pith. sign in

arxiv: 2605.31149 · v1 · pith:25TNL3FSnew · submitted 2026-05-29 · 💻 cs.HC · cs.AI

Developing a UXR Point of View for Cognitive Accessibility in Mobile Learning with Generative AI

Fatima Ahmad Muazu , Festus Adedoyin , Huseyin Dogan , Abiodun Adedeji , Melike Akca , Olumuyiwa Ayorinde This is my paper

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

classification 💻 cs.HC cs.AI
keywords cognitive accessibilitymobile learningUX researchgenerative AIrequirements engineeringDeLone-McLean modelQuality Function Deploymentplay cards
0
0 comments X

The pith

A four-stage UXR process with LLM support turns cognitive accessibility principles into measurable, traceable requirements for mobile learning systems.

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

The paper develops a Cognitive Accessibility UXR Playbook by applying the UXR Point-of-View pyramid across four stages: structuring psychological and design layers, validating them with the DeLone-McLean model and Quality Function Deployment, consolidating insights into nine Play Cards, and articulating stakeholder-specific points of view. LLM-supported synthesis assists theme clustering and refinement under human oversight. The authors find that many usability and engagement problems in mobile learning for users with cognitive disabilities arise from ambiguous requirements rather than from interface choices alone. The resulting playbook is presented as a way to make those requirements technically traceable and to align theory, system architecture, and team strategy.

Core claim

By progressing through foundational structuring, DeLone-McLean and QFD validation, Play Card development, and PoV articulation, with LLM assistance for synthesis, the study produces a Cognitive Accessibility UXR Playbook that embeds accessibility principles into measurable and technically traceable requirements for mobile learning aimed at learners with cognitive disabilities.

What carries the argument

The UXR Point-of-View (PoV) pyramid framework, executed in four stages and supported by LLM-assisted synthesis under oversight, that generates the nine Cognitive Accessibility UXR Play Cards and the final Playbook.

If this is right

  • Usability and engagement issues shift from being treated as design problems to being treated as requirements-specification problems.
  • Requirements become explicitly linked to psychological, behavioral, and design layers through the Play Cards.
  • Stakeholder communication improves because each group receives a tailored PoV derived from the same validated structure.
  • LLM assistance is positioned as a tool for clustering and refinement rather than as a replacement for human judgment.

Where Pith is reading between the lines

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

  • The method could be tested on other disability categories or learning platforms to check whether the same four-stage structure generalizes.
  • If the Playbook reduces requirement ambiguity, downstream metrics such as task completion time or retention for cognitive-disability users should improve in controlled deployments.
  • The absence of a reported baseline comparison leaves open the possibility that simpler requirement templates might achieve similar traceability without the full pyramid process.

Load-bearing premise

The four-stage process plus LLM-supported synthesis will produce higher-quality, more traceable requirements than standard UXR methods.

What would settle it

A side-by-side comparison in which two teams develop requirements for the same mobile learning app—one using the proposed Playbook and one using conventional UXR methods—then measure resulting learner performance and error rates on cognitive tasks.

read the original abstract

This study investigates how UX research (UXR) principles, combined with Large Language Model (LLM)-supported analysis, can be used to improve the quality of requirements for mobile learning systems designed for learners with cognitive disabilities. Using the UXR Point-of-View (PoV) pyramid as a methodological framework, the study progressed through four stages: foundational structuring of psychological, behavioral, and design layers; structured validation using the DeLone and McLean Information Systems Success Model and Quality Function Deployment (QFD); insight consolidation through the development of nine Cognitive Accessibility UXR Play Cards; and stakeholder-specific PoV articulation to support interdisciplinary communication. LLM-supported synthesis was integrated to assist in theme clustering, requirement refinement, and hypothesis formulation under human oversight. Findings suggest that many usability and engagement challenges in mobile learning originate from ambiguous or under-specified requirements rather than interface design alone. By embedding cognitive accessibility principles into measurable and technically traceable requirements, the proposed Cognitive Accessibility UXR Playbook provides a structured pathway for aligning theory, system architecture, and stakeholder strategy.

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

2 major / 1 minor

Summary. The manuscript describes a four-stage UXR methodology based on the Point-of-View pyramid for developing cognitive accessibility requirements in mobile learning systems. The stages comprise foundational structuring of psychological/behavioral/design layers, validation via DeLone-McLean IS Success Model and QFD, consolidation into nine Cognitive Accessibility UXR Play Cards, and stakeholder PoV articulation, with LLM-supported synthesis under human oversight. The central claim is that ambiguous requirements, rather than interface design, drive most usability issues, and that the resulting Cognitive Accessibility UXR Playbook supplies measurable, traceable requirements that align theory, architecture, and strategy.

Significance. If the method were shown to produce higher-quality requirements than standard UXR approaches, the Playbook could supply a practical bridge between accessibility theory and system specification in educational technology. The work explicitly credits the use of established models (DeLone-McLean, QFD) and human oversight of LLM output, which are positive elements. However, the manuscript supplies no outcome metrics, traceability examples, or comparative data, so the claimed alignment benefit remains untested.

major comments (2)
  1. [Abstract] Abstract: the statement that 'many usability and engagement challenges in mobile learning originate from ambiguous or under-specified requirements rather than interface design alone' is presented as a finding, yet the manuscript reports no participant data, theme-clustering reliability, error analysis, or empirical support for this assertion.
  2. [Methodology / Findings] The four-stage process (foundational structuring, DeLone-McLean + QFD validation, Play Card development, PoV articulation): no quantitative metrics, inter-rater agreement scores, traceability matrices linking Play Cards to architecture components, or head-to-head comparison against baseline UXR methods are provided to substantiate that the LLM-assisted workflow yields superior requirements.
minor comments (1)
  1. [Play Card development] The invented entities 'Cognitive Accessibility UXR Play Cards' and 'Cognitive Accessibility UXR Playbook' are introduced without a clear definition of their format or reuse criteria.

Simulated Author's Rebuttal

2 responses · 0 unresolved

We thank the referee for the detailed and constructive comments. The manuscript is a methodological proposal for a UXR framework rather than an empirical evaluation study. We acknowledge the concerns about unsupported claims and lack of metrics, and will revise the abstract, methodology, and discussion sections to clarify scope, reframe interpretive insights, and explicitly state limitations. No new data collection is feasible within the current work.

read point-by-point responses

  1. Referee: [Abstract] Abstract: the statement that 'many usability and engagement challenges in mobile learning originate from ambiguous or under-specified requirements rather than interface design alone' is presented as a finding, yet the manuscript reports no participant data, theme-clustering reliability, error analysis, or empirical support for this assertion.

    Authors: We agree the phrasing presents the statement as a finding without direct empirical support from participant data or reliability measures. The statement is an interpretive synthesis drawn from the literature review and the structured four-stage process using established models, not from new empirical evidence. We will revise the abstract to frame it as an insight or hypothesis emerging from the methodology. A new limitations subsection will be added to the discussion to explicitly note the absence of participant data, theme-clustering reliability, or error analysis. revision: yes

  2. Referee: [Methodology / Findings] The four-stage process (foundational structuring, DeLone-McLean + QFD validation, Play Card development, PoV articulation): no quantitative metrics, inter-rater agreement scores, traceability matrices linking Play Cards to architecture components, or head-to-head comparison against baseline UXR methods are provided to substantiate that the LLM-assisted workflow yields superior requirements.

    Authors: The manuscript proposes and describes the four-stage methodology without claiming quantitative superiority or providing comparative evaluation, as its purpose is framework development rather than validation against baselines. No inter-rater agreement scores are reported because the process was conducted by the core research team with LLM assistance under human oversight, without multiple independent coders. We will add an illustrative traceability matrix example linking one Play Card to system components and expand the methodology and discussion sections to include explicit limitations regarding the lack of metrics and head-to-head comparisons. This will clarify that the work offers a structured, traceable approach but does not empirically demonstrate superiority. revision: partial

Circularity Check

1 steps flagged

Findings on ambiguous requirements presented as emerging from author-constructed four-stage UXR framework without external validation or comparison

specific steps
  1. fitted input called prediction [Abstract]
    "Findings suggest that many usability and engagement challenges in mobile learning originate from ambiguous or under-specified requirements rather than interface design alone. By embedding cognitive accessibility principles into measurable and technically traceable requirements, the proposed Cognitive Accessibility UXR Playbook provides a structured pathway for aligning theory, system architecture, and stakeholder strategy."

    The findings about the origin of challenges and the value of the Playbook are stated as results of the four-stage process the authors constructed; the outcome is therefore equivalent to the method's own inputs by construction, with no reported external benchmarks.

full rationale

The paper's derivation proceeds through four author-defined stages (foundational structuring, DeLone-McLean + QFD validation, nine Play Cards, PoV articulation) plus LLM synthesis, then presents the resulting 'findings' and 'structured pathway' as outputs. No independent metrics, inter-rater data, traceability examples, or head-to-head comparisons are reported, so the central claim reduces to the inputs of the constructed method itself.

Axiom & Free-Parameter Ledger

0 free parameters · 2 axioms · 2 invented entities

The central claim rests on the untested premise that the authors' four-stage process and LLM-assisted steps improve requirement quality; no free parameters appear because the work is methodological rather than quantitative, but multiple domain assumptions and two new named artifacts are introduced without independent evidence.

axioms (2)
  • domain assumption The UXR Point-of-View pyramid constitutes a valid foundational framework for structuring psychological, behavioral, and design layers
    Invoked as the starting point of the four-stage process in the abstract without further justification or citation of prior validation.
  • domain assumption LLM-supported synthesis under human oversight reliably assists theme clustering, requirement refinement, and hypothesis formulation
    Stated as integrated into the workflow; no evidence or error bounds supplied in the abstract.
invented entities (2)
  • Cognitive Accessibility UXR Play Cards no independent evidence
    purpose: Consolidate insights from the validation stage
    Newly developed artifact mentioned as an output of stage three; no independent evidence of utility provided.
  • Cognitive Accessibility UXR Playbook no independent evidence
    purpose: Provide a structured pathway aligning theory, architecture, and strategy
    Proposed final deliverable; effectiveness asserted but not demonstrated in the abstract.

pith-pipeline@v0.9.1-grok · 5742 in / 1725 out tokens · 32167 ms · 2026-06-28T21:06:23.214641+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

15 extracted references

  1. [1]

    Research into influencing factors in user experiences of university mobile libraries b ased on mobile learning mode,

    T. Jiang, G. Luo, Z. Wang, and W. Yu, “Research into influencing factors in user experiences of university mobile libraries b ased on mobile learning mode,” Libr. Hi Tech, vol. 42, no. 2, pp. 564–579, May 2024

    2024

  2. [2]

    mLUX: Usability and User Experience Development Framework for M -Learning,

    A. Dirin and M. Nieminen, “mLUX: Usability and User Experience Development Framework for M -Learning,” Int. J. Interact. Mob. Technol., vol. 9, no. 3, p. 37, Jul. 2015

    2015

  3. [3]

    Dynamic UX based m -learning using user profile of learning style,

    A. Nimkoompai and W. Paireekreng, “Dynamic UX based m -learning using user profile of learning style,” in Proceedings of the 3rd International Conference on Communication and Information Processing , 2017, pp. 221–225

    2017

  4. [4]

    Framework for UX Based M -Learning Using Learning Style and Recommendation System,

    A. Nimkoompai and W. Paireekreng, “Framework for UX Based M -Learning Using Learning Style and Recommendation System,” Int. J. Informatics Inf. Syst., vol. 3, no. 3, pp. 106–113, 2020

    2020

  5. [5]

    Study on UX design in enhancing student motivations in mobile language learning,

    J. Seppala, T. Mitsuishi, Y. Ohkawa, X. Zhao, and M. Nieminen, “Study on UX design in enhancing student motivations in mobile language learning,” in 2020 IEEE International Conference on Teaching, Assessment, and Learning for Engineering (TALE) , 2020, pp. 948–951

    2020

  6. [6]

    Implementation of Quality Function Deployment to Improve Online Learning and Teaching in Higher Education Institutes of Engineering in Oman,

    J. R. Al yaarubi and A. Rajakannu, “Implementation of Quality Function Deployment to Improve Online Learning and Teaching in Higher Education Institutes of Engineering in Oman,” Int. J. Learn. Teach. Educ. Res., vol. 23, no. 12, pp. 463–486, Dec. 2024

    2024

  7. [7]

    The DeLone and McLean Model of Information Systems Success: A Ten -Year Update,

    W. H. DeLone and E. R. McLean, “The DeLone and McLean Model of Information Systems Success: A Ten -Year Update,” J. Manag. Inf. 9 Syst., vol. 19, no. 4, pp. 9–30, 2003

    2003

  8. [8]

    W3C Web Accssibility Inititaitve,

    WAI, “W3C Web Accssibility Inititaitve,” Cognitive Accessibility at W3C, 2019. [Online]. Available: https://www.w3.org/WAI/cognitive/. [Accessed: 15-Jul-2025]

    2019

  9. [9]

    UI/UX prototype design for a personalized learning mobile app to boost comprehension: a desi gn thinking model,

    O. J. F. Chavez and T. Palaoag, “UI/UX prototype design for a personalized learning mobile app to boost comprehension: a desi gn thinking model,” TQM J., Jun. 2025

    2025

  10. [10]

    Enhancing User Experience in Mobile Learning by Affective Interaction,

    L. Shen, B. Xie, and R. Shen, “Enhancing User Experience in Mobile Learning by Affective Interaction,” in 2014 International Conference on Intelligent Environments, 2014, pp. 297–301

    2014

  11. [11]

    UX Testing for Mobile Learning Applications of Deaf Children,

    N. Mohamad and N. L. Hashim, “UX Testing for Mobile Learning Applications of Deaf Children,” Int. J. Adv. Comput. Sci. Appl., vol. 12, no. 11, 2021

    2021

  12. [12]

    User Experience Research: Point of View Playbook,

    H. Dogan, S. Giff, and R. Barsoum, “User Experience Research: Point of View Playbook,” in Extended Abstracts of the CHI Conference on Human Factors in Computing Systems, 2024, pp. 1–7

    2024

  13. [13]

    Development of a persuasive User Experience Research (UXR) Point of View for Exp lainable Artificial Intelligence (XAI),

    M. Naiseh, H. Dogan, S. Giff, and N. Jiang, “Development of a persuasive User Experience Research (UXR) Point of View for Exp lainable Artificial Intelligence (XAI),” in The workshop held at the ACM Conference on Human Factors in Computing Systems , 2025

    2025

  14. [14]

    The use of mobile learning in special education nee ds and disabilities (SEND) settings: state-of-the-art classification of studies,

    F. A. Muazu, F. A. Adedoyin, H. Dogan, N. Mavengere, and P. Whittington, “The use of mobile learning in special education nee ds and disabilities (SEND) settings: state-of-the-art classification of studies,” ACM Int. Conf. Proceeding Ser., pp. 486–495, 2024

    2024

  15. [15]

    Defining a UX Research Point of View (POV),

    H. Dogan, R. M. Barsoum, S. Giff, A. Dix, and E. Churchill, “Defining a UX Research Point of View (POV),” in Proceedings of the Extended Abstracts of the CHI Conference on Human Factors in Computing Systems , 2025, pp. 1–3

    2025