Leveraging AI Technologies for Personalized Learning Support in Dyslexic Students

Abstract

Dyslexia,aprevalentlearningdifficultyaffectingreading,writing,andspelling,requiresspecializedinterventionsthat traditional educational systems often lack. This paper proposes an AI-assisted learning platform aimed ataddressing the diverse needs of dyslexic students. The system first tests for dyslexia, classifying students intothree zones—low, moderate, and high—based on severity. Using Natural language processing (NLP), Machinelearning, speech-to-text (STT), and Text-to-speech (TTS) these are some of the AI technologies, the platformprovidespersonalizedlearningpracticestailoredtoeachstudent\'sclassification.Continuousassessmentandreal-time monitoring allow for dynamic adaptation of the learning process to accommodate individual progress,ensuring that interventionsareboth responsive andeffective.

Introduction

In the evolving educational landscape, technology plays a crucial role in enhancing learning experiences and providing inclusive opportunities. However, traditional e-learning platforms often overlook the unique needs of students with learning challenges such as dyslexia—a brain-based condition affecting approximately 10–15% of the global population. Dyslexia impairs the ability to interpret written language, making tasks like reading, writing, and comprehension particularly challenging.

Traditional e-learning systems often adopt a one-size-fits-all approach, failing to address the diverse learning requirements of dyslexic students. This paper proposes an AI-enhanced e-learning platform designed specifically for dyslexic students. By utilizing AI-assisted evaluation tests, the platform categorizes students based on the severity of their dyslexia—Low, Mid, or High—and then tailors the learning modules accordingly. Through the integration of AI, the platform not only provides personalized learning paths but also continuously adapts based on each student's progress and needs, creating a more inclusive and supportive learning environment.

Key AI Technologies in the Proposed Model

• Natural Language Processing (NLP): Simplifies complex texts, rephrases sentences, and adjusts vocabulary to suit the student's reading level.

• Neural Networks: Classify students based on the severity of their dyslexia and monitor progress over time.

• Machine Learning (ML): Tailors educational content, adjusts difficulty levels, and offers personalized learning paths based on real-time performance.

• Speech-to-Text (STT) and Text-to-Speech (TTS): Assist students in reading and writing by converting spoken language into text and vice versa, aiding in comprehension and expression.

• Adaptive Learning Systems: Modify content pace, difficulty, and type based on student performance and interaction, ensuring appropriate stimulation.

• Gamification: Incorporates game elements like points and rewards to increase motivation and engagement.

• Emotional and Behavioral Monitoring: Detects emotional states and adjusts content delivery to support learning without frustration or anxiety.

Experimental Results

The AI-assisted learning platform successfully addresses the specific needs of dyslexic students by providing personalized, adaptive learning interventions. Key features include:

1. Personalized Learning Paths: Tailored learning activities based on the severity of dyslexia, ensuring an optimal pace and difficulty level.

2. Real-time Monitoring and Adaptation: Continuous assessment of student progress allows for dynamic adjustments in content and difficulty.

3. Assistive Tools: Integration of STT and TTS technologies offers multimodal support, enhancing reading comprehension and writing expression.

4. Engagement and Motivation: Gamification elements keep learners motivated and engaged, adjusting challenges in real-time based on progress.

Conclusion

In conclusion, by integrating artificial intelligence (AI) technologies offers significant potential to transformeducation for dyslexic students by providing personalized, adaptive, and effective learning experiences. ByutilizingAImethodslikenaturallanguageprocessing(NLP),machinelearning(ML),speechrecognition,text-to-speech (TTS), and adaptive learning technologies, students with dyslexia can receive tailored interventions thatmatch their individual learning needs. AI enables early detection of dyslexia, offers continuous monitoring, andadaptsteachingstrategiesinrealtime,ensuringthatlearnersaresupported throughouttheiracademicjourney.Byaddressingchallengesrelated toreading,writing,andcomprehension,andbyincorporatingtools suchasgamification and emotional monitoring, AI creates an engaging and supportive environment that encouragessuccess.Nonetheless,additionalstudiesarerequiredtotackleconcernsrelatedtodataprivacy,biasesinalgorithms, and the scalability of AI systems. Ultimately, AI\'s potential to create inclusive and equitable learningenvironments establishes it as an effective instrument for improving educational results. for dyslexic students,making educationmore accessibleandpersonalizedfor alllearners.

References

[1] Snowling,M.J.,&Hulme,C.(2012).\"Interventionsforchildren\'slanguageandliteracydifficulties.\"InternationalJournalofLanguage&CommunicationDisorders. [2] Rello,L.,Baeza-Yates,R.(2016).\"Howtopresentmorereadabletextforpeoplewithdyslexia.\"UniversalAccessinthe InformationSociety. [3] Pino,M.,&Mortari,L.(2014).\"Theinclusionofstudentswithdyslexiainhighereducation: Asystematicreviewusingnarrative synthesis.\"Dyslexia. [4] Zhao,Y.,&Shute,V.J.(2019). \"AIforpersonalized learninginadaptiveeducational systems.\"InternationalJournalofArtificialIntelligence inEducation. [5] Graesser,A.C.etal.(2018).\"AIinintelligenttutoringsystems:Learningthroughnaturallanguagedialogue.\"JournalofArtificialIntelligencein Education. [6] Rello,L.,Ballesteros,M.,&Bigham,J.P.(2015).\"Aspellcheckerfordyslexia.\"Human-ComputerInteraction-INTERACT2015. [7] Knox,C.,&Douglas,G.(2018).\"AIandmachinelearningindyslexiadetectionandintervention.\"Computers&Education. [8] Gaggioli,A.etal.(2014).\"AI-drivenassistivetechnologiesforstudentswithlearningdisabilities:Areview.\"IEEETransactionsonLearningTechnologies. [9] Sénéchal,M.,&Ouellette,G.(2016).\"Theroleofphonologicalawarenessinearlyliteracy: Anoverview.\"JournalofEducationalPsychology. [10] D\'Mello,S.K.,Graesser,A.C.(2012).\"Automaticdetectionoflearner\'saffectivestatesforintelligenttutoringsystems.\"UserModelingandUser-AdaptedInteraction. [11] Yeung,M.W.,&Chung,A.C.(2020).\"Dyslexiaandassistivetechnology:AI-driventoolsforimprovingliteracy.\" Computers&Education. [12] Zhu, H., & Tetreault, J. (2017). \"Natural language processing applications for education.\" Proceedings of the12th Workshop onInnovativeUseofNLPforBuilding EducationalApplications. [13] Thoutenhoofd,E.D.etal.(2019).\"CognitivemodelsofdyslexiaandAIinterventions:Acomprehensivereview.\" FrontiersinPsychology. [14] Adams,M.J.,&Briscoe,C.(2021).\"AI-assistedreadingsystems fordyslexiclearners.\"JournalofEducationalTechnology &Society. [15] Baker,R.S.etal.(2019).\"LearninganalyticsandAIinpersonalizedlearningenvironments.\"JournalofLearningAnalytics. [16] Zhang,X.,&Liu,L.(2018).\"Deeplearningmodelsfordyslexiadetectionandintervention.\"InternationalJournalofArtificialIntelligence inEducation. [17] McCarthy,J.etal.(2020).\"Speechrecognitiontoolsfordyslexicstudents.\"IEEETransactionsonSpeechandAudio Processing. [18] Jain, L. C., & Martin, N. (2016). \"Adaptive educational hypermedia systems using AI.\"Journal of ArtificialIntelligenceinEducation. [19] Nguyen,T.,&Zafar,A.(2020).\"AI-basedcontinuous assessment inadaptivelearningenvironments.\"IEEEAccess. [20] Gomez-Perez,D.etal.(2021).\"AhybridAIapproachforpersonalizeddyslexiainterventions.\"ExpertSystemswithApplications.

Copyright

Copyright © 2025 M. Maragadhavalli Meenakshi, V. Visakan, P. Deepak, G. Bhuvaneshwaran, D. Manoj Kiran. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.