 Enhancing mathematical modeling competencies through AI-powered VRNejla Gürefe, Hava Öksüz and Gülfem Sarpkaya Aktaş PLOS ONE, 2025, vol. 20, issue 12, 1-28 Abstract: Background: Improving students’ problem-solving skills is one of the primary objectives of mathematics education. Problem-solving skills are closely related to the mathematical modeling process and the competencies required in this process, which are essential in various aspects of daily life. Method: The study was designed as a mixed design. A quasi-experimental design to examine the impact of an instructional model based on an artificial intelligence-supported virtual reality (VR) application on students’ modeling competencies for quantitative data and opinion and observation forms were used for qualitative data. These competencies included inductive, deductive, pragmatic, planned, and problem-solving thinking. The study involved 30 students from two 6th-grade classes at a Science and Art Center located in the western part of Turkey. One class served as the experimental group (f = 15) and engaged with the AI-pVR approach, while the other class served as the control group (f = 15) and followed the traditional teaching model. In the study, independent samples t-tests and ANCOVA were performed for quantitative analysis, and to check ANCOVA assumptions, normality, homogeneity of variances, linearity, and homogeneity of regression slopes were examined. Descriptive analysis was also performed for qualitative analysis. Results: The findings of this study revealed that the intervention had a significant large effect (η² = 0.37) on students’ mathematical modeling competencies. Among the components of modeling competence, understanding and simplifying the problem, mathematizing, working mathematically, interpreting, and verifying all exhibited significant large effects (η² = 0.33, 0.19, 0.32, 0.39, respectively), while defining the problem showed a moderate effect (η² = 0.15). The variability observed in some measurements may be attributed to limitations in the number of practice trials and the small sample size. However, the educational process carried out within the scope of this study has shown that students have made significant progress in their mathematical modeling skills. Students have stated that they have meaningfully grasped the basic steps of the modeling process, such as analyzing real-life problems, relating these problems to mathematical structures, creating models, solving the model they have created step by step, interpreting and verifying the results. In addition, students have developed a significant awareness in sharing their models with their friends and teachers, receiving meaningful feedback, developing new models for different life situations, and establishing connections between real life and mathematics. Conclusion: The results indicated that the integration of the AI-pVR instructional approach significantly improved students’ modeling competencies and related sub-dimensions. These sub-dimensions were problem understanding and simplification, mathematizing, working mathematically, interpreting, and verifying. Based on these findings, it is recommended that artificial intelligence applications, which can positively influence various areas such as competencies, should be incorporated into teachers’ lessons and even included in curriculum programs. Date: 2025 Downloads: (external link) Related works: Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text Persistent link: https://EconPapers.repec.org/RePEc:plo:pone00:0326440 DOI: 10.1371/journal.pone.0326440 Access Statistics for this article More articles in PLOS ONE from Public Library of Science |
Is your work missing from RePEc? Here is how to contribute.
Questions or problems? Check the EconPapers FAQ or send mail to .
EconPapers is hosted by the
School of Business at Örebro University.