Learning Analytics in STEM Higher Education: Trends, Challenges, and Future Directions

• In Event: Computer Science Education and Computational Thinking

Abstract

The development of science, technology, engineering, and mathematics (STEM) education has grown in importance over the past two decades. This scoping review investigates the application of learning analytics (LA) in STEM disciplines in higher education, focusing on participants’ characteristics, methodological features, and LA application attributes. Our results indicate: (1) LA are used to predict student performance and model student behavior; (2) most studies employ quantitative methods, though mixed-methods approaches are recommended for deeper insights; (3) the presentation of LA data to end-users is underutilized for improved design and implementation. We provide strategies for researchers to enhance the rigor of LA studies and recommend best practices for integrating LA into STEM education.

Authors

• Zhihong Xu, Texas A&M University

• Shuai Ma, Texas A&M University

• Wenting Weng, Johns Hopkins University

• Xuan Zhou, Texas State University

• Ashlynn Kogut, Texas A&M University

• Yeping Li, Texas A&M University