Introduction: Student retention is a critical issue in higher education. Universities have responded by implementing supports like early alert systems. Objective: We investigated students’ knowledge of and experiences with an early alert system designed to enhance academic persistence. Method: We surveyed (N = 356) undergraduates at a large public university in the U.S. The survey was researcher-created and administered online. Participants self-selected into the study and provided informed consent prior to beginning the study. Data were coded by experts, who achieved excellent IRR. The analyses were frequency-based to understand diverse student knowledge, experiences, and responses with early alert systems. Results: Students commonly reported experiencing negative emotions after receiving an alert, but also reported that receiving an alert motivated them to increase their course attendance, improve their study habits, and participate more in class. Finally, students indicated that receiving an early alert facilitated supportive interactions with instructors, though student communication with academic advisors was less frequent. Student recommendations for system improvement included using positive language in alerts and providing actionable guidance. Conclusions: These results provide new insight into student views of early alert systems and suggest that these systems can positively impact students in need of support.

This study investigates the application of knowledge tracing to the domain of reading comprehension, a complex field characterized by rich contextual data and interrelated concepts. We propose adapting the Dynamic Key-Value Memory Networks (DKVMN) model to incorporate sentence embeddings to better capture the semantic richness of reading tasks, naming our new model Context-embedded DKVMN (CDKVMN). The study employs an extant dataset of 405 students that each completed the reading game "Map Conquest." This game was designed to evaluate students' mastery and use of key reading strategies, such as paraphrasing and bridging. Our findings indicate that CDKVMN outperforms Deep Knowledge Tracing and performs similarly or better than DKVMN in predicting students' performance. This research underscores the potential of advanced, context-sensitive knowledge tracing models to track students' mastery of reading strategies, which can be used to provide support and adapt learning activities to the user. Future work will focus on refining the contextual embeddings, expanding the dataset to a variety of reading games, and interpreting the detected latent concepts.