Ultra-Lightweight Early Prediction of At-Risk Students in CS1

Ultra-Lightweight Early Prediction of At-Risk Students in CS1
复制标题

CS1 中高危学生的超轻量级早期预测

DOI:
10.1145/3545945.3569764
复制
发表时间:
2023
期刊:
SIGCSE 2023: Proceedings of the 54th ACM Technical Symposium on Computer Science Education
影响因子:
--
通讯作者:
Vahid, Frank
Vahid, Frank
中科院分区:
--
文献类型:
--
作者:
Gordon, Chelsea;Zhao, Stanley;Vahid, Frank

文献摘要

参考文献

被引文献

相似文献

早期预测学生在CS 1中表现不佳的风险可以使早期干预或班级调整成为可能。最好是,预测方法应该是轻量级的,不需要教师进行太多额外的活动或数据收集工作。以前的方法包括进行调查,收集(可能敏感的)人口统计数据,在讲座中引入点击器问题,或者使用本地开发的分析编程行为的系统,每一种方法都需要教师付出一定的努力。今天,在CS 1课堂上广泛使用的教科书/学习系统是zyBooks,每年有数十万学生使用。系统自动收集与阅读、家庭作业和编程作业相关的数据。对于300多名学生的CS 1课程,我们发现该系统在最初几周(1-4)自动收集的三个数据指标能够很好地预测第6周期中考试的表现:不认真完成指定的阅读,编码作业的挣扎以及编程作业的低分数,相关性分别为0.44,0.58和0.72。我们将这些指标结合到决策树模型中,预测期中考试不及格的学生(<70%,意味着D或F),并实现了85%的预测准确率,82%的灵敏度和89%的特异性,这高于以前发表的早期预测方法。这种方法可能意味着成千上万的教师已经使用zyBooks(或类似的系统)可以获得更准确的风险学生的早期预测,而不需要额外的努力或活动,并避免收集敏感的人口统计数据。
Early prediction of students at risk of doing poorly in CS1 can enable early interventions or class adjustments. Preferably, prediction methods would be lightweight, not requiring much extra activity or data-collection work from instructors beyond what they already do. Previous methods included giving surveys, collecting (potentially sensitive) demographic data, introducing clicker questions into lectures, or using locally-developed systems that analyze programming behavior, each requiring some effort by instructors. Today, a widely used textbook / learning system in CS1 classes is zyBooks, used by several hundred thousand students annually. The system automatically collects data related to reading, homework, and programming assignments. For a 300+ student CS1 class, we found that three data metrics, auto-collected by that system in early weeks (1-4), were good at predicting performance on the week-6 midterm exam: non-earnest completion of the assigned readings, struggle on the coding homework, and low scores on the programming assignments, with correlation magnitudes of 0.44, 0.58, and 0.72, respectively. We combined those metrics in a decision tree model to predict students at-risk of failing the midterm exam (<70%, meaning D or F), and achieved 85% prediction accuracy with 82% sensitivity and 89% specificity, which is higher than previously-published early-prediction approaches. The approach may mean that thousands of instructors already using zyBooks (or a similar system) can get a more accurate early prediction of at-risk students, without requiring extra effort or activities, and avoiding collection of sensitive demographic data.
步入正轨,保持正轨:在 CS1 研讨会中结合早期干预和学习技能
DOI: --
发表时间: 2017
期刊: Western Canadian Conference on Computing Education
影响因子: --
作者:
Brian Harrington
通讯作者: Brian Harrington
计算机编程能力的某些组成部分的识别。
DOI: --
发表时间: 1972
期刊:
影响因子: --
作者:
Carol Ann Alspaugh
通讯作者: Carol Ann Alspaugh
有助于计算机科学入门课程的成功:十二个因素的研究
DOI: --
发表时间: 2001
期刊: Technical Symposium on Computer Science Education
影响因子: --
作者:
B. Wilson;S. Shrock
通讯作者: S. Shrock
PrairieLearn:通过机器学习驱动的自适应评分和建议来解决基于掌握的在线问题
DOI: --
发表时间: 2015
期刊:
影响因子: --
作者:
Matthew West;Geoffrey L. Herman;C. Zilles
通讯作者: C. Zilles
CS1 中表现较高和较低的学生的行为
DOI: 10.1145/3304221.3319740
发表时间: 2019
期刊: 2019 ACM Conference on Innovation and Technology in Computer Science Education
影响因子: --
作者:
Liao, Soohyun Nam;Valstar, Sander;Thai, Kevin;Alvarado, Christine;Zingaro, Daniel;Griswold, William G.;Porter, Leo
通讯作者: Porter, Leo