How Artificial Intelligence Is Impacting on the STEM Education of

Students with Disabilities: A Five Years Review

Marina Buzzi

, Giuditta Pieriboni

and Barbara Leporini

2,3 b

IIT-CNR, via Moruzzi 1, 56124 Pisa, Italy

Department of Computer Science, University of Pisa, via Fibonacci, Pisa, Italy

ISTI-CNR, via Moruzzi 1, Pisa, Italy

Keywords: Accessibility, AI, Education, STEM, Student with Disabilities.

Abstract: Artificial intelligence promises to revolutionize our life, bringing significant advances in any fields: health,

education, work and leisure time. This paper analyzes the last 5-year literature concerning the use of AI for

supporting people with disabilities in education. The aim is to investigate the current state of art of accessible

applications in the STEM (Science, Technology, Engineering, Mathematics) field and understand if contents

and tools are accessible for all, regardless of personal need and abilities. Personalization and adaptation

emerge as fundamental factors when designing for people with disabilities. Privacy and ethics aspects often

neglected are very relevant. The analysis suggests that the STEM field still suffers from accessibility gaps,

and current tools need to evolve and be increased to be exploited by different disabilities and ensure the same

opportunities for every student, engaging, motivating, and empowering them..

1 INTRODUCTION

People with Disabilities (PD) can experience many

difficulties and obstacles when studying, if materials

are not fully accessible, ie. suitable for their sensorial

needs, learning pace, interaction and cognitive

abilities. Artificial Intelligence (AI) can greatly

support students with disabilities in different ways

(Jadán-Guerrero et al., 2024). First of all personalized

learning and adaptive systems (Katonane Gyonyoru

2024, Tapalova & Zhiyenbayeva, 2022) can improve

students’ performance, engagement, and motivation.

AI tutors and chatbots can leverage difficulties and

obstacles encountered by people with sensorial,

cognitive or physical impairment supporting students

in their educational path (Neha et al., 2024, Nacheva

& Czaplewski 2024). Unfortunately few attention is

devoted to accessibility of chatbots for visually

impaired (Grassini et al. 2024).

Accessibility of educational content and materials

is necessary for a student with disability, to have the

same possibilities to study and build a satisfying

career as any other person. This requires different

assistive technologies and tools being adopted for

different impairments. Content simplification is

https://orcid.org/0000-0003-1725-9433

https://orcid.org/0000-0003-2469-9648

useful to improve comprehension for students with

cognitive and learning disabilities (Heuer &

Glassman, 2023). Specific AI tools assist and

empower students with disabilities. They include

assistive technologies (de Freitas, et al., 2022), real-

time AI captioning systems very useful for deaf and

hard-of-hearing students (Coy et al., 2024), text-to-

speech systems to support people with learning

disabilities (Bhatti et al. 2024) and real-time image

recognition and description crucial for the visually

impaired and blind students to be able to understand

the educational meaning delivered by the image

(Islam et al., 2023).

AI based emotional recognition systems and

chatbots can support students with emotional or

cognitive disabilities in deal with different situations

and scenarious. They are able to detect emotional

states and deliver them in an accessible way offering

cognitive and behaviour support for students with

learning disabilities or attention disorders (Neha et

al., 2024, Hopcan et al., 2023). Last, concerning

physical disability, AI-based Wearable Devices and

robots assist students in mobility and movements

(Pancholi et al.2024). However despite this great

progress in AI applied to educational field, students

Buzzi, M., Pieriboni, G. and Leporini, B.

How Artiﬁcial Intelligence Is Impacting on the STEM Education of Students with Disabilities: A Five Years Review.

DOI: 10.5220/0013267900003932

Paper published under CC license (CC BY-NC-ND 4.0)

In Proceedings of the 17th International Conference on Computer Supported Education (CSEDU 2025) - Volume 1, pages 323-330

ISBN: 978-989-758-746-7; ISSN: 2184-5026

323

still can experience difficulties and obstacles,

especially in STEM education field where images are

frequent content and accessibility problem are still

present (Buzzi et al. 2024).

This study is part of the PRIN project

2022HXLH47 “STEMMA -Science, Technology,

Engineering, Mathematics, Motivation and

Accessibility” (funded by the European Union - Next

Generation EU, Mission 4 Component C2 CUP

B53D23019500006). We carried out a systematic

review study to understand how AI based technology

is actually exploited in education in the STEM field.

Specifically, this study aims to answer the following

research questions:

RQ1: What are applications of AI in the field of

inclusive education?

RQ2: In the STEM field, there are effective AI-

based tools for inclusive education?

The paper is organized in 5 section. After this

introduction the method is described in section 2.

Section 3 includes a table summarizing main features

of the selected paper. Section 4 discusses results

showing how literature progresses in this field and

analyzing current trend and future research

challenges. Last conclusion ends the paper.

2 METHOD

Considering the focus of our search is on STEM field

accessibility for students with disabilities, an

extensive search has been carried out by this paper

authors in 2 popular scientific databases: Google

Scholar which includes main scientific publishers

(IEEE Xplore, ACM, Elsevier, Springer, Elsevier,

Acta, etc.) and PubMed, more oriented to clinical and

psychological fields. As previously mentioned our

focus is on accessibility of STEM content and

educational journey. Applying 3 keywords “artificial

intelligence” and “students with disabilities” and

“stem” since 2020 (last 5 years) we retrieved 15.800

results in scholar and only 1 in PubMed. So we

decided to increase the Keywords to restrict the

search output of Google Scholar in a more

manageable number of items and to discard PubMed

since it seems to not be focused on ICT field.

Refining the search with Google Scholar, 7

Keywords have been selected in order to limit the

number of results in a set to easily screen manually

by researchers: “artificial intelligence" and "students

with disabilities" and "app" and "stem" and

"inclusion" and "education" and "user experience".

We included the term “app” to try selecting actual

implementation and the terms "inclusion" and

"education" and "user experience" to select HCI

oriented studies.

Applying the filters: since 2020 and review

studies we retrieved 143 item results in

Google.scholar.com. Figure 1 shows results

distributed by years, also detailing the review studies.

The number of total papers is very increased in the

last 2 years, confirming the increased interest in this

research field. This review included papers published

until September 2024.

Figure 1: The graph shows the total of retrieved papers by

year, and the reviews studies.

The screening process started with a 1st iteration

consisting in reading title and abstract to verify the

focus on AI and the educational field. General studies

do not involving artificial intelligence or not related

to the education field as well as low-quality papers

(by predatory publishers) have been discarded. In this

process about 2/3 of retrieved items were discarded

(N=91), reducing the candidate papers to 52. A 2nd

iteration consisted in reading the papers and selecting

the more focused on our research focus, i.e. students

with disability. Unfortunately although mentioning

students with disability many papers were not focused

on this population. Then after the second screening

only 21 papers have been eligible for our study.

3 THE STUDY

The selected papers have been categorized by a)

content type (theoric study, review, implementation)

b) Purpose or Use of AI c) Target Disabilities, d)

Technology/Method, e) user test. In case of system or

application the last parameter records if the app or

system has been tested with targeted users. Table 1

organizes the analyzed studies versus the selected

parameters.

CSEDU 2025 - 17th International Conference on Computer Supported Education

324

Table 1: Select papers ordered by years.

SOURCE Type

PURPOSE

Or USE of AI

TARGET Disability

Technology/

Method

TEST

Pierrès et al. 2024 Systematic Review

Could the use of AI in higher education hinder students with

disabilities?

All disabilities

Kim et al. 2024 Theoric study

Improving communication and promoting social inclusion for

hearing-impaired users

Hearing-impaired Mobile applications yes

Bhatti et al. 2024 Review

Reviewing/assessing AI applications for students with learning

disabilities

Learning disabilities

Rai et al. 2024 Implementation

Ethical and social impact of AI driven analysis for students with

learning disabilities

Learning disabilities

Song et al. 2024 Theoric study

Developing a framework for inclusive AI learning design for

diverse learners

Learning disabilities

Hamash et al. 2024 Review

Systematic Review of Extended Reality in Education for the

Visually Impaired

Stalmach et al.

2024

Theoric study

Research study of digital learning methods that promote

inclusive learning in schools

Learning disabilities

Mogavi et al. 2024 Theoric study

Assessing ChatGPT in education: a qualitative study exploring

early adopters’ utilization and perceptions

All disabilities

Shivashankar et al.

2024

Theoric study

AI’s potential in crafting an inclusive, personalized and efficient

learning environment for children with disabilities

All disabilities

Sumak et al. 2024 Focused Review

To identify and discuss benefits and challenges of AI-based tools

in inclusive higher education

All disabilities

Watters et al. 2024 Implementation

Make hands-on laboratory tasks accessible.

The Denver Virtual Lab Assistant enables students with VI to

perform the laboratory using voice control. The Assistant can be

accessed via smartphone or Amazon Echo device

Visually impaired

Amazon Web Services, Alexa

Skills Kit, microcontroller

Raspberry Pi. Compatible with

Talking LabQuest

Zhai et al. 2023 Systematic Review

Systematic review on AI and education for student with special

needs

Learning disabilities

Frolli et al. 2023 Theoric study

Artificial intelligence (AI) to generate images based on text

descriptions, facilitating communication for individuals with

autism

Students with ASD

Contreras-Ortiz et

al. 2023

Systematic review Systematic review: E-Learning Ecosystems for people with ASD Students with ASD

PRISMA approach (2017 – 2022

studies)

Iniesto et al. 2023 Implementation

Creation and test of conversational user interfaces (CUIs) to

facilitate web interaction for students with disabilities

Visual and learning

disabilities

MS Azure Cognitive Services.

Direct Line speech. AI Services

QnA Maker and Language

Understanding

Herdliska & Zhai

2023

Use of SW in science

classes

AI-based scientific inquiry to K-12 students in a way that science

is manifested (Google Teachable Machine)

Learning disabilities

Hughes et al. 2022 Implementation

Robotics & AI to improve STEM and social skills for students

with ASD

Students with ASD yes

Das 2021 Implementation

Making computer science concepts accessible to K-12 students

who are Deaf/Hard of Hearing, Blind/Low Vision and those with

motor disabilities providing technical strategies to break

accessibility barriers

Visually Impaired/

Hearing impaired/

Motor disabilities

yes

Lai 2021 Theoric study

Recommendations for secondary and higher education in terms

of digital assessment formats, content, and approach to enhance

learning of mathematics.

All disabilities

Zingoni et al 2021

Design for

Implementation

BeSpecial exploits AI to suggest the most suitable strategies for

each student (best practices for teachers and digital tools to

deliver more accessible contents)

Dyslexya Yes

Das et al. 2021 Theoric study

Producing videos and developing an accessible block-based web

application for deaf/hard hearing students

Hearing-impaired

users

How Artiﬁcial Intelligence Is Impacting on the STEM Education of Students with Disabilities: A Five Years Review

325

4 DISCUSSION

In this review we analyze scientific studies involving

AI for enhancing education of students with

disabilities. Impaired functioning of perception

channels makes the STEM journey of students more

challenging. Deaf students in STEM fields often face

challenges due to a lack of teachers experienced in

working with deaf individuals, missing the deep

knowledge their communication needs. This can

result in deaf students feeling discomforted or unable

to study STEM subjects (Meghdari & Alemi 2020).

For blind and visually impaired students STEM is

intrinsically difficult since it is hard to appropriately

decode diagrams, formulas, functions, i.e. to be able

to fully understand the semantic value of complex

images. Alternative text for digital images does not

guarantee that the description is accurate especially if

performed by automated tools, including AI large

language model (LLM) (Buzzi et al. 2024). The

alternative text should be accurate and descriptive

while concise as possible, to not overload the user

with information not useful (Leotta et al 2023).

Learning disabilities as well as students with ASD

can very benefit from personalization and adaptation.

Stalmach et al. (2024) investigate numerous digitally

enhanced learning methods, focusing on students

with special needs in an inclusive learning

environment. These approaches have the potential of

improving students’ academic skills and social

performance, but, due to the unicity of each student

with learning disability, their effectiveness depends

on the competence, flexibility, and adaptability of the

teacher delivering accessible instructions and

providing adequate support.

Review studies included in this analysis,

investigate general aspects for all disabilities such as

ethics, privacy, educational and social impact, or

focus on a specific theme (focused reviews, system or

apps implementation, etc.). In the following first we

describe these general studies and after we move on

focused studies organizing them by type of disability.

Pierrès et al. (2024) carried out a review analyzing

72 articles presenting AI educational technologies in

higher education and observed that there is a clear

lack of ethical consideration for students with

disabilities. Many of analyzed articles did not

consider ethics and mainly focus on privacy,

transparency, or bias. The perspective of people with

disabilities is rarely considered and they are at

discrimination risk for bias and exclusion, when AI is

exploited for assessing students. Mogavi et al. (2024)

investigated the adoption and perception of ChatGPT

in education by analyzing qualitative data collected

from social media platforms. Content creation and

editing emerged as the most prevalent applications of

this technology in higher education (78.11%).

However opportunities for ChatGPT to support

learning are undermined by concrete risks associated

with overreliance on this tool: critical thinking and

creativity limitation, lack of a deep understanding,

that could favor laziness and passivity.

Song et al. (2024) proposed a framework for

inclusive AI learning design grounded in recent

literature on AI learning and the principles of UDL

(Universal Design for Learning). The proposed

framework relies on “AI Five Big Ideas” and

emphasizes inclusivity by funding on the three UDL

principles i.e., engagement (“why”), representation

(“what”) and action & expression (“how”).

Shivashankar & Bakthavatchaalam (2024)

explored the development of data-driven

management practices and policies to address the

educational needs of children with disabilities

proposing a model for helping that all students,

regardless of their abilities, have the opportunity to

have success at school. Artificial Intelligence in

education can offer personalized learning

experiences, adaptive assessments, and smart content

delivery, transforming the way students learn and

interact with educational content (Aithal, & Maiya

2023).

Contreras-Ortiz et al. (2023) analyzed 20-years of

scientific of literature observing the evolution of AI

approaches from static data to currently sophisticated

large language models able to deal with huge amount

of real-time multi-modal data (e.g., student-

teacher/peer interaction data, click-stream

information, web-browsing data).

Aldoukhi et al. (2023) analyzed personal

assistants like Siri, Alexa, and Google Assistant to

support students with disabilities in accessing

information and communicate naturally via voice. AI-

powered real-time captioning and speech recognition

software can aid the hearing-impaired and students

with physical disabilities. Predictive text and natural

language processing system can support people with

cognitive disabilities, while smart devices and

chatbots can enable greater control and access

supporting students. Adaptive learning software

exploits artificial intelligence to customize the

educational training path and satisfy the unique needs

of every students. Personalized instruction and

feedback can be delivered via AI tutors.

Zhai & Panjwani-Charania (2023) carried out a

systematic review on AI and education for student

with special needs categorizing the application field:

Adaptive learning was the most frequent use of AI in

CSEDU 2025 - 17th International Conference on Computer Supported Education

326

the educational field. AI is used to deliver learning

support based on individual learning needs. This

includes intelligent, serious games, intelligent

tutoring systems, or advanced e-learning

management system. Intelligent tutor exploits

dynamic machine learning models to detected

student’s learning difficulties and recommend a

personalized learning strategy. Intelligent assistants

support effectively students with ASD or dyslexia.

Exploiting AI to enhance Augmentative and

Alternative Communication (AAC) increases the

ease of verbal communication for students. AI tools

correct frequent text writing errors of students with

dyslexia. AI based chat assistants provide

accessibility support to students.

Iniesto et al. (2023) created conversational user

interfaces (CUIs) that supports written and spoken

dialogue, as a simpler a natural interaction alternative

to static web forms filled by students with disabilities.

Concerning engagement and monitoring students’

progress over time, machine learning and AI models

are exploited to understand the user’s progress and

support the user in achieving mastery (mastery

learning) and facial expression recognition to

predicting student engagement.

4.1 Visually Impaired

Watters et al. (2021) implemented a new AI tool, the

MSU Denver Virtual Lab Assistant that enables

visually impaired students to perform the hands-on

laboratory autonomously using voice control. This is

very important for student autonomy and self-

confidence. The system accessed through any

smartphone or via Amazon Echo assists the student in

the science lab tasks. It is designed to be applicable to

different science laboratory works. This AI based

system is an inclusive tool making accessible science

education lab tasks to visually impaired. Sounds

augmentation associated to haptic and tactical

feedback delivers sensory information and enable an

Augmented Reality experience for visually impaired

users, tailored to meet specific needs of the user. In

this context artificial intelligence personalizes the

learning experiences and delivers real-time feedback

in the educational applications (Hamash et al., 2024).

4.2 Hearing-Impaired

Kim et al (2024) investigates the usability of

communication-assistive applications for hearing-

impaired users, with a focus on enhancing user

experience and promoting social inclusion showing

that improvements are necessary. The increasing

employ of AI requires more inclusive research

methodologies that involve disabled individuals in

designing of apps, products and services. It is crucial

considering the unique requirements and experiences

of hearing-impaired users, when developing user

interfaces that favor relations and social support.

Das et al (2020) investigates how to improve

Computer Science and coding skill in K-12 deaf/hard

hearing students delivering Sign Language video

resources and an interactive funny block-based

coding learning environment (web application) where

students can control programmatically a robot, in

order to favor and stimulate independent learning and

creative problem solving (based on MIT’s Scratch).

4.3 Motor Impaired

Das (2021) suggests how to create Accessible Block-

Based Programming tools for students with different

needs. Motor Disabilities population can exploit

speech-to-text converters and the case for language

understanding by using AI to enhance these solutions.

4.4 Learning Disabilities

This impairment impacts in one or more processes

involved in language comprehension or usage and

reduced ability in listening, thinking, speaking,

reading, writing, spelling or performing mathematical

computations (dyslexia, dyscalculia, ...). Bhatti et al.

(2024) carried out a systematic review on Artificial

Intelligence Applications for Students with Learning

Disabilities. Seven distinct types of AI applications

can support students with learning disabilities:

adaptive learning emerged as the most prevalent,

facial expression analysis, chat robots,

communication assistants, mastery learning systems,

intelligent tutors, and interactive robots. They show

the great potential of AI in enhancing the educational

experience for students with learning disabilities.

Rai et al. (2024) integrated AI capabilities (for

gesture recognition) to provide recommendations for

enhancing education through a decision support

system (DSS). Exploiting artificial intelligence to

select appropriate study strategies can contribute to

reduce the negative effects of learning disabilities on

student academic performance. This is achieved by

offering personalized interventions, adjusting

educational methods to match students' cognitive

profiles, and promoting inclusivity. In this way

academic results improve for any students, regardless

of their abilities.

Zingoni et al. (2021) exploits students’ clinical

reports of dyslexia, survey results, and psychometric

How Artiﬁcial Intelligence Is Impacting on the STEM Education of Students with Disabilities: A Five Years Review

327

test results as inputs to train AI algorithms, in order

to be able to predict individual needs (e.g.,

concentration, memory impairments) and provide

support and adaptive strategies (e.g., conceptual

maps, schemes, highlighted keywords).

4.5 Autism Spectrum Disorder

Interaction is an important challenge especially for

students with Autism spectrum disorder (ASD).

Interactive and social robot offering an unambiguous

and predictable answer, can support students

exploiting multimodal machine learning to for

engagement in the classroom. Best results in

interventions with students with ASD are observed

exploiting: a) technology devices (e.g., touch screens,

smartphones, laptops, smart glasses), b) AI-based

systems, serious games, augmented reality, and

robots. Lack of generalization is one of the most

challenging factors to counteract, related to

heterogeneity of the population, the intervention

duration, and complexity of skills (Mallik et al 2023).

Hughes et al. (2022) created an virtual learning

environment that assists children with autism in

STEM skills along with improving social-emotional

and communication skills. The AI based system

delivers interactive, personalized, and individualized

process matching needs of students with ASD. The

system control if students are at the tablet and are

making progress on the programming tasks. Results

suggest that creating student-driven AI tools, that

students can use to assist their self-regulation in any

environment, could help neurodivergent people being

represented in STEM fields.

In addition to personalized learning and

communication support AI-based tool can provide

Behavioral and Emotional Support: detecting patterns

of behaviors and providing feedback to help

individuals to keep behaviors adequate to the context

and training them to regulate their emotions (Frolli et

al., 2023).

Despite the large amount of STEM literature, only

few studies focus on STEM and students with

disabilities and accessibility of SW tools, digital

materials, and multimedia educational contents. Lai

(2021) analyzes literature and accessibility of

software for learning math currently on the market

providing useful recommendations in terms of

assessment formats, content, and approach to enhance

learning for students with disabilities in higher

education. There is not an accessible tool that would

promote learning for everyone but a good tool suits

the needs of the pupils and teachers. Herdliska & Zhai

(2023) investigates the use of Google Teachable

Machine, an AI application, to lead science classes.

Teachable Machine exploits AI and machine learning

to develop algorithms that could solve complex,

concrete problems, offering a great support for STEM

topics for students with learning disabilities.

5 CONCLUSION

AI is rapidly transforming the educational ecosystem

by making learning more inclusive by empowering

students with disabilities in deal with their academic

path. AI models still need to progress for ensuring

accessibility for people with disabilities, specifically

need to improve readability. Understandability of

chatbot output in fact depends on the prompt's focus

and current readability metrics do not discriminate

whether the text is useful or not (Nacheva &

Czaplewski 2024).

Important suggestions for promoting inclusion

through the application of Artificial Intelligence can

be delivered by caregivers (both teachers and parents)

for identifying challenges and proposing the

implementation of adapted educational resources

(Jadán-Guerrero et al., 2024). This requires adequate

infrastructure, specialized tools, inclusive

methodologies, and software to facilitate the learning

process and avoid educational gap.

To answer this study’s research questions, there

are a number of AI applications in the field of

inclusive education addressing need of different

disability but only few of them propose solutions

focused on STEM contents, suggesting that more

research is needed in this way area. Moreover the

effectiveness of AI-based tools in the STEM field

needs more effort since the most of studies do not

collect data regarding tests or effective use in

classroom with students with disabilities. Very few

apps and systems are actually implemented, tested

and used at large scale. It is urgent to create free,

reliable and usable open source solutions to benefit

students with disability in order to filling the STEM

filed gap and really offer fair opportunities for any

students.

REFERENCES

Aithal, P. S., & Maiya, A. K. (2023). Innovations in Higher

Education Industry–Shaping the Future. International

Journal of Case Studies in Business, IT, and Education

(IJCSBE), 7(4), 283-311.

Alam, A., & Mohanty, A. (2022). Foundation for the future

of higher education or ‘misplaced optimism’? Being

CSEDU 2025 - 17th International Conference on Computer Supported Education

328

human in the age of artificial intelligence. In

International Conference on Innovations in Intelligent

Computing and Communications (pp. 17-29). Cham:

Springer International Publishing.

Aldoukhi, M., Angel, M., Bare, L., Blacher, D., Cawi, J.,

Chabanel, T., ... & Mesa, J. C. (2023). Access of

Persons with Disabilities to Public Ground

Transportation and Roadways.

Bhatti, I., Mohi-U-din, S. F., Hayat, Y., & Tariq, M. (2024).

Artificial Intelligence Applications for Students with

Learning Disabilities: A Systematic Review. European

Journal of Science, Innovation and Technology, 4(2),

40-56.

Buzzi, M., Galesi, G., Leporini, B. and Nicotera A. (2024).

Is Generative AI Mature for Alternative Image

Descriptions of STEM Content? In proceedings of

Webist 2024.

Contreras-Ortiz, M. S., Marrugo, P. P., & Ribon, J. C. R.

(2023). E-Learning Ecosystems for People With

Autism Spectrum Disorder: A Systematic Review.

IEEE Access, 11, 49819-49832.

Coy, A., Mohammed, P. S., & Skerrit, P. (2024). Inclusive

Deaf Education Enabled by Artificial Intelligence: The

Path to a Solution. International Journal of Artificial

Intelligence in Education, 1-39.

Das, M., Marghitu, D., Jamshidi, F., Mandala, M., &

Howard, A. (2020). Accessible computer science for k-

12 students with hearing impairments. In UAHCI 2020,

HCII 2020, Proceedings, Part II 22 (pp. 173-183).

Springer International Publishing.

Das, M. (2021). Accessible Computer Science for K-12

Students with Disabilities (Master's thesis, Auburn

University).

de Freitas, M. P., Piai, V. A., Farias, R. H., Fernandes, A.

M., de Moraes Rossetto, A. G., & Leithardt, V. R. Q.

(2022). Artificial intelligence of things applied to

assistive technology: a systematic literature review.

Sensors, 22(21), 8531.

Drigas, A., & Kefalis, C. (2024). STREΑMING: A

Comprehensive Approach to Inclusive STEM

Education. Scientific Electronic Archives, 17(5).

Frolli, A., Cavallaro, A., La Penna, I., Sica, S. L., & Bloisi,

D. (2023). Artificial intelligence and autism spectrum

disorders: a new perspective on learning. Proc. of the

Digital Innovations for Learning and

Neurodevelopmental Disorders, Rome, Italy.

Grassini, E., Buzzi, M., Leporini, B., & Vozna, A. (2024).

A systematic review of chatbots in inclusive healthcare:

insights from the last 5 years. Universal Access in the

Information Society, 1-9.

Hamash, M., Ghreir, H., & Tiernan, P. (2024). Breaking

through Barriers: A Systematic Review of Extended

Reality in Education for the Visually Impaired.

Education Sciences, 14(4), 365.

Herdliska, A., & Zhai, X. (2023). Artificial intelligence-

based scientific inquiry. Zhai, X. & Krajcik, J. Uses of

Artificial Intelligence in STEM Education.

Heuer, H., & Glassman, E. L. (2023). Accessible Text

Tools for People with Cognitive Impairments and Non-

Native Readers: Challenges and Opportunities.

Proceedings of Mensch und Computer 2023, 250-266.

Hopcan, S., Polat, E., Ozturk, M. E., & Ozturk, L. (2023).

Artificial intelligence in special education: A

systematic review. Interactive Learning Environments,

31(10), 7335-7353.

Hughes, C. E., Dieker, L. A., Glavey, E. M., Hines, R. A.,

Wilkins, I., Ingraham, K., ... & Taylor, M. S. (2022).

RAISE: Robotics & AI to improve STEM and social

skills for elementary school students. Frontiers in

Virtual Reality, 3, 968312.

Islam, R. B., Akhter, S., Iqbal, F., Rahman, M. S. U., &

Khan, R. (2023). Deep learning based object detection

and surrounding environment description for visually

impaired people. Heliyon, 9(6).

Iniesto, F., Coughlan, T., Lister, K., Devine, P., Freear, N.,

Greenwood, R., ... & Tudor, R. (2023). Creating a

simple conversation: designing a conversational user

interface to improve the experience of accessing

support for study. ACM Transactions on Accessible

Computing, 16(1), 1-29.

Jadán-Guerrero, J., Tamayo-Narvaez, K., Méndez, E., &

Valenzuela, M. (2024). Adaptive Learning

Environments: Integrating Artificial Intelligence for

Special Education Advances. In International

Conference on Human-Computer Interaction (pp. 86-

94). Cham: Springer Nature Switzerland.

Katonane Gyonyoru, K. I. (2024). The Role of AI-based

Adaptive Learning Systems in Digital Education.

Journal of Applied Technical and Educational

Sciences, 14(2), 1-12.

Kim, H., Hwang, H., Gwak, S., Yoon, J., & Park, K. (2024).

Improving communication and promoting social

inclusion for hearing-impaired users: Usability

evaluation and design recommendations for assistive

mobile applications. PloS one, 19(7), e0305726.

Lai, S. I. Effective Online Assessment Methods for Maths

Education and Student Access. (Thesis). University of

Leeds, Institute for Teaching Excellence.

Leotta, M., Mori, F., & Ribaudo, M. (2023). Evaluating the

effectiveness of automatic image captioning for web

accessibility. Universal access in the information

society, 22(4), 1293-1313.

Mallik, S., & Gangopadhyay, A. (2023). Proactive and

reactive engagement of artificial intelligence methods

for education: a review. Frontiers in artificial

intelligence, 6, 1151391.

Meghdari, A., & Alemi, M. (2020). STEM teaching-

learning communication strategies for deaf students. In

Proc. 17th international RAIS conference on social

sciences and humanities (pp. 47-55).

Mogavi, R. H., Deng, C., Kim, J. J., Zhou, P., Kwon, Y. D.,

Metwally, A. H. S., ... & Hui, P. (2024). ChatGPT in

education: A blessing or a curse? A qualitative study

exploring early adopters’ utilization and perceptions.

Computers in Human Behavior: Artificial Humans,

2(1), 100027.

Nacheva, R., & Czaplewski, M. (2024). Artificial

Intelligence In Helping People With Disabilities:

How Artiﬁcial Intelligence Is Impacting on the STEM Education of Students with Disabilities: A Five Years Review

329

Opportunities And Challenges. HR and Technologies,

(1), 102-124.

Neha, K., Kumar, R., & Sankat, M. (2024). AI Wizards:

Pioneering Assistive Technologies for Higher

Education Inclusion of Students with Learning

Disabilities. In Applied Assistive Technologies and

Informatics for Students with Disabilities (pp. 59-70).

Singapore: Springer Nature Singapore.

Pancholi, S., Wachs, J. P., & Duerstock, B. S. (2024). Use

of artificial intelligence techniques to assist individuals

with physical disabilities. Annual Review of Biomedical

Engineering, 26.

Pierrès, O., Christen, M., Schmitt-Koopmann, F., &

Darvishy, A. (2024). Could the Use of AI in Higher

Education Hinder Students With Disabilities? A

Scoping Review. IEEE Access.

Rai, H. L., Saluja, N., & Pimplapure, A. (2024). Ethical and

Social Impact of AI Driven Analysis for Students with

Learning Disabilities Processes. Journal of Electrical

Systems, 20(7s), 2704-2715.

Salas-Pilco, S. Z., Xiao, K., & Oshima, J. (2022). Artificial

intelligence and new technologies in inclusive

education for minority students: a systematic review.

Sustainability, 14(20), 13572.

Shivashankar, K., & Bakthavatchaalam, V. (2024).

Education Policies Through Data Driven Decision

Making: Accelerating Inclusive Education for People

with Disabilities. Artificial Intelligence Enabled

Management: An Emerging Economy Perspective, 15.

Song, Y., Weisberg, L. R., Zhang, S., Tian, X., Boyer, K.

E., & Israel, M. (2024). A framework for inclusive AI

learning design for diverse learners. Computers and

Education: Artificial Intelligence, 100212.

Stalmach, A., D’Elia, P., Di Sano, S., & Casale, G. (2024).

Digital methods to promote inclusive and effective

learning in schools: A mixed methods research study.

Open Education Studies, 6(1), 20240023.

Tapalova, O., & Zhiyenbayeva, N. (2022). Artificial

intelligence in education: AIEd for personalised

learning pathways. Electronic Journal of e-Learning,

20(5), 639-653.

Watters, J., Hill, A., Weinrich, M., Supalo, C., & Jiang, F.

(2021). An Artificial Intelligence Tool for Accessible

Science Education. Journal of Science Education for

Students with Disabilities, 24(1), n1.

Zhai, X., & Panjwani-Charania, S. (2023). AI for Students

with Learning Disabilities: A Systematic Review. In X.

Zhai & J. Krajcik (Eds.), Uses of Artificial Intelligence

in STEM Education. Oxford University Press.

Zingoni, A., Taborri, J., Panetti, V., Bonechi, S., Aparicio-

Martínez, P., Pinzi, S., & Calabrò, G. (2021).

Investigating issues and needs of dyslexic students at

university: Proof of concept of an artificial intelligence

and virtual reality-based supporting platform and

preliminary results. Applied Sciences, 11(10), 4624.

CSEDU 2025 - 17th International Conference on Computer Supported Education

330