A psychological network analysis to specify predictions of fraction subtopics on algebra subtopics in an intelligent tutoring system

Abstract

Many students face difficulties with algebra. It has been observed that fraction understanding predicts algebra achievements; hence, gaining a better understanding of how algebra understanding builds on fraction understanding is an important goal for research and educational practice. However, a wide range of algebra and fraction subtopics exists, and little is known about which specific fraction subtopics matter most for (i.e., best predict) which specific algebra subtopics. Here, we capitalized on a large data set (3,158 students; 257,321 problem sets) from an intelligent tutoring system (ITS) and employed state-of-the-art psychological network analysis. Using psychological network analysis allowed us to visualize and quantify interdependencies between students’ performance on different fraction and algebra subtopics. We observed relatively high partial correlations between algebra subtopics and between fraction subtopics, respectively. We also found that two fraction subtopics significantly predicted four algebra subtopics. Overall, our study generates differentiated insights into interdependencies in mathematics learning and highlights the potential of psychological network analysis for analyzing learning data from ITSs.