Educational Data Mining versus Learning Analytics: A Review of Publications From 2015 to 2019

ABSTRACT

To examine the similarities and differences between two closely related yet distinct fields – Educational Data Mining (EDM) and Learning Analytics (LA) – this study conducted a literature review of the empirical studies published in both fields. We synthesized 492 LA and 194 EDM articles published during 2015–2019. We compared the similarities and differences in research across the two fields by examining data analysis tools, common keywords, theories, and definitions listed. We found that most studies in both fields did not clearly identify a theoretical framework. For both fields, theories of self-regulated learning are most frequently used. We found, through keyword analysis, that both fields are closely related to each other as “learning analytics” is most frequently listed keyword for EDM and vice versa for LA. However, one notable difference relates to how LA studies listed social-related keywords whereas EDM studies listed keywords related to technical methods. The tools used for data analysis overlap largely but some of the LA studies listed tools for qualitative data analysis and social network analysis whereas EDM studies did not. Finally, the distinction of the two fields is defined differently by authors as some demarcate the differences whereas some address them interchangeably.

KEYWORDS:

• Educational Data Mining
• learning analytics
• systematic review
• education
• educational technology

Disclosure statement

No potential conflict of interest was reported by the author(s).

Additional information

Notes on contributors

Clare Baek

Clare Baek: is a PhD student at the Rossier School of Education, University of Southern California.

Tenzin Doleck

Tenzin Doleck: is an Assistant Professor and Canada Research Chair (Tier II) at Simon Fraser University.