A quantitative comparison of program plagiarism detection tools

Daniël Heres; Jurriaan Hage

doi:10.1145/3162087.3162101

A quantitative comparison of program plagiarism detection tools

Daniël Heres, Jurriaan Hage

Utrecht University

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

In this work we compare a total of 9 different tools for the detection of source code plagiarism. We evaluated the plagiarism or copy detection tools CPD, JPlag, Sherlock, Marble, Moss, Plaggie and SIM and two baselines, one based on the Unix tool diff and one based on the difflib module from the Python Standard Library. We provide visualizations of the output of these tools and compare the performance of each tool when running it on different tasks by comparing both the F-measures and the area under the precision-recall-curve (AUC-PR). We compare the performance using these metrics on each task and identify the best performing tools.

Original language	English
Title of host publication	Proceedings of the 6th Computer Science Education Research Conference
Subtitle of host publication	CSERC '17
Publisher	Association for Computing Machinery
Pages	73-82
Number of pages	10
ISBN (Print)	9781450363389
DOIs	https://doi.org/10.1145/3162087.3162101
Publication status	Published - 14 Nov 2017

Keywords

Empirical study
Program plagiarism detection
Quantitative comparison
Tools

Access to Document

10.1145/3162087.3162101

Cite this

@inproceedings{ccb6ff87a7f04352821a18694e577390,

title = "A quantitative comparison of program plagiarism detection tools",

abstract = "In this work we compare a total of 9 different tools for the detection of source code plagiarism. We evaluated the plagiarism or copy detection tools CPD, JPlag, Sherlock, Marble, Moss, Plaggie and SIM and two baselines, one based on the Unix tool diff and one based on the difflib module from the Python Standard Library. We provide visualizations of the output of these tools and compare the performance of each tool when running it on different tasks by comparing both the F-measures and the area under the precision-recall-curve (AUC-PR). We compare the performance using these metrics on each task and identify the best performing tools.",

keywords = "Empirical study, Program plagiarism detection, Quantitative comparison, Tools",

author = "Dani{\"e}l Heres and Jurriaan Hage",

year = "2017",

month = nov,

day = "14",

doi = "10.1145/3162087.3162101",

language = "English",

isbn = "9781450363389",

pages = "73--82",

booktitle = "Proceedings of the 6th Computer Science Education Research Conference",

publisher = "Association for Computing Machinery",

address = "United States",

}

TY - GEN

T1 - A quantitative comparison of program plagiarism detection tools

AU - Heres, Daniël

AU - Hage, Jurriaan

PY - 2017/11/14

Y1 - 2017/11/14

N2 - In this work we compare a total of 9 different tools for the detection of source code plagiarism. We evaluated the plagiarism or copy detection tools CPD, JPlag, Sherlock, Marble, Moss, Plaggie and SIM and two baselines, one based on the Unix tool diff and one based on the difflib module from the Python Standard Library. We provide visualizations of the output of these tools and compare the performance of each tool when running it on different tasks by comparing both the F-measures and the area under the precision-recall-curve (AUC-PR). We compare the performance using these metrics on each task and identify the best performing tools.

AB - In this work we compare a total of 9 different tools for the detection of source code plagiarism. We evaluated the plagiarism or copy detection tools CPD, JPlag, Sherlock, Marble, Moss, Plaggie and SIM and two baselines, one based on the Unix tool diff and one based on the difflib module from the Python Standard Library. We provide visualizations of the output of these tools and compare the performance of each tool when running it on different tasks by comparing both the F-measures and the area under the precision-recall-curve (AUC-PR). We compare the performance using these metrics on each task and identify the best performing tools.

KW - Empirical study

KW - Program plagiarism detection

KW - Quantitative comparison

KW - Tools

U2 - 10.1145/3162087.3162101

DO - 10.1145/3162087.3162101

M3 - Conference contribution

SN - 9781450363389

SP - 73

EP - 82

BT - Proceedings of the 6th Computer Science Education Research Conference

PB - Association for Computing Machinery

ER -

A quantitative comparison of program plagiarism detection tools

Abstract

Keywords

Access to Document

Fingerprint

Cite this