arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2205.08520cs.CLcs.AI
收藏

程序设计导论课程中剽窃行为的度量

Measuring Plagiarism in Introductory Programming Course Assignments

Higher Colleges of Technology(高等技术学院);Faculty of Computer Information Science(计算机信息科学学院);The University of Central Punjab(中旁遮普大学)

Muhammad Humayoun, Muhammad Adnan Hashmi, Ali Hanzala Khan

摘要:

衡量编程作业中的剽窃行为是教育过程中的一项重要任务。本文讨论了在用C++编写的程序设计入门课程作业中剽窃及其检测的方法。一个小的语料库的作业是免费提供的。一个通用的框架来计算解决方案对之间的相似性,使用三个基于令牌的相似性方法作为特征,并预测解决方案是否是抄袭的。每个特征的重要性也被衡量,这反过来又对使用中的每个方法的有效性进行排名。最后,人工生成的数据集与原始数据相比改进了结果。我们在原始数据集和合成数据集上的F1得分分别为0.955和0.971。

英文摘要:

Measuring plagiarism in programming assignments is an essential task to the educational procedure. This paper discusses the methods of plagiarism and its detection in introductory programming course assignments written in C++. A small corpus of assignments is made publically available. A general framework to compute the similarity between a solution pair is developed that uses the three token-based similarity methods as features and predicts if the solution is plagiarized. The importance of each feature is also measured, which in return ranks the effectiveness of each method in use. Finally, the artificially generated dataset improves the results compared to the original data. We achieved an F1 score of 0.955 and 0.971 on original and synthetic datasets.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑