The State of Educational Data Mining in 2009: A Review and Future Visions
Состояние интеллектуального анализа образовательных данных в 2009 году: обзор и перспективы развития
2009-10-01
SCID: 54.1/4vzk9hn9
Discuss with AI
Educational Data Miningdiscovery with modelspredictionrelationship miningresearch trends
Figures from the paper
Abstract (AI)
We review the history and current trends in the field of Educational Data Mining (EDM). We consider the methodological profile of research in the early years of EDM, compared to in 2008 and 2009, and discuss trends and shifts in the research conducted by this community. In particular, we discuss the increased emphasis on prediction, the emergence of work using existing models to make scientific discoveries ("discovery with models"), and the reduction in the frequency of relationship mining within the EDM community. We discuss two ways that researchers have attempted to categorize the diversity of research in educational data mining research, and review the types of research problems that these methods have been used to address. The most cited papers in EDM between 1995 and 2005 are listed, and their influence on the EDM community (and beyond the EDM community) is discussed.
Key Findings
1
It categorizes the diversity of EDM research, examines the problems addressed by different methods, and discusses influential papers published between 1995 and 2005.
2
Relationship mining became less frequent within the Educational Data Mining community in 2008 and 2009.
3
The review compares methodological profiles across EDM’s early years, 2008, and 2009, highlighting changes in research emphasis.
4
The review identifies a shift in Educational Data Mining toward predictive research during 2008 and 2009.
5
Using existing models to make scientific discoveries, termed “discovery with models,” emerged as an important EDM research direction.
Research Object
Educational Data Mining (EDM) research and its research community
Research Subject
The historical development, methodological trends, research-problem categories, and influential publications of EDM, including shifts toward prediction and discovery with models and reduced relationship mining
Publication Details
Publication Date
2009-10-01
Journal
Publisher
ISSN
Open access PDF
Access Type
Author Information
Download PDF
Subscribe to digest