Effect of source-code preprocessing techniques on plagiarism detection accuracy in student programming assignments

doctoral thesis

• Title (croatian): Utjecaj tehnika za predobradu izvornog koda na točnost otkrivanja plagijata u studentskim zadacima iz programiranja
• Author: Matija Novak; MBZ: 343365
• Mentor: Dragutin Kermek (mentor); MBZ: 136014
• Mentor: Mike S. Joy https://orcid.org/0000-0001-9826-5928 (komentor)
• Committee member: Jasminka Dobša (predsjednik povjerenstva); MBZ: 218640
• Committee member: Marjan Krašna (član povjerenstva); MBZ: 11127
• Committee member: Zlatko Stapić (član povjerenstva); MBZ: 291843
• Granter: University of Zagreb; Faculty of Organization and Informatics; Varaždin
• Defense date and country: 2020-02-02, Croatia
• Scientific / art field, discipline and subdiscipline: SOCIAL SCIENCES; Information and Communication Sciences
• Universal decimal classification (UDC): 004 - Computer science and technology. Computing. Data processing

Abstract

Plagiarism is a serious problem in academia and students cheat for various reasons, but whateverthereasonsuchbehaviourshouldnotbeaccepted. Whileitiseasytocontrolplagiarism in classrooms with few students it can be a challenge to do it in a classroom with one hundred students or more. To help teacher detect plagiarism similarity detection tools are built, usually called plagiarism detection tools. While in academia plagiarism can be done in many areas the two most common are textual and programming assignments. In this thesis, the focus is on detecting plagiarism in student programming assignments. Since the tools are not perfect there is always room for improvement and one possibility to improve the plagiarism detection quality is the usage of preprocessing techniques. Preprocessing techniques have been used in many plagiarism detection tools but there is not much research focusing on the effects of such techniques. To investigate the effect of preprocessing techniques on plagiarism detection tools an experiment was conducted on six tools using five techniques on two different datasets, whereby one dataset is publicly available. To be more precise the six tools were actually three tools whereby each tool had two modes to operatethespecializedmodewhichisspeciallydevelopedtoperformasource-codecomparison and textual mode developed for normal text comparison. In this experiment two hypotheses were stated, one focusing on the differences between the preprocessing techniques and when no preprocessing technique is used and other focusing on differences between two different techniques. In addition to the hypothesis one research question was stated to give more insight into the effects of the preprocessing techniques. Resultsoftheexperimentwereanalysedquantitativelyusingthemultifactoranalysisofvariance and qualitatively by analysing the most interesting cases. The whole process of detection and statistical analysis was automated using the newly developed system called Multiple Plagiarism Checker and the system R. The experimental results confirmed both hypotheses showing that using preprocessing has a positive effect on the quality of plagiarism detection and that some techniques gave better results than others. The most interesting result of this research is that by using preprocessing techniques textual versions of the tools outperformed in some cases the specialized version of the tool developed specifically for source-code similarity detection.

Abstract (croatian)

Plagiranje u akademskoj sredini je ozbiljan problem. Kako bi se pomoglo nastavnicima da otkriju plagiranje izrađuju se alati za otkrivanje sličnosti. Fokus ovog rada jest otkrivanje plagijata u studentskim zadacima iz programiranja. Kako alati nisu savršeni uvijek postoji način da ih se poboljša, a jedan način da se poboljša točnost otkrivanja plagijata jest primjena tehnika predobrade. Kako bi se istražio utjecaj tehnika predobrade na alate za otkrivanje plagijata proveden je eksperiment sa tri alata i pet tehnika na dva različita skupa podataka od kojih je jedan skup javno dostupan. Svaki od alata ima dva načina rada. Specijalizirani način koji je posebno razvijen da radi usporedbe izvornog koda i tekstualni način koji je razvijen za usporedbu normalnog teksta. Glavni cilj eksperimenta je bio identificirati utjecaj tehnika predobrade (TPO-a) na točnost otkrivanja plagijata u studentskim zadacima iz programiranja. Kako bi se postigao taj cilj prvo se ispitalo ima li primjena TPO-a utjecaj na točnost otkrivanja plagijata i ako da, ispitalo se kako, kada i zašto različite TPO-e utječu na točnost otkrivanja plagijata. Rezultati dobiveni eksperimentom su pokazali da predobrađivanje ima pozitivan utjecaj na kvalitetu otkrivanja plagijata i da neke tehnike predobrade daju bolje rezultate od drugih tehnika. Najzanimljiviji rezultat ovog istraživanja jest da u nekim slučajevima, korištenjem tehnika predobrade, tekstualni način rada alata nadmašuje specijalizirani način rada alata koji je posebno razvijen za otkrivanje sličnosti u izvornom kodu.

• Keywords: plagiarsim detection; high education; source-code; programming assignements; preprocessing tehniques; comparison; program similarity
• Keywords (croatian): plagiranje-otkrivanje; visoko obrazovanje; programiranje-zadaci; izvorni kod
• Language: english
• URN:NBN: urn:nbn:hr:211:528052
• Study programme: Title: Postgraduate doctoral study in Information Science; Study programme type: university; Study level: postgraduate; Academic / professional title: doktor/doktorica znanosti, područje društvenih znanosti, polje informacijske i komunikacijske znanosti (doktor/doktorica znanosti, područje društvenih znanosti, polje informacijske i komunikacijske znanosti)
• Type of resource: Text
• File origin: Born digital
• Access conditions: Open access
• Created on: 2020-02-24 17:41:12