AI-Driven Recommendations for Digital Majors Based on Learning Styles

In response to industry demands, universities offer diverse digital technology majors, some focusing purely on technology while others integrate with domains like arts, business, or science. These interdisciplinary programs aim to equip students with the skills necessary to thrive in a digitally driven world. However, matching students with the right major can be challenging, especially given the diverse learning preferences among students. The VARK framework categorizes students into visual, aural, reading/writing, and kinesthetic learners, while the Kolb model classifies learners based on their experiences as diverger, assimilators, converger, or accommodators. These frameworks offer insights into how students prefer to acquire and retain information. The resulting predictive models will recommend the most suitable majors for students based on their learning styles. These recommendations will consider the compatibility between students' preferred learning methods with digital major. Moreover, leveraging machine learning models can predict students' suitability for digital majors based on learning styles. Analyzing student profiles and outcomes facilitates informed decisions, benefiting both students and universities in shaping educational pathways and career trajectories. Through the application of Support Vector Classifier, this study seeks to provide personalized academic guidance to students, helping them make informed decisions about their educational pathways. By considering students' individual learning styles, universities can enhance the effectiveness of their digital maj or offerings, ultimately addressing the shortage of skilled digital professionals in the workforce. The study findings showcase the proposed approach as highly promising, achieving outstanding classification accuracy. Specifically, the Area Under the Curve (AUC) accuracy values are notable: Animation and Visual Effects with an AUC of 0.89, Business Computer with an AUC of 0.97, and Computer Engineering with an AUC of 0.96.