Ontology-Based Dataset for Student and Course Performance Monitoring, Data Retrieval, and Decision-Making

This dataset was developed to support the study of “Adaptive Ontology-Enabled Data Retrieval Model for Learning Analytics Integration Across Heterogeneous Educational Platforms.” The dataset addresses the challenge of integrating heterogeneous educational data sources, including Learning Management Systems (LMS) and Student Information Systems (SIS), into a unified framework for learning analytics applications. The research hypothesizes that an ontology-driven, graph-based model can more effectively integrate diverse data and enable accurate, flexible retrieval compared to traditional relational database approaches by preserving semantic relationships and supporting interoperable cross-platform querying. The dataset is organized into eight sheets: SECI_1 – enrolment records linking students, lecturers, faculties, and programmes. SECI_2 – course metadata, credit hours, and prerequisite structures. CPI_1 – grade distributions across semester, cohorts, groups, and lecturers. SAI_1 – detailed individual assessment scores, totals, and grades. SAI_2 – monthly student attendance by course and semester, and the lecturer responsible for teaching the group. SAI_3 – lecture engagement indicators measured through discussion posts. These sheets capture performance and engagement across conventional courses and classroom/lecturer activities. The ontology-based retrieval model successfully harmonized heterogeneous data without schema conflicts. A laboratory experimental session involving four domain experts was conducted to verify the retrieval results. The confusion matrix evaluation achieved above 99.8% accuracy and above 99.7% precision across both participating institutions (Institution A and Institution B). Only a small number of false positives and false negatives were recorded. How the Data Can Be Interpreted Records represent validated student and course performance data that can be interpreted across three themes: (1) managing resource allocation, including course groups, lecturer assignments, and prerequisite structures; (2) monitoring course performance through grade distributions and pass/fail analysis; and (3) monitoring student performance, attendance, and online engagement activities. Ontology cross-linking enables flexible semantic queries, such as “What is the total number of students who passed a course?” or “What was the student attendance for the previous month?” The dataset demonstrates the value of ontology-based integration for scalable, accurate, and flexible learning analytics across heterogeneous educational platforms.