Every action we make is recorded – Witten and Frank (2011) state:
“We are overwhelmed with data. The amount of data in the world and in our lives seems ever-increasing—and there’s no end in sight. Omnipresent computers make it too easy to save things that previously we would have trashed.
Educational Data Mining (EDM) has been defined by IEDMS (2009) as:
“an emerging discipline, concerned with developing methods for exploring the unique types of data that come from educational settings, and using those methods to better understand students, and the settings which they learn in.” (see educational data mining).
EDM develops and applies methods from statistics, machine learning and data mining to analyze data collected from online learning system. The book by Witten and Frank (2011) presents a good introduction to data mining landscape. Are you interested in digging deeper into the algorithms involved in machine learn? Witten and Frank (2011) explain a wide variety of them.
What is the difference between EDM and Learning analytics?
Siemens and Baker (2012) noted (here and here) that while the EMD and LA communities share similar goals and interests, they have distinct technological, ideological, and methodological orientations. One of the differences described by Siemens and Baker (2012) is that the EMD has greater focus on automated adaption. It means that the educational software identifies a need and automatically adapts to personalize the learner’s experience. By contrast, learning analytics are more often designed to inform and empower instructors and learners, such as informing instructors about ways that specific students are struggling, and then pedagogical strategies can be applied.
So How Can Data Mining and Analytics Enhance Education?
This beautiful and very informative infographic summarizes how analytics and EDM can improve education.
Deep dives: What Educational Data Mining Can Bring to the Table?
“EDM applies data mining techniques such as prediction modeling (including classification), discovery of latent structure (such as clustering and q-matrix discovery), relationship mining (such as association rule mining and sequential pattern mining), and discovery with models to understand learning and learner individual differences and choices better” (Berland, Baker & Blikstein, 2014). Reviews of these methods have been covered by Professor Baker (here and here).
I belive that throughout the DALMOOC course this post will be updated. In a next post I’ll cover prediction modeling…
Baker, R., Siemens, G. (in press) Educational data mining and learning analytics. To appear in Sawyer, K. (Ed.) Cambridge Handbook of the Learning Sciences: 2nd Edition.(full text)
Berland, M., Baker, R.S., Blikstein, P. (2014) Educational data mining and learning analytics: Applications to constructionist research. Technology, Knowledge, and Learning, 19, 205-220.(full text)
Collegestats (november, 2014) http://collegestats.org/
IEDMS. (2009). International Educational Data Mining Society. Retrieved April 22, 2013, from http://www.educationaldatamining.org/
Siemens, G., and R. S. J. d. Baker. 2012. “Learning Analytics and Educational Data Mining: Towards Communication and Collaboration.” In Proceedings of LAK12: 2nd International Conference on Learning Analytics & Knowledge, New York, NY: Association for Computing Machinery, 252–254. (full text)
Witten,I.H., Frank, E.(2011) Data Mining: Practical Machine Learning Tools and Techniques.