![[2601.00004] Finetuning Large Language Models for Automated Depression Screening in Nigerian Pidgin English: GENSCORE Pilot Study](https://arxiv.org/static/browse/0.3.4/images/arxiv-logo-fb.png){kind=logo}
[2601.00004] Finetuning Large Language Models for Automated Depression Screening in Nigerian Pidgin English: GENSCORE Pilot Study
Summary
This study explores the use of fine-tuned large language models for automated depression screening in Nigerian Pidgin English, addressing mental health challenges in underserved communities.
Why It Matters
Mental health issues, particularly depression, are prevalent in Nigeria, yet access to screening tools is limited. This research highlights the potential of AI to bridge linguistic and cultural gaps, making mental health resources more accessible to diverse populations.
Key Takeaways
- Fine-tuned LLMs can effectively screen for depression in Nigerian Pidgin.
- GPT-4.1 outperformed other models in accuracy and cultural relevance.
- The study provides a framework for deploying AI in resource-constrained environments.
Computer Science > Artificial Intelligence arXiv:2601.00004 (cs) [Submitted on 28 Nov 2025 (v1), last revised 13 Feb 2026 (this version, v2)] Title:Finetuning Large Language Models for Automated Depression Screening in Nigerian Pidgin English: GENSCORE Pilot Study Authors:Isaac Iyinoluwa Olufadewa, Miracle Ayomikun Adesina, Ezekiel Ayodeji Oladejo, Uthman Babatunde Usman, Owen Kolade Adeniyi, Matthew Tolulope Olawoyin View a PDF of the paper titled Finetuning Large Language Models for Automated Depression Screening in Nigerian Pidgin English: GENSCORE Pilot Study, by Isaac Iyinoluwa Olufadewa and 5 other authors View PDF Abstract:Depression is a major contributor to the mental-health burden in Nigeria, yet screening coverage remains limited due to low access to clinicians, stigma, and language barriers. Traditional tools like the Patient Health Questionnaire-9 (PHQ-9) were validated in high-income countries but may be linguistically or culturally inaccessible for low- and middle-income countries and communities such as Nigeria where people communicate in Nigerian Pidgin and more than 520 local languages. This study presents a novel approach to automated depression screening using fine-tuned large language models (LLMs) adapted for conversational Nigerian Pidgin. We collected a dataset of 432 Pidgin-language audio responses from Nigerian young adults aged 18-40 to prompts assessing psychological experiences aligned with PHQ-9 items, performed transcription, rigorous preproc...