ArAl: An Online Tool for Source Code Snapshot Metadata Analysis
- Publication Type:
- Conference Proceeding
- ACM International Conference Proceeding Series, 2019, pp. 118 - 125
- Issue Date:
Files in This Item:
|2019_01_ACE_AhadiListerAndMathieson2019ArAl_anOnlineToolForSourceCodeSnapshotMetadataAnalysis_AcceptedManuscriptWithoutPublishersStuff.pdf||Accepted Manuscript version||170.72 kB|
Copyright Clearance Process
- Recently Added
- In Progress
- Open Access
This item is open access.
© 2019 Association for Computing Machinery. Several systems that collect data from students' problem solving processes exist. Within computing education research, such data has been used for multiple purposes, ranging from assessing students' problem solving strategies to detecting struggling students. To date, however, the majority of the analysis has been conducted by individual researchers or research groups using case by case methodologies. Our belief is that with increasing possibilities for data collection from students' learning process, researchers and instructors will benefit from ready-made analysis tools. In this study, we present ArAl, an online machine learning based platform for analyzing programming source code snapshot data. The benefit of ArAl is two-fold. The computing education researcher can use ArAl to analyze the source code snapshot data collected from their own institute. Also, the website provides a collection of well-documented machine learning and statistics based tools to investigate possible correlation between different variables. The presented web-portal is available at online-analysisdemo. herokuapp.com. This tool could be applied in many different subject areas given appropriate performance data.
Please use this identifier to cite or link to this item: