Intrinzična detekcija plagijata

master's thesis

• Title (english): Intrinsic plagiarism detection
• Author: Helena Viher
• Mentor: Vedran Juričić (mentor)
• Committee member: Sanja Seljan (predsjednik povjerenstva)
• Committee member: Ivan Dunđer (član povjerenstva)
• Committee member: Vedran Juričić (član povjerenstva)
• Granter: University of Zagreb; Faculty of Humanities and Social Sciences; (Department of information and Communication sciences); Zagreb
• Defense date and country: 2020-12-07, Croatia
• Scientific / art field, discipline and subdiscipline: SOCIAL SCIENCES; Information and Communication Sciences

Abstract

Detekcija plagijata podrazumijeva pronalaženje i prepoznavanje plagiranih dijelova teksta unutar pisanih dokumenata kao što su znanstveni radovi, školski eseji i seminarski radovi, no može se provesti i nad programskim kodom, umjetničkim djelima i sl. Pojavom interneta plagiranje je postalo sve prisutnije, a zbog velike količine izvora iz kojih je moguće plagirati, detekcija plagijata bez pomoći računala uvelike je otežana. Kod računalno potpomognute detekcije plagijata moguća su dva pristupa: ekstrinzični i intrinzični. Ekstrinzična detekcija uspoređuje rad s referentnim tekstovima, dok intrinzična detekcija plagirane dijelove teksta prepoznaje na temelju nedosljednosti u tekstu te promjena u stilu pisanja. U radu se daje pregled intrinzične detekcije plagijata, prikazuje njen način rada i pristupi koji se koriste u detekciji promjena u stilu pisanja. Na samom kraju navode se prednosti i nedostaci ovog pristupa te evaluacija uspješnosti u pronalaženju plagiranih dijelova teksta.

Abstract (english)

Plagiarism detection involves finding and recognizing plagiarized parts of text within written documents such as scientific papers, school essays, seminar papers, etc., and can also be performed on program code, works of art and other examples of work. With the advent of the Internet, plagiarism has become more prevalent and due to a large number of sources to plagiarize from the detection of plagiarism without the help of a computer is greatly hampered. In computer-assisted plagiarism detection two approaches are possible: extrinsic and intrinsic. Extrinsic detection compares the work with reference texts, while intrinsic detection recognizes plagiarized parts of the text based on inconsistencies in the text and changes in writing styles. This paper provides an overview of intrinsic plagiarism detection, shows how it operates and the approaches used in detecting changes in writing styles. At the very end, the advantages and disadvantages of this approach are stated and the evaluation of its success in finding plagiarized parts of the text.

• Keywords: plagiranje; detekcija plagijata; intrinzična detekcija plagijata; stilometrija
• Keywords (english): plagiarism; plagiarism detection; intrinsic plagiarism detection; stylometry
• Language: croatian
• URN:NBN: urn:nbn:hr:131:681101
• Study programme: Title: Information Sciences; specializations in: Informatology, Information Sciences (teaching), Information Sciences (research); Course: Information Sciences (research); Study programme type: university; Study level: graduate; Academic / professional title: magistar/magistra informacijskih znanosti (magistar/magistra informacijskih znanosti)
• Type of resource: Text
• File origin: Born digital
• Access conditions: Open access
• Created on: 2020-12-10 12:07:11