Search for: All records

An advantage of Large Language Models (LLMs) is their contextualization capability – providing different responses based on student inputs like solution strategy or prior discussion, to potentially better engage students than standard feedback. We present a design and evaluation of a proof-of-concept LLM application to offer students dynamic and contextualized feedback. Specifically, we augment an Online Programming Exercise bot for a college-level Cloud Computing course with ChatGPT, which offers students contextualized reflection triggers during a collaborative query optimization task in database design. We demonstrate that LLMs can be used to generate highly situated reflection triggers that incorporate details of the collaborative discussion happening in context. We discuss in depth the exploration of the design space of the triggers and their correspondence with the learning objectives as well as the impact on student learning in a pilot study with 34 students. 

Abstract Giant kelp (Macrocystis pyrifera) forests are common along the California coast. Attached on the rocky bottom at depths of approximately 5–25 m, the kelp, when mature, spans the water column and develops dense, buoyant canopies that interact with waves and currents. We present two novel results based on observations of surface gravity waves in a kelp forest in Point Loma, California. First, we report short wave (1–3 s) attenuation in kelp, quantified by an exponential decay coefficient —comparable to the dampening effect of sea ice. Second, we identify seasonal and tidal changes in attenuation, peaking mid‐summer with maximum kelp cover, and during low tide when a greater proportion of the fronds are at the surface. Thus, the naturally occurring surface canopies of kelp forests can act as temporally varying, high‐frequency filters of wave energy. 

In this study, an AR-based mobile learning application is proposed to assist online civil engineering course learning during the COVID-19 pandemic. A quasi-experiment has been conducted, and feedback from both the teacher and students has been analysed to examine the effectiveness of the proposed approach in terms of learning achievements. The subjects were 46 sophomores who majored in civil engineering in one class taught by one instructor in a southern U.S. state university. The quasi-experimental results showed that the proposed approach could not significantly improve the students’ online learning achievements. However, the feedbacks brought some explanation to this non-significant result. They indicated that students found this mobile AR app to be an interesting, helpful, practical, and effective approach in their online learning that helped them gain more in-depth knowledge than traditional teacher-centred classroom instruction.