What Learning Analytics‐Based Prediction Models Tell Us About Feedback Preferences of Students

Learning analytics seeks to enhance learning processes through systematic measurements of learning-related data and to provide informative feedback to learners and educators (Siemens & Long, 2011). This study examined the use of preferred feedback modes in students by using a dispositional learning-analytics frame-work, combining learning-disposition data with data extracted from digital systems. We analyzed the use of feedback of 1,062 students taking an introductory mathematics and statistics course, enhanced with digital tools. Our findings indicated that compared with hints, fully worked-out solutions demonstrated a stronger effect on academic performance and acted as a better mediator between learning dispositions and academic performance. This study demonstrated how e-learners and their data can be effectively redeployed to provide meaningful insights to both educators and learners.