(School of Computer Science and Technology Donghua University, Shanghai, 201620, China)
Abstract：Nowadays, more and more colleges tend to organize online programming examination, which is benefit to improve student’s practice skills. However, this may bring a problem, as the programming source code is easy to copy, some students may cheat in the examination. The traditional manual method of cheating detection has some disadvantages, such as time-consuming and inaccuracy. To address this issue, an efficient and accurate method based on the Self-organizing maps (SOM) and tree structure similarity is proposed in this paper. We use abstract syntax trees to represent source codes. By SOM, all source codes are divided into several classes, and the source codes in each class are similar. And then we can detect cheating source codes in each class by using tree structure similarity.
Key words：Self-organizing maps; Programming source code; Cheating; Abstract syntax tree, Similarity
References
[1]. N. Selwyn, "‘Not necessarily a bad thing …’: a study of online plagiarism amongst undergraduate students," Assessment & Evaluation in Higher Education, vol. 33, pp. 465-479, 2008/10/01 2008.
[2]. Z. Guojin and Z. Xingyin, "The Growing Self-organizing Map for Clustering Algorithms in Programming Codes," in Artificial Intelligence and Computational Intelligence (AICI), 2010 International Conference on, 2010, pp. 178-182.
[3]. T. Kohonen, "The self-organizing map," Proceedings of the IEEE, vol. 78, pp. 1464-1480, 1990.
[4]. J. Jones, "Abstract Syntax Tree Implementation Idioms," in Proceedings of the 10th Conference on Pattern Languages of Programs (PLoP2003), 2003.
[5]. P. Bille, "A survey on tree edit distance and related problems," Theor. Comput. Sci., vol. 337, pp. 217-239, 2005.
[6]. K. Zhang and D. Shasha, "Simple Fast Algorithms for the Editing Distance between Trees and Related Problems," SIAM Journal on Computing, vol. 18, pp. 1245-1262, 1989.
[7]. Http://en.wikipedia.org/wiki/Moore_neighborhood
Guojin Zhu is an associate professor at the Department of Computer Science, Donghua University (DHU), Shanghai, China. He received his M.S. and Ph.D. degrees from DHU in 1991 and 2007, respectively. He was a visiting scholar at the Department of Computer Science and Engineering, Michigan State University, East Lansing, Michigan, USA from November 2007 to November 2008. His current research interests include semantic web, knowledge discovery, and neural computing.
Le Liu is a graduate student of Computer Application Technology at Donghua University (DHU). He was born in Hunan province, P. R. China in 1987, and received the bachelor degree of computer science and technology in Hunan Institute of Humanities Science and Technology in 2010. His current main research interest is computer network and AI.
Contact: Le Liu Address: Donghua University, Songjiang District, Shanghai Wenhui Road, No. 300, Building 4
