論文アブストラクト： Designing engaging learning content is important but difficult, and typically involves a lot of manual specification. We present a unified framework that utilizes automatic problem decomposition and partial ordering graph construction to facilitate multiple workflows: knowledge assessment and progression analysis and design. We present results from a study with 847 participants in an online Japanese-language assessment tool demonstrating that our framework can efficiently measure student ability and predict student performance on specific problems. We also present results from analysis of curricula showing that the progressions of two different textbooks are surprisingly similar, and that our framework can lead to the discovery of general principles of expert progression design. Finally, we demonstrate automatic progression generation with desired sequencing and pacing, allowing for tailoring of progressions and mapping of parameters extracted from one curriculum onto another.
論文アブストラクト： Practical work in optics allows supporting the construction of knowledge, in particular when the concept to be learned remains diffuse. To overcome the limitations of the current experimental setups, we have designed a hybrid system that combines physical interaction and numerical simulation. This system relies on 3D-printed replicas of optical elements, which are augmented with pedagogical information. In this paper, we focus on the well-known Michelson interferometer experiment, widely studied in undergraduate programs of Science. A 3-months user study with 101 students and 6 teachers showed that, beyond the practical aspects offered by this system, such an approach enhances the technical and scientific learning compared to a standard Michelson interferometer experiment.
論文アブストラクト： Analysis of student data is critical for improving education. In particular, educators need to understand what approaches their students are taking to solve a problem. However, identifying student strategies and discovering areas of confusion is difficult because an educator may not know what queries to ask or what patterns to look for in the data. In this paper, we present a visualization tool, PathViewer, to model the paths that students follow when solving a problem. PathViewer leverages ideas from flow diagrams and natural language processing to visualize the sequences of intermediate steps that students take. Using PathViewer, we analyzed how several students solved a Python assignment, discovering interesting and unexpected patterns. Our results suggest that PathViewer can allow educators to quickly identify areas of interest, drill down into specific areas, and identify student approaches to the problem as well as misconceptions they may have.