Skip to content

AI in Education: How LMS Analytics Can Personalise Education

lms analytics aied AI in education Shamsher Haider SQL, ML AI Bigdata Data Engineering

Learning Management Systems (LMS) have been a ubiquitous element of modern education and can be considered the bedrock of developments in AI in Education .Platforms like Canvas,Blackboard, and Brightspace serve as central hubs for distributing course materials, managing assignments, and facilitating communication between instructors and students. However, despite their widespread adoption, LMS usability often falls short of ideal, with both students and educators encountering limitations in functionality and user-friendliness.

This article explores the potential of AI in Education in conjunction with Learning Analytics (LA) to address these shortcomings and improve the overall LMS experience for students. LA refers to the collection, measurement,analysis, and reporting of data about learners’ interactions with a learning environment. By leveraging this data and the power of AI, LMS developers can design features that provide targeted support and personalize the learning experience for each student.

Current Landscape of LMS Usability

Research suggests a disconnect between the intended functionalities of LMS and the actual user experience. Studies by Orfanou et al.,(2015) and Tevekeli, (2022) highlight student and educator frustrations with cumbersome interfaces and a lack of features that truly enhance usability. These limitations can hinder student engagement and ultimately impede learning outcomes.

The Power of AI in Learning Analytics

LA offers a data-driven approach to bridge this gap. By analyzing student interactions with course materials, assignments,and discussions within the LMS, LA tools can glean valuable insights into student behavior and learning patterns.However, when this data is analyzed by AI algorithms, it unlocks a new level of personalization:

  • Adaptive Learning Powered by AI: AI can analyse student performance data and learning patterns to identify areas of strength and weakness. This information can then be used to recommend supplementary materials, suggest connections to previously covered topics, or even adjust the difficulty level of learning modules in real-time.Essentially, AI can tailor the learning path to the individual needs of each student.
  • Intelligent Tutoring Systems: AI-powered tutoring systems can analyze student performance and intervene at the moment of need. Imagine an LMS that can identify a student struggling with a specific concept and provide immediate, personalized feedback or suggest alternative learning resources. This can significantly improve student comprehension and reduce the feeling of being lost in the learning material.
  • Predictive Analytics for Early Intervention: AI can analyse historical student data to predict students at risk of falling behind or dropping out. This allows instructors to proactively intervene and offer additional support before issues escalate.

Beyond Personalisation: Additional Benefits of AI in Education

The potential of AI in LMS extends beyond personalization. Here are some additional benefits:

  • Automated Grading and Feedback: AI can automate the grading of certain types of assessments, freeing up instructor time for more personalized feedback and interaction with students.
  • Content Creation and Curation: AI can assist instructors in creating personalized learning materials or curating existing resources based on student needs and learning styles.


While AI in Education offers a compelling path forward, it is crucial to acknowledge potential drawbacks. Data privacy concerns and the ethical implications of student behavior analysis must be carefully addressed. Additionally, further research is needed to explore the optimal integration of AI features within LMS interfaces to ensure user-friendliness and maximise their effectiveness.

In conclusion, Artificial Intelligence in conjunction with Learning Analytics presents a transformative opportunity to personalise education within Learning Management Systems. By harnessing the power of data and intelligent algorithms, LMS can evolve from static content repositories into dynamic platforms that actively support and empower student learning. As research and development in this area progress, we can expect to see LMS platforms that not only deliver content but also become intelligent companions, tailoring the educational experience to each student’s unique journey towards knowledge acquisition.


  • Chen, Y., Lin, Y., & Liu, S. (2021). Affordances of a learning management system (LMS) for teachers’ professional development in the context of online learning environments.  International Journal of Educational Technology in Higher Education, 18(1), 1-18. 
  • Cobb, C., Evans, N., Jafari, A., & Le, H. (2018).  Developing online teacher education courses: A design resource.Springer.
  • Derick, R., Hao, Y., Martinez, M. E., & Moreno-Ger, P. (2017, July). Visualizing learner affect in an LMS: A case study on student engagement and performance. In Proceedings of the 2017 ACM on Conference on Human Information Processing in Education (pp. 261-266). ACM. 
  • Feild, H. S. (2015). Nudge theory: Applications in behavior change communication. Health Promotion Practice,16(1), 126-134. 
  • Kia, R., Elçi, A., Yılmaz, O., & Şen, A. (2020).  Learning Analytics: Data, Pattern, and Applications. CRC Press.
  • Orfanou, M., Economides, A., & Papadopoulou, V. (2015). Usability evaluation of a learning management system:A case study.  Interactive Technology and Smart Education, 12(3), 142-158. 
  • Sahin, S., & Ifenthaler, D. (2021). Learning analytics dashboards: A systematic review of design elements and functionalities.  Educational Technology Research and Development, 69(4), 1675-1709. 
  • Sahin, S., & Yurdugül, N. (2022). The effects of peer comparison interventions delivered through learning analytics dashboards on student achievement and self-efficacy.  Computers & Education, 182, 103582. 
  • Salas-Pilco, Y. A., Peña-Ayala, M., & Zapata-Rosas, J. A. (2022).  Artificial Intelligence in Education: Approaches and Applications. Springer International Publishing.
  • Schumacher, C., & Ifenthaler, D. (2018). Learning analytics dashboards to support student self-regulation in blended learning environments.  The International Journal of Learning Analytics and Student Services, 5(2), 3-20.
  • Sedrakyan, G., Balakrishnan, G., Eagle, M., Djamasbi, S., Hung, J., Jovanovic, V., Rafferty, A., & Sullivan, D. G.(2020).  Learning Analytics: From Research to Practice. Springer International Publishing.
  • Shakarian, P. (1995). A goal theory of motivation in academic settings.  Educational Psychologist, 30(4), 149-156.
  • Susnjak, M., Tepić, I., Kovačić, M., & Kovačić, Ž. (2022). Learning analytics at universities: A systematic review of benefits and challenges.  Sustainability (Switzerland), 14(3), 1096.