{"id":"https://openalex.org/W2963165069","doi":"https://doi.org/10.1145/3321408.3322862","title":"Measuring code similarity using word mover's distance for programming course","display_name":"Measuring code similarity using word mover's distance for programming course","publication_year":2019,"publication_date":"2019-05-17","ids":{"openalex":"https://openalex.org/W2963165069","doi":"https://doi.org/10.1145/3321408.3322862","mag":"2963165069"},"language":"en","primary_location":{"id":"doi:10.1145/3321408.3322862","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3321408.3322862","pdf_url":null,"source":{"id":"https://openalex.org/S4306523950","display_name":"Proceedings of the ACM Turing Celebration Conference - China","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM Turing Celebration Conference - China","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/A5060595906","display_name":"Xu Bin","orcid":"https://orcid.org/0000-0003-0744-8513"},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Bin Xu","raw_affiliation_strings":["Northeastern University, Shenyang, Liaoning"],"affiliations":[{"raw_affiliation_string":"Northeastern University, Shenyang, Liaoning","institution_ids":["https://openalex.org/I9224756"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037102944","display_name":"Fan Gao","orcid":"https://orcid.org/0000-0003-0656-6382"},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fan Gao","raw_affiliation_strings":["Northeastern University, Shenyang, Liaoning, China"],"affiliations":[{"raw_affiliation_string":"Northeastern University, Shenyang, Liaoning, China","institution_ids":["https://openalex.org/I9224756"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049254877","display_name":"Kening Gao","orcid":null},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kening Gao","raw_affiliation_strings":["Northeastern University, Shenyang, Liaoning, China"],"affiliations":[{"raw_affiliation_string":"Northeastern University, Shenyang, Liaoning, China","institution_ids":["https://openalex.org/I9224756"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003114697","display_name":"Changkuan Zhao","orcid":null},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Changkuan Zhao","raw_affiliation_strings":["Northeastern University, Shenyang, Liaoning, China"],"affiliations":[{"raw_affiliation_string":"Northeastern University, Shenyang, Liaoning, China","institution_ids":["https://openalex.org/I9224756"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101512200","display_name":"Dan Yang","orcid":"https://orcid.org/0000-0002-3817-7333"},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dan Yang","raw_affiliation_strings":["Northeastern University, Shenyang, Liaoning, China"],"affiliations":[{"raw_affiliation_string":"Northeastern University, Shenyang, Liaoning, China","institution_ids":["https://openalex.org/I9224756"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5060595906"],"corresponding_institution_ids":["https://openalex.org/I9224756"],"apc_list":null,"apc_paid":null,"fwci":0.7149,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.78055556,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"2"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11492","display_name":"Academic integrity and plagiarism","score":0.9973999857902527,"subfield":{"id":"https://openalex.org/subfields/3311","display_name":"Safety Research"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11492","display_name":"Academic integrity and plagiarism","score":0.9973999857902527,"subfield":{"id":"https://openalex.org/subfields/3311","display_name":"Safety Research"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.957099974155426,"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":0.909500002861023,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8039448261260986},{"id":"https://openalex.org/keywords/word2vec","display_name":"Word2vec","score":0.6291228532791138},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.5817071199417114},{"id":"https://openalex.org/keywords/commit","display_name":"Commit","score":0.5645624995231628},{"id":"https://openalex.org/keywords/plagiarism-detection","display_name":"Plagiarism detection","score":0.5609472990036011},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5528686046600342},{"id":"https://openalex.org/keywords/mistake","display_name":"Mistake","score":0.5181530714035034},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.49178794026374817},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.47421884536743164},{"id":"https://openalex.org/keywords/the-internet","display_name":"The Internet","score":0.45695969462394714},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.4546017348766327},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.378360390663147},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.34576770663261414},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.329231858253479},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3252720534801483},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.2800801694393158},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.16593298316001892}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8039448261260986},{"id":"https://openalex.org/C2776461190","wikidata":"https://www.wikidata.org/wiki/Q22673982","display_name":"Word2vec","level":3,"score":0.6291228532791138},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.5817071199417114},{"id":"https://openalex.org/C153180980","wikidata":"https://www.wikidata.org/wiki/Q19776675","display_name":"Commit","level":2,"score":0.5645624995231628},{"id":"https://openalex.org/C2780907237","wikidata":"https://www.wikidata.org/wiki/Q2986238","display_name":"Plagiarism detection","level":2,"score":0.5609472990036011},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5528686046600342},{"id":"https://openalex.org/C2777179996","wikidata":"https://www.wikidata.org/wiki/Q911222","display_name":"Mistake","level":2,"score":0.5181530714035034},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.49178794026374817},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.47421884536743164},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.45695969462394714},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.4546017348766327},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.378360390663147},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.34576770663261414},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.329231858253479},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3252720534801483},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.2800801694393158},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.16593298316001892},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3321408.3322862","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3321408.3322862","pdf_url":null,"source":{"id":"https://openalex.org/S4306523950","display_name":"Proceedings of the ACM Turing Celebration Conference - China","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM Turing Celebration Conference - China","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7599999904632568,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":3,"referenced_works":["https://openalex.org/W2012833704","https://openalex.org/W2111295912","https://openalex.org/W2906891466"],"related_works":["https://openalex.org/W3127553152","https://openalex.org/W3002459461","https://openalex.org/W3173165160","https://openalex.org/W3127649977","https://openalex.org/W4287331153","https://openalex.org/W4312858192","https://openalex.org/W2155491649","https://openalex.org/W4224015079","https://openalex.org/W2100097978","https://openalex.org/W3091649732"],"abstract_inverted_index":{"Teachers":[0],"tend":[1],"to":[2,17,31,53],"ask":[3],"students":[4,104,127],"submit":[5],"their":[6,106,153],"assignments":[7],"online":[8,12],"not":[9],"only":[10],"in":[11,45,94,119],"courses":[13],"but":[14],"also":[15],"face":[16,18],"courses.":[19],"The":[20,159],"phenomena":[21],"of":[22,60,71,73,176],"plagiarism":[23,62,75,101,157],"is":[24,82,132,169,186],"becoming":[25],"more":[26,28,78,113],"and":[27,68,128,152,191],"serious":[29],"due":[30],"the":[32,41,95,99,138,163],"ease":[33],"with":[34,87,147],"which":[35],"resources":[36],"can":[37],"be":[38],"found":[39],"on":[40,162],"Internet":[42],"also,":[43],"especially":[44],"a":[46,55,77,133],"computer":[47],"programming":[48,64,123],"course.":[49,65],"This":[50],"paper":[51],"aims":[52],"develop":[54],"robust":[56,79],"automated":[57],"detection":[58,80],"technology":[59,81],"code":[61,74,117,135,177],"towards":[63],"After":[66],"analyzing":[67],"summarized":[69],"state":[70],"art":[72],"technology,":[76],"developed":[83],"by":[84],"combining":[85],"word2vec":[86],"Word":[88],"mover's":[89],"distance":[90],"(WMD)":[91],"similarity":[92,184],"metric":[93,185],"paper.":[96],"We":[97,179],"consider":[98],"different":[100,156,174],"methods":[102],"when":[103],"commit":[105],"program":[107],"source":[108],"code.":[109],"Then":[110],"we":[111,140],"collect":[112],"than":[114],"20":[115],"thousands":[116],"submissions":[118],"our":[120,143,167],"introductory":[121],"C++":[122],"course":[124],"for":[125,155,172,188],"non-major":[126],"check":[129],"whether":[130],"it":[131],"plagiarized":[134],"manually.":[136],"In":[137],"process,":[139],"examine":[141],"how":[142],"proposed":[144],"method":[145],"compare":[146],"two":[148],"other":[149],"main":[150],"algorithms":[151],"suitability":[154],"characteristics.":[158],"results":[160],"obtained":[161],"dataset":[164],"indicate":[165],"that":[166,181],"approach":[168],"well":[170],"suited":[171],"detect":[173],"types":[175],"plagiarism.":[178],"conclude":[180],"incorporating":[182],"WMD":[183],"crucial":[187],"improved":[189],"effective":[190],"adaptability.":[192]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
