Educational Data Mining (EDM) is a newly emerging inter-disciplinary research field which conducts research on education-oriented analytics, machine learning, knowledge discovery, and data mining to analyze educational systems, problems and data, including academic systems, educational administration and management, performance and quality auditing and evaluation, learning analytics, ranking and reputation, student satisfaction, alumni feedback, interactive learning systems, intelligent tutoring systems, and institutional administration data. The primary goals of EDM is to uncover scientific evidence, indications and knowledge to understand, improve, optimize educational objectives, performance, customer relationships, student positive experience, and strategic developments.
The research topics include but are not limited to the following areas:
- Pedagogical evaluation and innovation: evaluating shortcomings in pedagogical systems, methods, processes, syllabus, predicting opportunities to improve and optimize, etc.;
- Student learning performance analysis: analyzing students’ learning performance, detecting at-risk students, attrition, suspension, and disengaging behaviors, etc.;
- Performance and quality evaluation: evaluating students, staff, and institutional performance and quality, recommending areas, strategies and actions to improve and optimize performance and quality;
- Personalized teaching and learning: understanding student and subject-specific characteristics and circumstances, recommending individualized syllabus and pedagogical methods;
- Pathway and progression optimization: analyzing relations between learning performance and pathways, course progression, optimizing matching between pathways and syllabus, etc.;
- Course recommendation and planning: customizing the matching between a student’s circumstance and suitable courses, planning a set of courses and progression paths;
- Admission planning: estimating, evaluating and optimizing HSC cut-off scores for subjects, campaign planning and activities for admission;
- Mental and psychological health analysis: modeling student and staff mental health, sentiment, psychological health, depression, etc.;
- Career planning: analyzing personal career plan, performance, skillset, foundation, recommending career paths, training and development areas and strategies, etc.;
- Staff evaluation: evaluating appropriate staff workload, leave arrangement, resource planning, promotion planning, and career development;
- Ranking and reputation: building evaluation systems and measures, ranking methods, and reputation indexation to classify and categorize a subject area, a discipline and an institution;
- Misconduct analysis: detecting and predicting misconducts (including cheating, plagiarism, sexual harassment, racism) of students, faculty members and staff at different levels;
- Corporate asset assessment: evaluating and optimizing the value, allocation, utility of intangible and tangible corporate assets;
- Marketing and communication evaluation: evaluating and optimizing the strategies, campaign activities, resources, and planning of educational marketing and communication both internally and externally;
Since 2005, we’ve led the investigation of multiple projects sponsored by our university and the Australia’s National Office for Learning and Teaching (OLT), Department of Industry, Innovation, Science, Research, Climate Change and Tertiary Education. We delivered working systems and reports for university admission centre, academic management team, student centre, and senior executives for university’s teaching and learning decision-support.
Please also refer to the Educational Data Mining website for more information about the relevant activities, projects, and research.