Explainable Artificial Intelligence in Higher Education: A Systematic Literature Review of Methods, Applications, Challenges and Research Gaps

Sasikala P; Asha N; Pushpalatha M; Santhosh Kumar B N

Explainable Artificial Intelligence in Higher Education: A Systematic Literature Review of Methods, Applications, Challenges and Research Gaps

Author(s)	Dr. Sasikala P, Dr. Asha N, Dr. Pushpalatha M, Dr. Santhosh Kumar B N
Country	India
Abstract	Artificial Intelligence (AI) and Machine Learning (ML) have been increasingly applied in higher education with aims of student-performance prediction, dropout-risk identification, learning analytics, assessment, personalization, and academic decision support. While machine learning models can often identify patterns in student data, many models and their predictions remain opaque to teachers, administrators, and students. Explainable Artificial Intelligence (XAI) has therefore become an important research area that facilitates transparency, accountability, trust, and human-level understanding of educational decisions made by ML models. This paper provides a systematic review of research on XAI in higher education with a focus on student-performance prediction, as well as educational decision support. In particular, the review explores the application areas, predictive models, explanation methods, types of explanations, and challenges in applying XAI in higher education. The review highlights that SHAP, feature importance, rule-based models, decision trees, and local explanation techniques have been commonly applied for model interpretation in education. However, most of the prior work focuses on simply providing explanations rather than turning the insights into educational interventions. The review also reveals that fairness, individual-level explanations, visualization, personalization, and educational relevance of model explanations have received insufficient attention in the literature. Based on the review, this paper proposes a conceptual framework for trustworthy XAI-enabled higher education analytics that integrates educational data, modelling, explanations, fairness, domain knowledge, human-level interpretation, and interventions. This paper also identifies research gaps and discusses potential research directions in relation to human-centric explanations, domain-knowledge-aware XAI, fairness-aware prediction, multimodal educational data, and evaluation of usefulness of model explanations. The review and framework proposed in this paper provide a foundation for researchers and higher-education institutions that seek to build explanatory and trustworthy AI-driven systems for education.
Keywords	Explainable Artificial Intelligence, Higher Education; Educational Data Mining, Student Performance Prediction, Learning Analytics, Machine Learning, SHAP, Trustworthy AI, Personalized Learning.
Field	Computer Applications
Published In	Volume 8, Issue 4, July-August 2026
Published On	2026-08-23

View / Download PDF File

About IJFMR Fees & Payment Current Issue Publication Archive	Submit Research Paper Track Submission Status Publication Guidelines Publication Ethics Peer Review & Plagiarism	Join as a Reviewer Editors & Reviewers Reviewer Referral Program Get Reviewer Membership Certi.	Website/Journal Policies Usage Policy Content Policies Privacy Policy

Contact Us		+91-9687-828-838	editor@ijfmr.com

International Journal For Multidisciplinary Research

A Widely Indexed Open Access Peer Reviewed Multidisciplinary Bi-monthly Scholarly International Journal

Explainable Artificial Intelligence in Higher Education: A Systematic Literature Review of Methods, Applications, Challenges and Research Gaps

Share this