Enhanced Educational Experiences through Personalized and AI-based Learning

Abstract

Academic motivation is a pivotal factor in shaping students' educational trajectories. Mathematics education holds a unique position as a school subject, due to its influence on students' grade transitions and cognitive development at both basic and advanced levels. From March to May 2023, the AI Education (AIEDN) research project investigated how an AI-based learning assistant can enhance students’ understanding of the subject matter through video-based learning. For this study, 275 students were selected in the age range of 14-20 from two secondary (N=137) and two grammar schools (N=138) in Baden-Württemberg, Germany. The quantitative experiment tested the extent to which learners solve more tasks, build broader (transfer) knowledge, and retain it. Students were given a set of mathematical problems on an unknown topic to solve in 90 minutes. The test group used the AI assistant to ask questions, while the control group used only keyword searches. The results of the t-test indicated that the test group who used the AI Learning assistant in the advanced course achieved a significantly strong (Cohen’s d=.63) increase in performance results (T(19)=-2.82; p<.01). Conversely, the advanced course control group as well as both the test and control groups of the basic course(s) showed no significant improvements.