{"id":"https://openalex.org/W3107733564","doi":"https://doi.org/10.1145/3428029.3428065","title":"Preprocessing for Source Code Similarity Detection in Introductory Programming","display_name":"Preprocessing for Source Code Similarity Detection in Introductory Programming","publication_year":2020,"publication_date":"2020-11-19","ids":{"openalex":"https://openalex.org/W3107733564","doi":"https://doi.org/10.1145/3428029.3428065","mag":"3107733564"},"language":"en","primary_location":{"id":"doi:10.1145/3428029.3428065","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3428029.3428065","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Koli Calling '20: Proceedings of the 20th Koli Calling International Conference on Computing Education Research","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5043851929","display_name":"Oscar Karnalim","orcid":"https://orcid.org/0000-0003-4930-6249"},"institutions":[{"id":"https://openalex.org/I78757542","display_name":"University of Newcastle Australia","ror":"https://ror.org/00eae9z71","country_code":"AU","type":"education","lineage":["https://openalex.org/I78757542"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"Oscar Karnalim","raw_affiliation_strings":["University of Newcastle, Australia"],"affiliations":[{"raw_affiliation_string":"University of Newcastle, Australia","institution_ids":["https://openalex.org/I78757542"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Simon","orcid":null},"institutions":[{"id":"https://openalex.org/I78757542","display_name":"University of Newcastle Australia","ror":"https://ror.org/00eae9z71","country_code":"AU","type":"education","lineage":["https://openalex.org/I78757542"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Simon","raw_affiliation_strings":["University of Newcastle, Australia"],"affiliations":[{"raw_affiliation_string":"University of Newcastle, Australia","institution_ids":["https://openalex.org/I78757542"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5072345952","display_name":"William Chivers","orcid":"https://orcid.org/0000-0002-9731-5441"},"institutions":[{"id":"https://openalex.org/I78757542","display_name":"University of Newcastle Australia","ror":"https://ror.org/00eae9z71","country_code":"AU","type":"education","lineage":["https://openalex.org/I78757542"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"William Chivers","raw_affiliation_strings":["University of Newcastle, Australia"],"affiliations":[{"raw_affiliation_string":"University of Newcastle, Australia","institution_ids":["https://openalex.org/I78757542"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5043851929"],"corresponding_institution_ids":["https://openalex.org/I78757542"],"apc_list":null,"apc_paid":null,"fwci":1.9477,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.89996684,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"10"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.9991999864578247,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.9991999864578247,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11241","display_name":"Advanced Malware Detection Techniques","score":0.9927999973297119,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10743","display_name":"Software Testing and Debugging Techniques","score":0.984499990940094,"subfield":{"id":"https://openalex.org/subfields/1712","display_name":"Software"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8393542170524597},{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.7152958512306213},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.6855517625808716},{"id":"https://openalex.org/keywords/plagiarism-detection","display_name":"Plagiarism detection","score":0.6538373827934265},{"id":"https://openalex.org/keywords/identifier","display_name":"Identifier","score":0.5712754726409912},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5066919922828674},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.48790356516838074},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.4803784489631653},{"id":"https://openalex.org/keywords/abstract-syntax-tree","display_name":"Abstract syntax tree","score":0.47603490948677063},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.4597075581550598},{"id":"https://openalex.org/keywords/static-program-analysis","display_name":"Static program analysis","score":0.45104172825813293},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4336088001728058},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.42233502864837646},{"id":"https://openalex.org/keywords/syntax","display_name":"Syntax","score":0.4135710597038269},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.3818294107913971},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.2750861942768097},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2665802240371704},{"id":"https://openalex.org/keywords/software-development","display_name":"Software development","score":0.1698639690876007},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.09930640459060669}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8393542170524597},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.7152958512306213},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.6855517625808716},{"id":"https://openalex.org/C2780907237","wikidata":"https://www.wikidata.org/wiki/Q2986238","display_name":"Plagiarism detection","level":2,"score":0.6538373827934265},{"id":"https://openalex.org/C154504017","wikidata":"https://www.wikidata.org/wiki/Q853614","display_name":"Identifier","level":2,"score":0.5712754726409912},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5066919922828674},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.48790356516838074},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.4803784489631653},{"id":"https://openalex.org/C58646249","wikidata":"https://www.wikidata.org/wiki/Q127380","display_name":"Abstract syntax tree","level":3,"score":0.47603490948677063},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.4597075581550598},{"id":"https://openalex.org/C137287247","wikidata":"https://www.wikidata.org/wiki/Q1329550","display_name":"Static program analysis","level":4,"score":0.45104172825813293},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4336088001728058},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.42233502864837646},{"id":"https://openalex.org/C60048249","wikidata":"https://www.wikidata.org/wiki/Q37437","display_name":"Syntax","level":2,"score":0.4135710597038269},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.3818294107913971},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.2750861942768097},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2665802240371704},{"id":"https://openalex.org/C529173508","wikidata":"https://www.wikidata.org/wiki/Q638608","display_name":"Software development","level":3,"score":0.1698639690876007},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.09930640459060669},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3428029.3428065","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3428029.3428065","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Koli Calling '20: Proceedings of the 20th Koli Calling International Conference on Computing Education Research","raw_type":"proceedings-article"},{"id":"pmh:uon:40820","is_oa":false,"landing_page_url":"http://hdl.handle.net/1959.13/1439091","pdf_url":null,"source":{"id":"https://openalex.org/S4377196471","display_name":"NOVA (University of Newcastle Australia)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I78757542","host_organization_name":"University of Newcastle Australia","host_organization_lineage":["https://openalex.org/I78757542"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"conference paper"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7200000286102295,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W770523223","https://openalex.org/W1569888331","https://openalex.org/W1819770257","https://openalex.org/W1971922616","https://openalex.org/W2013278751","https://openalex.org/W2067982285","https://openalex.org/W2106487114","https://openalex.org/W2141128179","https://openalex.org/W2146659255","https://openalex.org/W2155056246","https://openalex.org/W2162992371","https://openalex.org/W2174793288","https://openalex.org/W2194609298","https://openalex.org/W2248990385","https://openalex.org/W2590391696","https://openalex.org/W2590657376","https://openalex.org/W2609731675","https://openalex.org/W2766078762","https://openalex.org/W2890485822","https://openalex.org/W2913993872","https://openalex.org/W2963366873","https://openalex.org/W2984910034","https://openalex.org/W3094215385","https://openalex.org/W4251504464","https://openalex.org/W4292014584","https://openalex.org/W6681648988"],"related_works":["https://openalex.org/W2117635164","https://openalex.org/W2389581423","https://openalex.org/W2186104229","https://openalex.org/W4312965042","https://openalex.org/W2013278751","https://openalex.org/W2293891280","https://openalex.org/W2074805222","https://openalex.org/W2751940653","https://openalex.org/W141292575","https://openalex.org/W4229035221"],"abstract_inverted_index":{"It":[0],"is":[1,42],"well":[2],"documented":[3],"that":[4,95,116,224],"some":[5],"students":[6,225],"either":[7],"work":[8,16],"together":[9],"on":[10,136],"programming":[11,144,217],"assessments":[12],"when":[13,158],"required":[14],"to":[15,67,107,151,156,168,219,228],"individually":[17],"(collusion)":[18],"or":[19,73,165],"make":[20],"unauthorised":[21],"use":[22],"of":[23,36,39,50,57,60,75,91,131,133,139,189,198,222],"existing":[24],"code":[25,44,62,78,121,161],"from":[26,142],"external":[27],"sources":[28],"(plagiarism).":[29],"One":[30],"approach":[31],"used":[32,119],"in":[33,86,120],"the":[34,47,65,69,71,76,87,92,126,129,169,199,220],"detection":[35,163],"these":[37,96,134],"violations":[38],"academic":[40],"integrity":[41],"source":[43,61,77,160],"similarity":[45,122,162],"detection,":[46,123],"automatic":[48],"checking":[49],"student":[51,140],"programs":[52,141],"for":[53],"unduly":[54],"high":[55],"levels":[56],"similarity.":[58],"Preprocessing":[59],"files":[63],"has":[64],"potential":[66],"increase":[68,184],"effectiveness,":[70],"efficiency,":[72],"both,":[74],"comparison":[79],"process.":[80],"There":[81],"are":[82,98,194],"many":[83],"possible":[84],"steps":[85,97,115,135,155,193],"preprocessing,":[88],"and":[89,100,124,128,176,180,202],"examination":[90],"literature":[93],"suggests":[94],"selected":[99],"implemented":[101],"without":[102],"any":[103],"empirical":[104],"evidence":[105],"as":[106],"their":[108],"value.":[109],"This":[110],"paper":[111,212],"lists":[112],"19":[113],"preprocessing":[114,154,192],"have":[117],"been":[118],"assesses":[125],"effectiveness":[127,175,185],"efficiency":[130],"16":[132],"data":[137,200],"sets":[138],"introductory":[143],"courses.":[145],"The":[146,211],"results":[147],"should":[148,203,213],"help":[149,215],"researchers":[150],"decide":[152],"what":[153],"include":[157],"designing":[159],"techniques":[164],"software.":[166],"According":[167],"study,":[170],"identifier":[171],"removal":[172],"increases":[173],"both":[174],"efficiency.":[177,190],"Token":[178],"renaming":[179],"syntax":[181],"tree":[182],"linearisation":[183],"at":[186],"a":[187],"cost":[188],"Other":[191],"dependent":[195],"upon":[196],"characteristics":[197],"set":[201],"ideally":[204],"be":[205],"empirically":[206],"tested":[207],"before":[208],"being":[209],"applied.":[210],"also":[214],"alert":[216],"educators":[218],"sorts":[221],"disguise":[223],"can":[226],"apply":[227],"copied":[229],"programs.":[230]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":2}],"updated_date":"2026-04-16T08:26:57.006410","created_date":"2025-10-10T00:00:00"}
