Context-Aware Analysis of Group Submissions for Group Anomaly Detection and Performance Prediction

Learning exercises that activate students’ additional cognitive understanding of course concepts facilitate contextualizing the content knowledge and developing higher-order thinking problem-solving skills. Student-generated instructional materials such as summaries problem sets are amongst strategies reflect active learning constructivist philosophy. The contributions this work twofold: 1) We introduce a practical implementation inside-outside strategy in an undergraduate deep will share our experiences incorporating student-generated design, 2) develop context-aware framework to draw insights from for (i) Detecting anomalies group activities (ii) Predicting median quiz performance students each group. This opens up avenue effectively implementing constructivism large-scale online courses build sense community between learners while providing automated tool instructors identify at-risk groups.