An AI Study on Learning Style Changes Among Generation C After COVID 19

The COVID-19 pandemic caused an unprecedented transformation in global education systems, forcing learners into prolonged online and hybrid learning environments. The cohort whose formative academic years coincided with this disruption—commonly referred to as Generation C (Gen C)—experienced intensified engagement with social networking platforms alongside formal learning activities. This study investigates how post-pandemic social networking styles have reshaped learning styles, attention regulation, self-directed learning, and academic performance among Gen C learners. A quantitative, data-driven research design is adopted, integrating survey-based behavioral data with learning analytics and machine-learning techniques. Social networking styles are identified using K-Means clustering, while Random Forest classification and Structural Equation Modeling (SEM) are employed to examine predictive and causal relationships between networking behavior and academic outcomes. Results indicate that instrumental academic networking positively influences engagement and deep learning, whereas passive and compulsive social networking styles significantly impair attention and promote surface learning strategies. Predictive models achieve accuracy levels exceeding 80%, demonstrating the feasibility of early academic risk detection. The study concludes that social networking has not uniformly degraded learning but has fundamentally restructured learning styles in post-COVID education. The findings provide actionable insights for educators, institutions, and policymakers seeking to design attention-aware, data-informed digital pedagogy.