Optimizing Educational Strategies for Dyslexia Through Multimodal Machine Learning

Dyslexia is a prevalent learning disability that affects reading, writing, and comprehension skills. Traditional interventions often rely on single-modality approaches, which may not fully address the diverse cognitive needs of dyslexic learners. This research explores the integration of multimodal machine learning as an optimized strategy for dyslexia interventions. By integrating visual, auditory, and textual inputs, multimodal AI systems can personalize learning experiences, enhance engagement, improve comprehension, and facilitate real-time adaptation of educational materials to match individual cognitive patterns. This research highlights the potential of AI-driven educational strategies in enhancing accessibility and inclusivity, paving the way for more effective dyslexia interventions in modern learning environments. It also shows how to optimize educational Strategies for Dyslexia through multimodal machine learning. A narrative synthesis and systematic literature review conducted under PRISMA guidelines, the research evaluates adaptive systems that personalize content in real time. Findings indicate that MML enhances reading fluency, knowledge retention, and learner engagement. These results highlight the potential of AI-driven multimodal frameworks to improve accessibility and inclusivity in dyslexia education.

Dyslexia, Multimodal machine learning, Machine Learning, Personalized learning

1. Barber, I. (2024, December 18). The Delphi study: A new definition of dyslexia. Dyslexia Action. Retrieved from 1 [Google Scholar] [Crossref]

2. Shaffer, J. (2021, September 1). How does dyslexia impact student learning long term? TeachHub. Retrieved from 2 [Google Scholar] [Crossref]

3. Barua, A., et al. (2023). *A Systematic Literature Review on Multimodal Machine Learning: Applications, Challenges, Gaps, and Future Directions*. Retrieved from [ResearchGate](https://www.researchgate.net/publication/368402582_A_Systematic_Literature_Review_on_Multimodal_Machine_Learning_Applications_Challenges_Gaps_and_Future_Directions). [Google Scholar] [Crossref]

4. Marantika, P. D., Suwastini, N. K. A., Adnyani, N. L. P. S., Mandala, M. A. K., & Artini, N. N. (2021). Multimodal Teaching in EFL Context: A Literature Review. Edu-Ling: Journal of English Education and Linguistics, 4(2), 140-155. Retrieved from Academia.edu. [Google Scholar] [Crossref]

5. Tzovaras, D., Standen, P. J., Brown, D. J., Taheri, M., Galvez Trigo, M. J., Boulton, H., Burton, A., Hallewell, M. J., Lathe, J. G., Shopland, N., Blanco Gonzalez, M. A., Kwiatkowska, G. M., Milli, E., Cobello, S., Mazzucato, A., Traversi, M., & Hortal, E. (2022). An evaluation of an adaptive learning system based on multimodal affect recognition for learners with intellectual disabilities. British Journal of Educational Technology, 51(6), 2151–2168. https://doi.org/10.1111/bjet.13010 [Google Scholar] [Crossref]

6. Juma, A. A. (2023-2024). The outcomes of using multimodality on language teaching and learning processes. Sultanate of Oman. [Google Scholar] [Crossref]

7. Yap, J. R., Aruthanan, T., & Chin, M. (2025). Artificial intelligence in dyslexia research and education: A scoping review. IEEE Access, 13, 7123-7134. https://doi.org/10.1109/ACCESS.2025.3526189 [Google Scholar] [Crossref]

8. Martínez Lirola, M. (2020). Multimodal teaching proposal in an English as a foreign language subject. ASIAN TEFL, 5(1), 39-52. https://www.asian-tefl.com [Google Scholar] [Crossref]

9. Felicia, G. (2025, April). Multimodal learning demystified: A deep dive. DyslexicHelp.org. . https://dyslexichelp.org/what-is-multimodal-learning-and-how-does-it-work [Google Scholar] [Crossref]

• What the Desert Fathers Teach Data Scientists: Ancient Ascetic Principles for Ethical Machine-Learning Practice
• Comparative Analysis of Some Machine Learning Algorithms for the Classification of Ransomware
• Comparative Performance Analysis of Some Priority Queue Variants in Dijkstra’s Algorithm
• Transfer Learning in Detecting E-Assessment Malpractice from a Proctored Video Recordings.
• Dual-Modal Detection of Parkinson’s Disease: A Clinical Framework and Deep Learning Approach Using NeuroParkNet