Programming instructors often conduct collaborative learning activities, like Peer Instruction, to foster a deeper understanding in students and enhance their engagement with learning. These activities, however, may not always yield productive outcomes due to the diversity of student mental models and their ineffective collaboration. In this work, we introduce VizGroup, an AI-assisted system that enables programming instructors to easily oversee students' real-time collaborative learning behaviors during large programming courses. VizGroup leverages Large Language Models (LLMs) to recommend event specifications for instructors so that they can simultaneously track and receive alerts about key correlation patterns between various collaboration metrics and ongoing coding tasks. We evaluated VizGroup with 12 instructors using a dataset collected from a Peer Instruction activity that was conducted in a large programming lecture. The results showed that compared to a version of VizGroup without the suggested units, VizGroup with suggested units helped instructors create additional monitoring units on previously undetected patterns on their own, covered a more diverse range of metrics, and influenced the participants' following notification creation strategies.

中文翻译：

---

VizGroup：用于实时协作编程学习分析的人工智能辅助事件驱动系统

编程教师经常开展协作学习活动，例如同伴指导，以加深学生的理解并提高他们对学习的参与度。然而，由于学生心智模式的多样性及其无效的合作，这些活动可能并不总是产生富有成效的成果。在这项工作中，我们介绍了 VizGroup，这是一种人工智能辅助系统，使编程教师能够轻松监督学生在大型编程课程中的实时协作学习行为。 VizGroup 利用大型语言模型 (LLM) 为讲师推荐活动规范，以便他们可以同时跟踪和接收有关各种协作指标和正在进行的编码任务之间的关键关联模式的警报。我们使用从大型编程讲座中进行的同伴指导活动中收集的数据集对 12 名讲师进行了评估。结果表明，与没有建议单元的 VizGroup 版本相比，具有建议单元的 VizGroup 帮助教师自行针对以前未检测到的模式创建额外的监控单元，涵盖了更多样化的指标，并影响了参与者的后续通知创建策略。