Abstract:

Adaptive Learning, as highlighted by Moskal et al. (2017), respects students' prior knowledge, addresses their learning needs, and helps reduce understanding gaps. Rincon-Flores et al. (2024) describe Adaptive Learning as an educational strategy that leverages data analytics technology to create personalized learning paths tailored to each student's performance level, profile, and needs. This strategy allows instructors to identify knowledge gaps, implement improvement actions, and refine their teaching practices, thus optimizing student performance.

The proposed Adaptive Learning model incorporates various educational strategies such as flipped classrooms, microlearning, and self-regulation, which, when integrated effectively, lead to superior academic outcomes. This Adaptive Learning Strategy supports course content mastery and student leveling, particularly for first-time students, by interweaving prior knowledge content with new course material. This approach enables students to refresh forgotten knowledge while focusing class time on current topics. The adaptive platform, powered by an artificial intelligence engine, facilitates pre-reading (inverted classroom) and personalizes effective learning paths, preparing students for class. Consequently, teachers can address specific questions, conduct practice sessions, and delve deeper into subjects.

This study aimed to measure the impact on student learning and leveling, as well as the didactic experiences of professors and students. A total of 521 students and 21 professors from various parts of Mexico participated, facilitated by the university's multicampus system. The research focused on the School of Engineering and the Fundamental Mathematical Modeling course. A mixed-methods approach was used, combining quantitative and qualitative methods, with a quasi-experimental design that included both a control group and an experimental (adaptive) group. Quantitative data were collected using three instruments: two pre-posttests (one for leveling and one for course knowledge) and a third test measuring the didactic experience. Qualitative data were gathered through open-ended questionnaires for both students and teachers.

Results indicated that students in the experimental group outperformed their counterparts in the post-tests for prior knowledge and course knowledge, showing statistically significant learning gains. Both students and teachers reported positive learning experiences. The research validated that a well-designed Adaptive Learning Strategy model enhances students' prior knowledge and course-specific knowledge, as demonstrated in the mathematics course. Future research will extend this model to other disciplines.

References:
[1] Moskal, P., Carter, D., & Johnson, D. (2017). Things you should know about adaptive learning. Educause Learning Initiative, 2. EDUCAUSE Learning Initiative (ELI), retrieved from: https://library.educause.edu/resources/2017/1/7-things-you-should-know-about-adaptive-learning.
[2] Rincon-Flores, E.G., Castano, L., Guerrero Solis, S.L. et al. Improving the learning-teaching process through adaptive learning strategy. Smart Learn. Environ. 11, 27 (2024). https://doi.org/10.1186/s40561-024-00314-9

Keywords:

Adaptive learning, Educational Innovation, Leveling, Higher education.