An Investigation of High School Students’ Errors in Introductory Programming: A Data-Driven Approach

Abstract

This study implemented a data-driven approach to identify Chinese high school students’ common errors in a Java-based introductory programming course using the data in an automated assessment tool called the Mulberry. Students’ error-related behaviors were also analyzed, and their relationships to success in introductory programming were investigated. This study identified 15 common compilation errors and 6 common test errors. The results showed that these common errors accounted for a large proportion of all errors, so identifying the common errors is important to help students succeed in introductory programming courses. Based on these common errors, five underlying student difficulties were identified and are discussed. In addition, after analyzing existing measures of students’ error-related behaviors, we developed a measure called improvement rate to quantify students’ success in fixing errors. The results of our study suggest that students’ competence of improving code is important to their success in introductory programming. We recommend researchers design and develop automated assessment tools that provide feedback messages for common student errors and instructors who explicitly teach knowledge and skills of improving code in class.