Developing Personalised Learning Plans Using Artificial Intelligence: Implications for Inclusive and Neurodiverse Learning Environments

 

Background

Personalised Learning Plans (PLPs) have long been recognised as a mechanism for supporting learner diversity by tailoring educational experiences to individual needs, strengths, and aspirations. The emergence of artificial intelligence (AI) in education has significantly expanded the potential of PLPs by enabling real-time adaptation, data-informed decision-making, and scalable individualisation. By critically examining the role of AI in the development and implementation of personalised learning plans, with a particular focus on inclusive and neurodiverse learning environments. Drawing on Universal Design for Learning (UDL), self-regulated learning theory, and inclusive education frameworks, the paper explores how AI can support learner profiling, goal setting, adaptive pathways, formative assessment, and feedback. Ethical considerations, including data privacy, algorithmic bias, and the risk of over-automation, are also examined. The article argues that AI-enabled PLPs, when guided by strong pedagogical principles and ethical oversight, can enhance learner agency, accessibility, and educational equity while reinforcing educators' leading role as designers and interpreters of learning experiences.

Keywords: personalised learning, artificial intelligence, inclusive education, neurodiversity, learning analytics

Introduction

Schools worldwide face the challenge of meeting the needs of increasingly diverse classrooms. Traditional teaching methods that focus on standardisation and a single pace often cannot address differences in ability, interests, culture, or how students think and learn (Tomlinson, 2017). PLPs help meet this challenge by providing structured ways to personalise learning goals, paths, and support for each student.

New developments in AI have renewed interest in personalised learning by enabling systems to adapt to how students behave and perform. AI tools can process large amounts of learning data, find patterns, and suggest personalised content, pacing, and feedback in ways impossible for humans alone (Holmes et al., 2019). This is especially important in inclusive classrooms, where students, including those who are neurodiverse, may need different types of support that change over time.

This paper explores how AI can create effective and ethical personalised learning plans in inclusive classrooms. It places AI-powered PLPs within established teaching and learning theories, examines their practical application, and considers the ethical and professional responsibilities involved. The main point is that AI can improve PLPs by supporting teachers' judgement and helping students take charge of their learning, not by replacing educators.

Theoretical Foundations of Personalised Learning

Personalised Learning and Inclusive Education

Personalised learning is based on the idea that students vary in how they engage with, understand, and show what they know (Pane et al., 2017). In inclusive education, personalisation is closely tied to fairness, aiming to give each student the support they need to fully participate in learning (Florian, 2019). Instead of lowering standards, inclusive personalisation focuses on making learning accessible, flexible, and responsive.

Personalised learning is especially important for neurodiverse students, such as those with autism, ADHD, dyslexia, or other cognitive differences. The neurodiversity approach does not see these differences as deficits, but as natural variations in how people think (Armstrong, 2012). AI-powered PLPs can support this view by focusing on students' strengths, preferences, and flexible supports instead of fixed labels.

Universal Design for Learning and Self-Regulated Learning

Universal Design for Learning (UDL) is a key framework for personalised learning because it encourages different ways for students to engage, access information, and show what they know (CAST, 2018). AI can put UDL into practice by offering different formats, supports, and learning paths that fit each student's needs.

Self-regulated learning (SRL) theory also shapes AI-supported PLPs by highlighting the importance of students setting their own goals, tracking their progress, and thinking about their results (Zimmerman, 2002). AI tools that show progress, give quick feedback, and encourage reflection can help students build the thinking skills they need for lifelong learning.

 AI-Enabled Components of Personalised Learning Plans

Learner Profiling and Data-Informed Insights

AI-driven PLPs start by creating a complete profile for each learner. AI brings together data from tests, learning platforms, engagement records, and student self-reports to build a picture of each student's needs and strengths (Siemens & Baker, 2012). Unlike fixed profiles, these AI-supported profiles update as students learn and evolve with their needs and goals.

In inclusive settings, it is important that learner profiles do not reduce students to their challenges or weaknesses. Profiles should be clear, open to change, and, when possible, created together with students. This way, data can help open rather than limit learning opportunities (Selwyn, 2019).

Personalised Goal Setting and Learning Pathways

AI can help turn curriculum standards into learning goals that match each student's readiness and interests. Adaptive systems can suggest realistic milestones, recommend additional challenges, or indicate when more support is needed (Luckin et al., 2016). When students are involved in this process, it can boost their motivation and sense of ownership.

AI systems can create learning paths that adjust the order, pace, and difficulty of lessons based on how students are performing. For neurodiverse students, this flexibility can help prevent overload and support planning skills by breaking learning into smaller, manageable steps.

Adaptive Content and Assessment

AI-powered PLPs often use adaptive content, providing students with information in different ways and offering new explanations when they misunderstand something. This aligns with UDL principles and supports students who learn best through a mix of formats (CAST, 2018).

Assessment in AI-supported PLPs usually focuses on ongoing, low-pressure methods. Tools such as adaptive quizzes, instant feedback, and learning analytics help identify learning challenges early, so teachers do not have to rely solely on final tests (Redecker & Johannessen, 2013). Still, it is important that people, not just machines, interpret the results.

Benefits of AI-Driven Personalised Learning Plans

Adding AI to PLPs brings several benefits. It lets teachers support more students without making their workload unmanageable. It also makes learning more accessible by giving each student the support they need. AI feedback and progress tracking can also help students feel more confident and engaged (Bandura, 1997).

In inclusive education, AI-powered PLPs can help teachers step in early, lower barriers to participation, and focus on students' strengths. Used carefully, these systems can make learning environments fairer for everyone.

Ethical and Pedagogical Considerations

Even though AI-powered PLPs have many benefits, they also raise important ethical questions. Protecting students' data and obtaining their consent are crucial, especially when handling sensitive information. Schools must comply with data protection laws and adopt clear, open data practices (OECD, 2021).

Another challenge is bias in AI systems, which can arise when the data used to train them does not fairly represent everyone. To address this, it is important to regularly check these systems, have them overseen, and involve both teachers and students in their design (Holmes et al., 2022).

There is also a risk of relying too much on automation, which can weaken teachers' judgement or treat students as just data. To use AI ethically in PLPs, technology should support decisions, not make them alone.

The Role of Educators in AI-Enabled PLPs

Teachers remain at the heart of personalised learning, even when AI is involved. They design learning experiences, interpret AI insights, support students' wellbeing, and ensure ethical practice. Ongoing training helps teachers feel confident using AI and understand how it fits with good teaching practice (Williamson & Eynon, 2020). Instead of replacing teachers, AI can help them focus on the creative and personal parts of teaching that only people can do.

Conclusion

Artificial intelligence can greatly improve personalised learning plans, especially in inclusive and neurodiverse classrooms. By enabling flexible changes, using data to guide learning, and enabling individual support at scale, AI can help students in ways that align with UDL, self-regulated learning, and inclusive education. For AI-powered PLPs to work well, they must be used thoughtfully, with strong ethics and ongoing human involvement. When teachers, students, and schools work together to guide AI use, personalised learning plans can help create more fairness, student choice, and positive change in education.

References

Armstrong, T. (2012). Neurodiversity in the classroom. ASCD.

Bandura, A. (1997). Self-efficacy: The exercise of control. W. H. Freeman.

CAST. (2018). Universal design for learning guidelines version 2.2. http://udlguidelines.cast.org

Florian, L. (2019). On the necessary co-existence of special and inclusive education. International Journal of Inclusive Education, 23(7–8), 691–704. https://doi.org/10.1080/13603116.2019.1622801

Holmes, W., Bialik, M., & Fadel, C. (2019). Artificial intelligence in education: Promises and implications for teaching and learning. Center for Curriculum Redesign.

Holmes, W., Porayska-Pomsta, K., Holstein, K., Sutherland, E., Baker, T., Shum, S. B., Santos, O. C., Rodrigo, M. M. T., Cukurova, M., Bittencourt, I. I., & Koedinger, K. R. (2022). Ethics of AI in education: Towards a community-wide framework. International Journal of Artificial Intelligence in Education, 32, 504–526.

Luckin, R., Holmes, W., Griffiths, M., & Forcier, L. B. (2016). Intelligence unleashed: An argument for AI in education. Pearson.

OECD. (2021). AI in education: Challenges and opportunities. OECD Publishing.

Pane, J. F., Steiner, E. D., Baird, M. D., & Hamilton, L. S. (2017). Informing progress: Insights on personalized learning implementation and effects. RAND Corporation.

Redecker, C., & Johannessen, Ø. (2013). Changing assessment—Towards a new assessment paradigm using ICT. European Journal of Education, 48(1), 79–96.

Selwyn, N. (2019). Should robots replace teachers? Polity Press.

Siemens, G., & Baker, R. S. J. D. (2012). Learning analytics and educational data mining. Proceedings of the 2nd International Conference on Learning Analytics and Knowledge, 252–254.

Tomlinson, C. A. (2017). How to differentiate instruction in academically diverse classrooms (3rd ed.). ASCD.

Williamson, B., & Eynon, R. (2020). Historical threads, missing links, and future directions in AI in education. Learning, Media and Technology, 45(3), 223–235.

Zimmerman, B. J. (2002). Becoming a self-regulated learner. Theory Into Practice, 41(2), 64–70.