Search for: All records

This work-in-progress paper presents a joint effort by engineering education and machine learning researchers to develop automated methods for analyzing student responses to challenging conceptual questions in mechanics. These open-ended questions, which emphasize understanding of physical principles rather than calculations, are widely used in large STEM classes to support active learning strategies that have been shown to improve student outcomes. Despite their benefits, written justifications are not commonly used, largely because evaluating them is time-consuming for both instructors and researchers. This study explores the potential of large pre-trained generative sequence-to-sequence language models to streamline the analysis and coding of these student responses. 

Abstract BackgroundIn taking up educational technology tools and student‐centered instructional practice, there is consensus that instructors consider the unique aspects of their instructional context. However, tool adoption success is often framed narrowly by numerical uptake rates or by conformity with non‐negotiable components. PurposeWe pursue an alternative ecosystems framing which posits that variability among contexts is fundamental to understanding instructors' uptake of instructional tools and the ways their teaching trajectories develop over time. Design/MethodThrough a multiple‐case study approach using interviews, usage data, surveys, and records of community meetings, we examine 12 instructors' trajectories to illustrate the dynamic uptake of a technology tool. ResultsCross‐case analysis found that instructors' trajectories are tool‐mediated and community‐mediated. We present five cases in detail. Two foreground ways that instructors gained insight into student learning from student responses in the tool. Two illustrate the role played by the project's Community of Practice (CoP), an extra‐institutional support for deepening practice. The final case illustrates the complexity of an evolving instructional ecosystem and its role in instructors' satisfaction and continued use. ConclusionsUse of the educational technology tool perturbed ecosystems and supported instructors' evolving trajectories through mediation of instructor and student activity. Instructors' goals guided initial uptake, but both goals and practice were adapted using information from interactions with the tool and the CoP and changes in instructional contexts. The study confirms the need to understand the complexity of the uptake of innovations and illustrates opportunities for educators, developers, and administrators to enhance uptake and support diversity goals.