ISECA: A Comprehensive Framework for Enhancing Engagement and Assessment Utilizing SVM and GBDT

As the focus on online formats increases, evaluating engagement and the effectiveness of content delivery has become essential. To address this challenge, this study proposes an integrated machine learning framework named ISECA. ISECA leverages Support Vector Machine (SVM) and Gradient Boosting Decision Tree (GBDT) models to analyze and evaluate feedback data, providing precise content effectiveness evaluation strategies. Experiments were conducted using feedback data from 743 participants. The results demonstrate that the ISECA framework achieved an accuracy of 93%, significantly outperforming the standalone SVM or GBDT models. The AUC value for the ISECA framework's prediction accuracy is 0.97, showcasing its robustness in handling missing values and outliers. This study's in-depth analysis of the ISECA framework not only enhances the accuracy of evaluating engagement and content effectiveness but also offers reliable decision support.