cs.HCMar 8, 2026

YAQIN: Culturally Sensitive, Agentic AI for Mental Healthcare Support Among Muslim Women in the UK

Authors: Yasmin Zaraket, Céline Mougenot

Organizations: Dyson School of Design Engineering, Imperial College London

Read PDF
Ask AI
Cite

Copy citation

DOINot available for this paper

Abstract

Mental healthcare services in the UK lack tools and resources to address the cultural needs of Muslim women, often leaving them feeling as though their values are pathologised and limiting trust and engagement [1]. Despite growing awareness of cultural competency, few interventions integrate Islamic frameworks into therapeutic support. This report investigates the design and evaluation of YAQIN, a co-designed AI-based application supporting culturally and faith-sensitive mental health engagement for Muslim women. With almost 1.9 million Muslim women in England in 2021, YAQIN responds to a gap in care [2]. It leverages AIś anonymity and continuous support through a faith-aware chatbot and guided journaling tool grounded in user-centred design and Islamic psychology. The YAQIN design research methodology comprised three stages: contextual investigation and literature review, user research with N=14 stakeholders including Muslim women and mental health experts, and prototype development informed by deductive thematic analysis, personas, journey maps, and design specifications. Evaluation involved a co-designed user study with five participants: four Muslim women and one mental health expert who reviewed therapeutic alignment and cultural sensitivity after using the chatbot prototype. Feedback focused on tone, faith relevance, emotional resonance, and the Retrieval-Augmented Generation pipeline enabling contextual continuity. Participants highlighted YAQINś ability to bridge cultural gaps in trust and therapeutic confidence. Feedback included suggestions of including linguistic diversity and routine-based guidance. This project demonstrates how culturally sensitive AI can improve mental healthcare accessibility and trust for marginalised communities and highlights the potential of faith-integrated technology in healthcare innovation.

Figures & tables

Figure 1: Motivating Use Case with Lina Persona
Figure 2: DRM Outline for YAQIN
Muslim Women ClientsC1C2C3C4C5C6C7
 Under-graduateTeacherMedical StudentUnder-graduateMaster’s StudentUnder-graduateUnder-graduate
Mental Healthcare ExpertsE1E2E3E4E5E6E7
 Psychologist, PsychotherapistPscho-therapist, CounsellorMedical ResearcherCounsellorClinical Team Lead, Pscyho-therapistPsychology Researcher, Islamic ScholarMental Health Pharmacist
Table 1: List of Interviewees and Their Occupation
ThemesCodes Identified in Literature Review
Changes in Cultural and Religious Diversity AcceptanceImprovement in Inclusivity and Representation
 Changes in Access and Acceptance
Stigma, Judgement, and Barriers to CareStigma and Cultural Taboo
 Therapist and Client Prejudice
Islamic Knowledge in TherapyIntegration of Religious Teachings in Sessions
 Prophetic Stories and Quranic Anchors
Table 2: Thematic Analysis Code and Theme Breakdown from Literature Review
Figure 3: Personas (top) MP1 Maryam: Muslim Woman Attending Therapy Sessions with a Muslim Therapist After a Non-Muslim Therapist Experience and (bottom) MP2 Lina: Muslim Woman Struggling to Access Mental Healthcare [ 63 ]
Figure 4: Personas (top) TP1 Layla: Muslim Woman Therapist Working with Diverse Clients and (bottom) TP2 Alex: Non-Muslim Therapist Supporting Faith-Inclusive Practice [ 63 ]
Figure 5: MP1 Maryam and MP2 Lina User Journey Maps: Different Journeys of Navigating Starting or Restarting Therapy Sessions
Figure 6: TP1 Layla and TP2 Alex User Journey Maps: Different Journeys of Navigating Clients with Familiar or Unfamiliar Cultural Backgrounds
Figure 7: Design Specifications for YAQIN Intervention
Figure 8: Concept UI Screens for (a) YAQIN Chatbot Landing Screen, (b) Example Entry and Response Chat, (c) Main Tafakkur (Reflection) Journal Landing Screen, and (d) Therapist Permission Request Feature
Figure 9: YAQIN Chatbot Use Case Flow
Figure 10: YAQIN RAG Diagram from the Use Case Flow
Figure 11: YAQIN Journal Use Case Flow
Figure 12: Co-Design Session Plan
Figure 13: Prompt Refinement Overview Based on Co-Design
Figure 14: Final Designed Main Features and their Alignment to the Design Specifications
Figure 15: Final User Journey Maps for (top) Muslim Clients MP1 and MP2, and (bottom) Therapists TP1 and TP2, Showing the Improved Interaction Pathways with YAQIN

Explore similar work

CardsList
Jun 11, 2025

"I Said Things I Needed to Hear Myself": Peer Support as an Emotional, Organisational, and Sociotechnical Practice in Singapore

Peer support plays a vital role in expanding access to mental health care by providing empathetic, community-based support outside formal clinical systems. As digital platforms increasingly mediate such support, the design and impact of these technologies remain under-examined, particularly in Asian contexts. This paper presents findings from an interview study with 20 peer supporters in Singapore, who operate across diverse online, offline, and hybrid environments. Through a thematic analysis, we unpack how participants start, conduct, and sustain peer support, highlighting their motivations, emotional labour, and the sociocultural dimensions shaping their practices. Building on this grounded understanding, we surface design directions for culturally responsive digital tools that scaffold rather than supplant relational care. Drawing insights from qualitative accounts, we offer a situated perspective on how AI might responsibly augment peer support. This research contributes to human-centred computing by articulating the lived realities of peer supporters and proposing design implications for trustworthy and context-sensitive AI in mental health.

Kellie Yu Hui Sim, Kenny Tsu Wei Choo

Singapore University of Technology and Design Singapore

Emotional Support ConversationHuman-Centered AIResponsible AI
AskPDF
Apr 22, 2026

Aligning Human-AI-Interaction Trust for Mental Health Support: Survey and Position for Multi-Stakeholders

Building trustworthy AI systems for mental health support is a shared priority across stakeholders from multiple disciplines. However, "trustworthy" remains loosely defined and inconsistently operationalized. AI research often focuses on technical criteria (e.g., robustness, explainability, and safety), while therapeutic practitioners emphasize therapeutic fidelity (e.g., appropriateness, empathy, and long-term user outcomes). To bridge the fragmented landscape, we propose a three-layer trust framework, covering human-oriented, AI-oriented, and interaction-oriented trust, integrating the viewpoints of key stakeholders (e.g., practitioners, researchers, regulators). Using this framework, we systematically review existing AI-driven research in mental health domain and examine evaluation practices for ``trustworthy'' ranging from automatic metrics to clinically validated approaches. We highlight critical gaps between what NLP currently measures and what real-world mental health contexts require, and outline a research agenda for building socio-technically aligned and genuinely trustworthy AI for mental health support.

Xin Sun, Yue Su, Yifan Mo +9

National Institute of Informatics (NII), Japan · Vrije Universiteit Amsterdam, the Netherlands

Mental HealthHuman-Centered AITrust in AI
AskPDF
Apr 7, 2026

Measuring What Matters!! Assessing Therapeutic Principles in Mental-Health Conversation

The increasing use of large language models in mental health applications calls for principled evaluation frameworks that assess alignment with psychotherapeutic best practices beyond surface-level fluency. While recent systems exhibit conversational competence, they lack structured mechanisms to evaluate adherence to core therapeutic principles. In this paper, we study the problem of evaluating AI-generated therapist-like responses for clinically grounded appropriateness and effectiveness. We assess each therapists utterance along six therapeutic principles: non-judgmental acceptance, warmth, respect for autonomy, active listening, reflective understanding, and situational appropriateness using a fine-grained ordinal scale. We introduce FAITH-M, a benchmark annotated with expert-assigned ordinal ratings, and propose CARE, a multi-stage evaluation framework that integrates intra-dialogue context, contrastive exemplar retrieval, and knowledge-distilled chain-of-thought reasoning. Experiments show that CARE achieves an F-1 score of 63.34 versus the strong baseline Qwen3 F-1 score of 38.56 which is a 64.26 improvement, which also serves as its backbone, indicating that gains arise from structured reasoning and contextual modeling rather than backbone capacity alone. Expert assessment and external dataset evaluations further demonstrate robustness under domain shift, while highlighting challenges in modelling implicit clinical nuance. Overall, CARE provides a clinically grounded framework for evaluating therapeutic fidelity in AI mental health systems.

Abdullah Mazhar, Het Riteshkumar Shah, Aseem Srivastava +2

IIIT Delhi · MBZUAI · Wysa

Clinical Language Model EvaluationLLM EvaluationConversational Agents
AskPDF