pith. sign in

arxiv: 2605.31131 · v1 · pith:7UAIOT6Qnew · submitted 2026-05-29 · 💻 cs.HC · cs.AI

UXR PoV for Neuroinclusive Emotion Regulation

Melike Akca , Mona Giff , Deniz Cetinkaya , Huseyin Dogan , Stephen Giff This is my paper

Pith reviewed 2026-06-28 21:18 UTC · model grok-4.3

classification 💻 cs.HC cs.AI
keywords ADHDemotion regulationneuroinclusive designgenerative AIUXR methodologyPlay CardsDBTdigital mental health
0
0 comments X

The pith

A Generative AI-augmented four-stage UXR process integrates DBT, SDT and COM-B to produce ten theory-informed Play Cards for neuroinclusive ADHD emotion regulation design.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The paper presents a replicable methodology that uses generative AI as a co-analytic tool within structured user experience research to bridge psychological frameworks with design practice for adults with ADHD. It operationalizes this through four stages that move from hypothesis generation to stakeholder-specific narratives, yielding actionable Play Cards that translate mechanisms like emotional regulation into design guidance. A sympathetic reader would care because existing digital interventions often lack neurodiversity accommodation and theoretical grounding, and this approach aims to reduce bias while making evidence-based insights usable by designers.

Core claim

The paper claims that a Generative AI-augmented UXR methodology, grounded in the UXR Point of View Playbook and integrating Dialectical Behaviour Therapy, Self-Determination Theory and the COM-B model, operationalizes a four-stage process of AI-supported hypothesis generation, foundational planning, insight generation via Building Blocks, and construction of PoV narratives; this process produces ten theory-informed UXR Play Cards that translate psychological mechanisms and empirical findings into actionable design guidance for emotionally intelligent and neuroinclusive digital emotion regulation interventions.

What carries the argument

The four-stage UXR process (AI-supported hypothesis generation, foundational planning, insight generation via Building Blocks, PoV narratives) that uses Generative AI to synthesize evidence from DBT, SDT and COM-B into ten Play Cards.

If this is right

  • The methodology supplies a replicable, bias-aware framework for integrating Generative AI into UXR practice.
  • It advances human-centred and neuroinclusive approaches to digital mental health design.
  • The resulting Play Cards translate established psychological mechanisms into concrete, stakeholder-specific design guidance.
  • The four-stage process supports synthesis, hypothesis formation and design articulation for ER interventions.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

  • Design teams working on other neurodiverse populations could adapt the same four-stage structure and theory set.
  • Empirical validation of the Play Cards in live design projects would be a direct next step to test outcome improvements.
  • The approach implies that structured AI co-analysis can surface hidden biases in UXR synthesis if the stages are followed sequentially.

Load-bearing premise

That applying DBT, SDT and COM-B together with Generative AI inside the described four-stage process will automatically deliver effective, bias-reduced design guidance without separate empirical testing of the resulting Play Cards.

What would settle it

A controlled comparison in which product teams using the ten Play Cards produce digital tools that show no measurable improvement in emotion regulation outcomes or user engagement for ADHD adults relative to teams using conventional UXR methods without the AI-augmented framework.

read the original abstract

Attention-deficit/hyperactivity disorder (ADHD) is a psychiatric disorder which presents itself in individuals through patterns of developmentally inappropriate levels of inattentiveness, hyperactivity, and impulsivity, with difficulties in decision making and emotional regulation (ER). Although digital and AI-based interventions have expanded access to ER support, many existing systems remain limited by weak theoretical integration, insufficient accommodation of neurodiversity, and a lack of structured user experience research (UXR) methodologies, that bridge psychological insight with design practice. This paper introduces a Generative AI-augmented UXR methodology, grounded in the UXR Point of View (PoV) Playbook, to support the design of emotionally intelligent and Neuroinclusive digital ER interventions for adults with ADHD. The approach integrates empirical evidence with established psychological frameworks Dialectical Behaviour Therapy (DBT), Self-Determination Theory (SDT), and the COM-B behavioural model and leverages Generative AI as a co-analytic tool to support synthesis, hypothesis formation, and design articulation. The methodology is operationalized through a four-stage UXR process encompassing AI-supported hypothesis generation, foundational planning, insight generation via Building Blocks, and the construction of stakeholder-specific PoV narratives. This process results in a set of ten theory informed UXR Play Cards that translate psychological mechanisms and empirical findings into actionable design guidance. The primary contribution of this work is a replicable, bias-aware framework for integrating Generative AI into UXR practice, advancing human-centred and Neuroinclusive approaches to digital mental health design.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Referee Report

0 major / 1 minor

Summary. The manuscript proposes a Generative AI-augmented four-stage UXR methodology, grounded in the UXR PoV Playbook, that integrates DBT, SDT, and COM-B frameworks to support the design of neuroinclusive digital emotion regulation interventions for adults with ADHD. GenAI is positioned as a co-analytic tool for hypothesis generation, planning, insight synthesis via Building Blocks, and construction of stakeholder PoV narratives. The process yields ten theory-informed Play Cards as actionable design guidance. The stated primary contribution is a replicable, bias-aware framework for integrating GenAI into UXR practice.

Significance. If the four-stage process is replicable as described and the bias-awareness mechanisms hold under independent application, the work offers a structured bridge between established psychological models and HCI design practice for digital mental health. The explicit grounding in multiple theories plus GenAI co-analysis represents a timely methodological contribution in neuroinclusive design, though its practical utility would require subsequent empirical evaluation.

minor comments (1)
  1. [Abstract] The abstract and introduction could more explicitly delimit the contribution as the replicable process description (rather than demonstrated effectiveness of the resulting Play Cards) to align reader expectations with the absence of user studies or validation data.

Simulated Author's Rebuttal

0 responses · 0 unresolved

We thank the referee for their positive review, recognition of the methodological contribution, and recommendation to accept. No major comments were raised in the report.

Circularity Check

0 steps flagged

No significant circularity

full rationale

The paper proposes a four-stage UXR methodology that integrates independent psychological frameworks (DBT, SDT, COM-B) with Generative AI as a co-analytic tool to generate Play Cards as design guidance. The central claim is the replicability and bias-awareness of this process description itself, not any quantitative predictions, fitted parameters, or outcomes that reduce by construction to the framework's own definitions. No load-bearing self-citations, uniqueness theorems, or ansatzes are invoked; the derivation chain consists of synthesis steps grounded in external theories without circular reduction. The contribution remains self-contained as a methodological proposal.

Axiom & Free-Parameter Ledger

0 free parameters · 2 axioms · 0 invented entities

The paper rests on three established psychological frameworks treated as domain assumptions and on the untested premise that Generative AI can serve as a reliable co-analytic tool without introducing new biases. No free parameters or invented entities are introduced in the abstract.

axioms (2)
  • domain assumption DBT, SDT and COM-B provide valid and sufficient psychological grounding for emotion regulation design in ADHD adults
    Invoked in the abstract as the basis for the Play Cards without further justification or testing.
  • ad hoc to paper Generative AI can be used as a bias-aware co-analytic tool in UXR synthesis
    Stated as part of the methodology but not supported by evidence in the provided text.

pith-pipeline@v0.9.1-grok · 5809 in / 1506 out tokens · 22986 ms · 2026-06-28T21:18:59.018901+00:00 · methodology

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Reference graph

Works this paper leans on

33 extracted references · 17 canonical work pages

  1. [1]

    Leverage GenAI and the UXR PoV Framework

  2. [2]

    Establish a Foundation Plan/Roadmap

  3. [3]

    Insight Generation and Card Development

  4. [4]

    Such capabilities align with recent studi es highlighting GenAI’s role in augmenting UX practitioner workflows and enabling AI-assisted POV construction [13]

    Craft PoV Narratives for Stakeholders UXR PoV for Neuroinclusive Emotion Regulation Emerging work on AI -supported UX research suggests that Generative AI can facilitate progression through structured research frameworks by supporting data synthesis, hypothesis generation, and insight articulation. Such capabilities align with recent studi es highlighting...

    2020

  5. [5]

    the PRISMA-organized Excel dataset,

  6. [6]

    the UXR PoV framework papers (Giff et al., 2025; Dogan et al., 2024) [10, 25], and

    2025

  7. [7]

    the UXR previously published papers and workshop PowerPoint slide,

  8. [8]

    Analyse this PRISMA_ADHD_ER Excel dataset and summarise recurring design –emotion–behaviour patterns

    the UXR PoV Playbook website and example Play Cards. A systematic literature review was conducted on the full dataset, followed by a thematic analysis using Braun and Clarke’s (2006) six-phase method [14]. Identified themes informed both human-led interpretation and AI-assisted synthesis. Comparative observa tions across AI systems were analysed descripti...

    2006

  9. [9]

    Poznyak, E., & Debbané, M. (2025). Emotion regulation beyond executive and attention difficulties: impact on daily life impairments in community adolescents. Child and Adolescent Psychiatry and Mental Health, 19(1), 1–12. DOI: 10.1186/s13034-025-00898-1

    work page doi:10.1186/s13034-025-00898-1 2025

  10. [10]

    Shaw, P., Stringaris, A., Nigg, J., & Leibenluft, E. (2014). Emotion dysregulation in attention deficit hyperactivity disorder. American Journal of Psychiatry, 171(3), 276–293. DOI: 10.1176/appi.ajp.2013.13070966

    work page doi:10.1176/appi.ajp.2013.13070966 2014

  11. [11]

    Executive function and emotion regulation in depressive and anxiety disorders: A cross-sectional study

    Shetty T, Kashyap H, Mehta UM, Binu VS. Executive function and emotion regulation in depressive and anxiety disorders: A cross-sectional study. Indian Journal of Psychological Medicine. Published online June 11, 2025:02537176251340586. doi:10.1177/02537176251340586 https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12162532/

    work page doi:10.1177/02537176251340586 2025

  12. [12]

    Development of a digital mental health intervention for youths with ADHD using a person-based approach

    Storetvedt M, Svendsen E, Lydersen M, Johansen AS. Development of a digital mental health intervention for youths with ADHD using a person-based approach. Front Digit Health. 2024;6:1386892. https://www.frontiersin.org/articles/10.3389/fdgth.2024.1386892/full

    work page doi:10.3389/fdgth.2024.1386892/full 2024

  13. [13]

    K., Nielsen, S

    Bernaerts, S., Van Daele, T., Carlsen, C. K., Nielsen, S. L., Schaap, J., & Roke, Y. (2024). User involvement in digital mental health: approaches, potential and the need for guidelines. Frontiers in Digital Health, 6, Article1440660. https://doi.org/10.3389/fdgth.2024.1s440660

    work page doi:10.3389/fdgth.2024.1s440660 2024

  14. [14]

    The limitations of user- and human-centered design in an eHealth context and how to move beyond them,

    L. van Velsen, G. Ludden, C. Grünloh, “The limitations of user- and human-centered design in an eHealth context and how to move beyond them,” J. Med. Internet Res., vol. 24, no. 8, e36437, 2022 doi:10.2196/37341

    work page doi:10.2196/37341 2022

  15. [15]

    A narrative review to identify promising approaches for digital health interventions to support emotion regulation for adolescents with Attention- Deficit/Hyperactivity Disorder

    Murray AL, Thye M, Obsuth I, Cai S, Lui M, Orr C, Saravanan A. A narrative review to identify promising approaches for digital health interventions to support emotion regulation for adolescents with Attention- Deficit/Hyperactivity Disorder. JMIR Ment Health. 2025 doi: 10.2196/56066

    work page doi:10.2196/56066 2025

  16. [16]

    M. M. Linehan, Skills Training Manual for Treating Borderline Personality Disorder. New York, NY, USA: Guilford Press, 1993. https://pmc.ncbi.nlm.nih.gov/articles/PMC2963469

    1993

  17. [17]

    Self-Determination Theory and the facilitation of intrinsic motivation, social development, and well-being,

    R. M. Ryan and E. L. Deci, “Self-Determination Theory and the facilitation of intrinsic motivation, social development, and well-being,” Am. Psychol., vol. 55, no. 1, pp. 68–78, Jan. 2000, doi:10.1037//0003-066x.55.1.68. https://pubmed.ncbi.nlm.nih.gov/11392867/

    work page doi:10.1037//0003-066x.55.1.68 2000

  18. [18]

    The behaviour change wheel: a new method for characterising and designing behaviour change interventions,

    S. Michie, M. M. van Stralen, and R. West, “The behaviour change wheel: a new method for characterising and designing behaviour change interventions,” Implementation Sci., vol. 6, no. 42, 2011, doi:10.1186/1748-5908-6-42 https://pubmed.ncbi.nlm.nih.gov/21513547/

    work page doi:10.1186/1748-5908-6-42 2011

  19. [19]

    M., Giff, S., Dix, A., & Churchill, E

    Dogan H, Barsoum RM, Giff S, Dix A, Churchill E. Defining a UX Research Point of View (POV). In CHI EA 2025 - Extended Abstracts of the 2025 CHI Conference on Human Factors in Computing Systems. Association for Computing Machinery; 2025:773. https://doi.org/10.1145/3706599.3706712

    work page doi:10.1145/3706599.3706712 2025

  20. [20]

    Endsley, M. R. (1995). Toward a theory of situation awareness in dynamic systems. Human Factors, 37(1), 32–64. DOI:10.1518/001872095779049499

    work page doi:10.1518/001872095779049499 1995

  21. [21]

    Munir, A., Aved, A., & Blasch, E. (2022). Situational Awareness: Techniques, Challenges, and Prospects. AI, 3(1), 55-77. https://doi.org/10.3390/ai3010005

    work page doi:10.3390/ai3010005 2022

  22. [22]

    Dogan H, Giff., S, Barsoum., R.N., and Dix., A. 2026. Developing an AI-Powered UX Research Point of View (POV). In Extended Abstracts of the 2026 CHI Conference on Human Factors in Computing Systems (CHI EA ’26), April 13–17, 2026, Barcelona, Spain. ACM, New York, NY, USA, 4 pages. https://doi.org/10.1145/3772363.3778773

    work page doi:10.1145/3772363.3778773 2026

  23. [23]

    Virginia Braun and Victoria Clarke. 2006. Using thematic analysis in psychology. Qualitative Research in Psychology 3, 2 (2006), 77–101. https://doi.org/10.1191/1478088706qp063oa UXR PoV for Neuroinclusive Emotion Regulation

    work page doi:10.1191/1478088706qp063oa 2006

  24. [24]

    International Journal of Human–Computer Interaction36(6), 495–504 47 (2020) https://doi.org/10.1080/10447318.2020.1741118

    Shneiderman B. Human-Centered Artificial Intelligence: Reliable, Safe & Trustworthy. International Journal of Human–Computer Interaction. 2022;38(1):1–12 https://doi.org/10.1080/10447318.2020.1741118

    work page doi:10.1080/10447318.2020.1741118 2022

  25. [25]

    Ai, Q., Zhan, J., & Liu, Y. (2025). Foundations of GenIR. https://arxiv.org/abs/2501.02842

    arXiv 2025

  26. [26]

    Klinger, J., Mateos-Garcia, J., & Stathoulopoulos, K. (2020). A narrowing of AI research? arXiv:2009.10385. https://arxiv.org/abs/2009.10385

    arXiv 2020

  27. [27]

    Krasanakis, E., & Papadopoulos, S. (2024). Towards Standardizing AI Bias Exploration. arXiv:2405.19022. https://arxiv.org/abs/2405.19022

    arXiv 2024

  28. [28]

    Trabelsi, B., Shaki, J., & Kraus, S. (2026). Pro-AI Bias in Large Language Models. arXiv:2601.13749. https://arxiv.org/abs/2601.13749

    arXiv 2026

  29. [29]

    Lin, Z. (2024). Beyond principlism: Practical strategies for ethical AI use in research practices. arXiv:2401.15284. https://arxiv.org/abs/2401.15284

    Pith/arXiv arXiv 2024

  30. [30]

    Vosough, S., et al. (2025). Altered oscillatory brain networks in ADHD: An eLORETA study. arXiv:2512.13539. https://arxiv.org/abs/2512.13539

    arXiv 2025

  31. [31]

    Mokander, J., et al. (2021). Conformity Assessments and Post-Market Monitoring in EU AI Regulation. arXiv:2111.05071. https://arxiv.org/abs/2111.05071

    arXiv 2021

  32. [32]

    Mohammad, S. (2020). Sentiment Analysis: Automatically Detecting Valence, Emotions, and Other Affectual States from Text. https://doi.org/10.1016/B978-0-12-821124-3.00011-9

    work page doi:10.1016/b978-0-12-821124-3.00011-9 2020

  33. [33]

    Strauss, I., et al. (2025). Real-World Gaps in AI Governance Research. arXiv:2505.00174. https://arxiv.org/abs/2505.00174 [25]Stephen Giff, Renée Barsoum, and Huseyin Dogan. 2024. User Experience Research: Point of View Playbook. In Extended Abstracts of the CHI Conference on Human Factors in Computing Systems (CHI EA ’24). ACM, New York, NY, USA. https:/...

    work page doi:10.1145/3613905.3637136 2025