Profiling students via clustering in a flipped clinical skills course using learning analytics

Abstract

Flipped classrooms have become popular as a student-centered approach in medical education because they allow students to improve higher-order thinking skills and problem-solving applications during in-class activities. However, students are expected to study videos and other class materials before class begins. Learning analytics and unsupervised machine learning algorithms (clustering) can be used to examine the pre-class activities of these students to identify inadequate student preparation before the in-class stage and make appropriate interventions. Furthermore, the students’ profiles, which provide their interaction strategies towards online materials, can be used to design appropriate interventions. This study investigates student profiles in a flipped classroom. The learning management system interactions of 375 medical students are collected and preprocessed. The k-means clustering algorithms examined in this study show a two-cluster structure: ‘high interaction’ and ‘low-interaction.’ These results can be used to help identify low-engaged students and give appropriate feedback.

Keywords:

• Clustering
• flipped classrooms
• learning analytics
• clinical skills

Disclosure statement

The authors report no conflicts of interest. The authors alone are responsible for the content and writing of the article.

Additional information

Notes on contributors

Alper Bayazit

Alper Bayazit is a lecturer at the Department of Medical Education and Informatics, Ankara University, School of Medicine, Turkey. Dr. Bayazit received his B.Sc. degree in Computer Education and Instructional Technologies in 2004, M.Sc. degree in 2007 and Ph.D. degree in Educational Technology in 2013 at Hacettepe University. He developed a predictive model with machine learning algorithms for answer correctness in a problem-solving setting and the study was published in Springer book series ‘Educational Data Mining: Trends and Applications’ in 2014. His academic interest areas are educational data mining, learning analytics and human-computer interaction applications in medical education.

Hale Ilgaz

Hale Ilgaz is working as an associate professor in Faculty of Open and Distance Education at Ankara University. She has graduated from Ankara University, Computer Education and Instructional Technology Department in 2006. She has got her master’s degree in Computer Education and Instructional Technology Department at Hacettepe University in 2008 and got doctoral degree in 2013 from the same department and same university. Her main research areas are distance education, e-learning, instructional design, cognitive processes in e-learning environments, cognitive psychology, and human-computer interaction. She is the assistant editor in Educational Technology Research and Development journal, and the section co-editor of Springer Learning, Design, and Technology: An International Compendium of Theory, Research, Practice, and Policy MRW Project.

İpek Gönüllü

İpek Gönüllü is working as an assistant professor in Faculty of Medicine, Department of Medical Education and Informatics at Ankara University. She has graduated from Ankara University, Faculty of Medicine in 1989. She has got her master’s degree in Program of Medical Education at Ankara University in 2007 and got PhD degree in 2011 from the Program of Educational Psychology in Ankara University. Her main research areas are medical education and educational psychology.

Şengül Erden

Şengül Erden is working as a lecturer in Faculty of Medicine, Department of Medical Education and Informatics at Ankara University. She has graduated from Ankara University, Department of Linguistics in 2003 and Faculty of Nursing in 2011. She has got her master’s degree in Program of Life-Long Learning and Adult Education Ankara University in 2016 and got PhD degree in 2020 from the same program and same university. Her main research areas are medical education and educational psychology.