Adaptive Smart Online Learning System Design (ASOLS)

The COVID-19 pandemic accelerated the global shift toward online learning, proving its necessity in ensuring uninterrupted education. Post-pandemic studies reveal a notable increase in student performance, highlighting the potential of digital platforms. Adaptive learning systems have emerged as a key driver of this progress by tailoring content to individual learner preferences. These systems can leverage established models such as the VAK (Visual, Auditory, Kinesthetic), Felder-Silverman, and David Kolb models to assess learner preferences and behaviours. The VAK model identifies whether students learn best through visual, auditory, or Kinesthetic means, enabling platforms to recommend multimedia content, interactive exercises, or hands-on simulations accordingly. The Felder-Silverman model expands this through dimensions like active/reflective or sensing/intuitive learning, while Kolb's experiential learning cycle focuses on concrete experience versus abstract conceptualization. By integrating these models, adaptive systems can efficiently recommend or adjust course material to fit individual learning styles, thereby maximizing engagement, retention, and outcomes for a diverse global learner population that increasingly prefers—and depends on online education.