Please use this identifier to cite or link to this item:
https://repository.isls.org/handle/1/9077| Title: | Challenges and Design Opportunities in Data Analysis for ML-Empowered Scientific Inquiry - Insights From a Teacher Professional Development Study |
| Authors: | Zhou, Xiaofei Tang, Jingwan Guo, Beilei Lyu, Hanjia Bai, Zhen |
| Keywords: | Learning Sciences |
| Issue Date: | 2022 |
| Publisher: | International Society of the Learning Sciences |
| Citation: | Zhou, X., Tang, J., Guo, B., Lyu, H., & Bai, Z. (2022). Challenges and design opportunities in data analysis for ML-empowered scientific inquiry - insights from a teacher professional development study. In Chinn, C., Tan, E., Chan, C., & Kali, Y. (Eds.), Proceedings of the 16th International Conference of the Learning Sciences - ICLS 2022 (pp. 847-854). International Society of the Learning Sciences. |
| Abstract: | The increasing impact of machine learning (ML) on real-world scientific investigations demands a shift to teaching ML-empowered scientific inquiry to familiarize younger students with authentic science practices. Evidence from previous studies has suggested that glyph-based data visualization is promising for making multidimensional data analysis accessible for novice learners. Little research, however, has examined the contextualized challenges of applying glyphs in K-12 ML-empowered scientific inquiry. Since teachers play a critical role at the frontier of technology integration for learning, as an initial attempt to address this research gap, we investigated the pattern recognition and interpretation behaviors of 18 K-12 STEM teachers when engaged in ML-empowered scientific inquiry during a professional development workshop. Findings confirm that teachers identified and interpreted ML-revealed patterns for scientific hypothesis formulation while it is challenging for novices to analyze and synthesize different patterns conceptually and extensively for more sophisticated inference. Underlying design opportunities and implications are discussed. |
| Description: | Long Paper |
| URI: | https://dx.doi.org/10.22318/icls2022.847 https://repository.isls.org//handle/1/9077 |
| Appears in Collections: | ISLS Annual Meeting 2022 |
Files in This Item:
| File | Size | Format | |
|---|---|---|---|
| ICLS2022_847-854.pdf | 1.06 MB | Adobe PDF | View/Open |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.