SCIENCE@home

Machine Learning–Driven Assistive Technologies for Enhancing Academic Assessment of Students with Learning Disabilities in Kerala’s Secondary Schools

Bibi C B,V. Mrunalini

Published 2025 in 2025 2nd Global AI Summit - International Conference on Artificial Intelligence and Emerging Technology (AI Summit)

ABSTRACT

However, persistent issues of validity, fairness, and accessibility plague summative and formative assessments for students with Specific Learning Disabilities (SLD) in India, thereby affecting equitable participation and the accurate assessment of learning outcomes. The goal of this research work is to investigate whether wearable assistive technology (AT) based on machine learning (ML) can enhance the content validity, fairness, usability, and overall effectiveness of assessments in a manner that does not compromise academic standards. A multi-study, mixed-methods research was carried out in government and aided secondary schools of Kerala: Study 1, Baseline Audit and Evidence of Validity for Current Assessment Practices. Experiment 1 piloted an ML-AT toolkit that included speech-to-text conversion, adaptive timing, optical character recognition combined with text simplification, webcam-based eye-tracking features, and real-time analytics in a quasi-experiment. User experiences were investigated through qualitative interviews with students, teachers, and parents in Study 3, and the cost-effectiveness and implementation feasibility were evaluated in Study 4. The follow-up outcome measures were the same as in Study II, except for the item analyses and usability measures (SUS/UEQ) and academic growth. The expected results are that ML-AT will enhance measurement precision, minimize accommodation-related bias, and improve subgroup parity on fairness metrics. Teachers should report a reduction in workload to teach students, and that the instruction has become more concentrated. The findings suggest that ML-AT holds promise for disrupting educational assessment to increase accessibility and psychometric rigor, with caveats that governance processes and teacher capacity development are incorporated into implementation plans.

PUBLICATION RECORD

  • Publication year

    2025

  • Venue

    2025 2nd Global AI Summit - International Conference on Artificial Intelligence and Emerging Technology (AI Summit)

  • Publication date

    2025-11-19

  • Fields of study

    Not labeled

  • Identifiers
    DOI 10.1109/AISummit66170.2025.11410981
  • External record

    Open on Semantic Scholar

  • Source metadata

    Semantic Scholar

CITATION MAP

EXTRACTION MAP

CLAIMS

  • No claims are published for this paper.

CONCEPTS

  • No concepts are published for this paper.

REFERENCES

Showing 1-27 of 27 references · Page 1 of 1

CITED BY

  • No citing papers are available for this paper.

Showing 0-0 of 0 citing papers · Page 1 of 1