一句话：提出一组变异算子，通过模拟学生错误评估自动评分配置的公平性与完整性。
自动评分在评估编程学生时，若配置不当可能产生不公平。本文提出利用变异分析来模拟学生编码错误，从而自动评估自动评分配置的公平性与完整性。作者从两门入门编程任务的真实学生解答中提取错误分类，并据此设计了一组变异算子，用于在自动评分评估技术中模拟学生可能犯的错误。该工作为检测自动评分配置缺陷、提升其公平性提供了基于变异分析的方法基础。
The use of autograding to assess programming students may lead to unfairness if an autograder is incorrectly configured. Mutation analysis offers a potential solution to this problem. By simulating student coding mistakes, an automated technique can evaluate the fairness and completeness of an autograding configuration. In this paper, we introduce a set of mutation operators to be used in such a technique, derived from a mistake classification of real student solutions for two introductory programming tasks.
@inproceedings{CleggNMF19,
title = {Simulating Student Mistakes to Evaluate the Fairness of Automated Grading},
author = {Benjamin Clegg and Siobhán North and Phil McMinn and Gordon Fraser},
booktitle = {ICSE},
year = {2019},
doi = {10.1109/icse-seet.2019.00021}
}