Please use this identifier to cite or link to this item: https://repository.isls.org/handle/1/10074
Title: Identifying Pre-Service Teachers’ Cognitive Engagement Patterns Using Time Series Clustering in a Programming Activity
Authors: Jin, Hao-Yue
Song, Yajie
Pan, Zexuan
Cutumisu, Maria
Keywords: Learning Sciences
Issue Date: 2023
Publisher: International Society of the Learning Sciences
Citation: Jin, H., Song, Y., Pan, Z., & Cutumisu, M. (2023). Identifying pre-service teachers’ cognitive engagement patterns using time series clustering in a programming activity. In Blikstein, P., Van Aalst, J., Kizito, R., & Brennan, K. (Eds.), Proceedings of the 17th International Conference of the Learning Sciences - ICLS 2023 (pp. 1893-1894). International Society of the Learning Sciences.
Abstract: Learners’ cognitive engagement has been identified as a key factor affecting learning outcomes. However, limited research has focused on how dynamic cognitive engagement patterns influence learning outcomes. In this study, ninety-three pre-service teachers participated in an online computational thinking (CT) activity. Four patterns were identified using time series clustering: (1) low-engagement; (2) high-engagement; (3) early-engagement; and (4) late-engagement. The findings revealed that high- and late-engagement learners displayed significantly higher CT skills than low-engagement learners.
Description: Poster
URI: https://doi.org/10.22318/icls2023.844281
https://repository.isls.org//handle/1/10074
Appears in Collections:ISLS Annual Meeting 2023

Files in This Item:
File SizeFormat 
ICLS2023_1893-1894.pdf88.55 kBAdobe PDFView/Open


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.