, A. Y., Sharma, Y., Daher, M., McDonald, C., Diebo, B. G., & Daniels, A. H. (2024). Large language model prompting techniques for advancement in clinical medicine. Journal of Clinical Medicine, 13(17), 5101. https://doi.org/10.3390/jcm13175101
Sham Sundhar, R., Shivavardhini, T., Daphine Desona Clemency, C., & Roobini, M. (2024). Lecter: A large language model chatbot for cognitive behavioural therapy. In M. L. Owoc, F. E. Varghese Sicily, K. Rajaram, & P. Balasundaram (Eds.), Computational intelligence in data science. ICCIDS 2024 (Vol. 717, pp. 41–53). Springer. https://doi.org/10.1007/978-3-031-69982-5_4
Snilstveit, B., Oliver, S., & Vojtkova, M. (2012). Narrative approaches to systematic review and synthesis of evidence for international development policy and practice. Journal of Development Effectiveness, 4(3), 409-429. https://doi.org/10.1080/19439342.2012.710641
Sodi, T., Abas, M., Abdulaziz, M., Amos, A., Burgess, R. A., Hanlon, C., Kakunze, A., Kpobi, L., Lund, C., & Mwangi, K. J. (2024). A research agenda for mental health in sub-Saharan Africa. Nature Medicine, 30(3), 616-617. https://doi.org/10.1038/s41591-023-02779-6
Spanhel, K., Balci, S., Feldhahn, F., Bengel, J., Baumeister, H., & Sander, L. B. (2021). Cultural adaptation of internet- and mobile-based interventions for mental disorders: A systematic review. NPJ Digital Medicine, 4(1), 128. https://doi.org/10.1038/s41746-021-00498-1
Stade, E. C., Stirman, S. W., Ungar, L. H., Boland, C. L., Schwartz, H. A., Yaden, D. B., Sedoc, J., DeRubeis, R. J., Willer, R., & Eichstaedt, J. C. (2024). Large language models could change the future of behavioural healthcare: A proposal for responsible development and evaluation. NPJ Mental Health Research, 3(1), 12. https://doi.org/10.1038/s44184-024-00056-z
Sun, H., Lin, Z., Zheng, C., Liu, S., & Huang, M. (2021). Psyqa: A Chinese dataset for generating long counselling text for mental health support. arXiv preprint arXiv:2106.01702. https://doi.org/10.48550/arXiv.2106.01702
Tonmoy, S., Zaman, S., Jain, V., Rani, A., Rawte, V., Chadha, A., & Das, A. (2024). A comprehensive survey of hallucination mitigation techniques in large language models. arXiv preprint arXiv:2401.01313. https://doi.org/10.48550/arXiv.2401.01313
Tricco, A. C., Lillie, E., Zarin, W., O'Brien, K. K., Colquhoun, H., Levac, D., Moher, D., Peters, M. D., Horsley, T., & Weeks, L. (2018). PRISMA extension for scoping reviews (PRISMA-ScR): Checklist and explanation. Annals of Internal Medicine, 169(7), 467–473. https://doi.org/10.7326/M18-0850
Twomey, C., O’Reilly, G., & Byrne, M. (2015). Effectiveness of cognitive behavioural therapy for anxiety and depression in primary care: A meta-analysis. Family Practice, 32(1), 3–15. https://doi.org/10.1093/fampra/cmu060
World Health Organisation. (2023). Depressive disorder (depression). World Health Organisation.
Xiao, M., Xie, Q., Kuang, Z., Liu, Z., Yang, K., Peng, M., Han, W., & Huang, J. (2024). HealMe: Harnessing cognitive reframing in large language models for psychotherapy. arXiv preprint arXiv:2403.05574. https://doi.org/10.48550/arXiv.2403.05574
Zaghir, J., Naguib, M., Bjelogrlic, M., Névéol, A., Tannier, X., & Lovis, C. (2024). Prompt engineering paradigms for medical applications: Scoping review. Journal of Medical Internet Research, 26, e60501. https://doi.org/10.2196/60501
Zhang, H., Qiao, Z., Wang, H., Duan, B., & Yin, J. (2024). VCounselor: A psychological intervention chat agent based on a knowledge-enhanced large language model. arXiv preprint arXiv:2403.13553.
Published
How to Cite
Issue
Section
Copyright (c) 2025 Kevin Igwe, Kevin Durrhiem
This work is licensed under a Creative Commons Attribution 4.0 International License.
