Assessment for Learning MOOC’s Updates
Educational Data Mining in Practice: Insights and Limitations
One piece of research that uses educational data mining (EDM) as a source of evidence is the study by Papamitsiou and Economides (2014). This study reviews various empirical research on learning analytics and EDM, highlighting how these methods can be used to improve educational outcomes1.
What EDM Can Tell Us: Educational data mining can reveal patterns in how students interact with online learning platforms. For example, it can show which topics students find most challenging, how much time they spend on different activities, and which resources they use most frequently. This information helps teachers understand where students might need more support and which teaching methods are most effective. EDM can also predict student performance, allowing for early interventions to help those at risk of falling behind.
What EDM Cannot Tell Us: Despite its strengths, EDM has limitations. It primarily focuses on quantitative data, such as clicks, time spent, and quiz scores. This means it might not capture the full picture of a student’s learning experience, such as their motivation, creativity, or critical thinking skills. Additionally, EDM relies on the quality and completeness of the data collected. If the data is incomplete or biased, the insights gained might be misleading.
In my college math classes, using EDM helps me tailor my teaching to better meet my students’ needs. For example, if I see that many students are struggling with a particular concept, I can spend more time on it in class. However, I also recognize that EDM is just one tool among many. To get a complete understanding of my students’ abilities and needs, I combine EDM with other forms of assessment, such as projects and class discussions.
References
- Papamitsiou, Z., & Economides, A. A. (2014). Learning analytics and educational data mining in practice: A systematic literature review of empirical evidence. Educational Technology & Society, 17(4), 49-64. Retrieved from https://www.jstor.org/stable/jeductechsoci.17.4.49