{"id":"https://openalex.org/W1970222407","doi":"https://doi.org/10.1145/2644866.2644879","title":"Classifying and ranking search engine results as potential sources of plagiarism","display_name":"Classifying and ranking search engine results as potential sources of plagiarism","publication_year":2014,"publication_date":"2014-09-16","ids":{"openalex":"https://openalex.org/W1970222407","doi":"https://doi.org/10.1145/2644866.2644879","mag":"1970222407"},"language":"en","primary_location":{"id":"doi:10.1145/2644866.2644879","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2644866.2644879","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2014 ACM symposium on Document engineering","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/A5027117126","display_name":"Kyle Williams","orcid":"https://orcid.org/0000-0003-4333-9111"},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Kyle Williams","raw_affiliation_strings":["The Pennsylvania State University, University Park, PA, USA","The Pennsylvania State University , University Park, PA, USA"],"affiliations":[{"raw_affiliation_string":"The Pennsylvania State University, University Park, PA, USA","institution_ids":["https://openalex.org/I130769515"]},{"raw_affiliation_string":"The Pennsylvania State University , University Park, PA, USA","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078925594","display_name":"Hung\u2010Hsuan Chen","orcid":"https://orcid.org/0000-0001-5137-4449"},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hung-Hsuan Chen","raw_affiliation_strings":["The Pennsylvania State University, University Park, PA, USA","The Pennsylvania State University , University Park, PA, USA"],"affiliations":[{"raw_affiliation_string":"The Pennsylvania State University, University Park, PA, USA","institution_ids":["https://openalex.org/I130769515"]},{"raw_affiliation_string":"The Pennsylvania State University , University Park, PA, USA","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001294898","display_name":"C. Lee Giles","orcid":"https://orcid.org/0000-0002-1931-585X"},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"C. Lee Giles","raw_affiliation_strings":["The Pennsylvania State University, University Park, PA, USA","The Pennsylvania State University , University Park, PA, USA"],"affiliations":[{"raw_affiliation_string":"The Pennsylvania State University, University Park, PA, USA","institution_ids":["https://openalex.org/I130769515"]},{"raw_affiliation_string":"The Pennsylvania State University , University Park, PA, USA","institution_ids":["https://openalex.org/I130769515"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5027117126"],"corresponding_institution_ids":["https://openalex.org/I130769515"],"apc_list":null,"apc_paid":null,"fwci":2.4804,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.89095591,"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":"97","last_page":"106"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11492","display_name":"Academic integrity and plagiarism","score":0.9983000159263611,"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":0.9983000159263611,"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/T10028","display_name":"Topic Modeling","score":0.996399998664856,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.9916999936103821,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/plagiarism-detection","display_name":"Plagiarism detection","score":0.788142740726471},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.7720124125480652},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7490280866622925},{"id":"https://openalex.org/keywords/search-engine","display_name":"Search engine","score":0.7286478281021118},{"id":"https://openalex.org/keywords/ranking","display_name":"Ranking (information retrieval)","score":0.6978500485420227},{"id":"https://openalex.org/keywords/precision-and-recall","display_name":"Precision and recall","score":0.501131534576416},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.5010130405426025},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.45905765891075134},{"id":"https://openalex.org/keywords/recall","display_name":"Recall","score":0.43079525232315063},{"id":"https://openalex.org/keywords/learning-to-rank","display_name":"Learning to rank","score":0.4248751997947693},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.36017537117004395},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.27679574489593506}],"concepts":[{"id":"https://openalex.org/C2780907237","wikidata":"https://www.wikidata.org/wiki/Q2986238","display_name":"Plagiarism detection","level":2,"score":0.788142740726471},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.7720124125480652},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7490280866622925},{"id":"https://openalex.org/C97854310","wikidata":"https://www.wikidata.org/wiki/Q19541","display_name":"Search engine","level":2,"score":0.7286478281021118},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.6978500485420227},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.501131534576416},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.5010130405426025},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.45905765891075134},{"id":"https://openalex.org/C100660578","wikidata":"https://www.wikidata.org/wiki/Q18733","display_name":"Recall","level":2,"score":0.43079525232315063},{"id":"https://openalex.org/C86037889","wikidata":"https://www.wikidata.org/wiki/Q4330127","display_name":"Learning to rank","level":3,"score":0.4248751997947693},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.36017537117004395},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.27679574489593506},{"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/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"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},{"id":"https://openalex.org/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1145/2644866.2644879","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2644866.2644879","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2014 ACM symposium on Document engineering","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.671.4141","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.671.4141","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.personal.psu.edu/kiw5209/papers/slides/2014/williams_doceng2014_plagiarism_slides.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.674.5995","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.674.5995","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://dr-hhchen.appspot.com/academic_works/williams2014_classifying.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.685.5223","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.685.5223","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.personal.psu.edu/kiw5209/papers/2014/williams_doceng2014_plagiarism.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G8251020264","display_name":null,"funder_award_id":"1143921","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W14532928","https://openalex.org/W66633355","https://openalex.org/W86855850","https://openalex.org/W191835235","https://openalex.org/W197093853","https://openalex.org/W1534477342","https://openalex.org/W1554365104","https://openalex.org/W1554944419","https://openalex.org/W1555316140","https://openalex.org/W1973435495","https://openalex.org/W1974336599","https://openalex.org/W1977729554","https://openalex.org/W1996430422","https://openalex.org/W2008831863","https://openalex.org/W2009571180","https://openalex.org/W2011501238","https://openalex.org/W2021947911","https://openalex.org/W2031169004","https://openalex.org/W2047221353","https://openalex.org/W2056081163","https://openalex.org/W2060636190","https://openalex.org/W2101234009","https://openalex.org/W2111593814","https://openalex.org/W2118978333","https://openalex.org/W2119114217","https://openalex.org/W2127176025","https://openalex.org/W2143296909","https://openalex.org/W2146769536","https://openalex.org/W2148143831","https://openalex.org/W2157063199","https://openalex.org/W2251179870","https://openalex.org/W2398009617","https://openalex.org/W2407707865","https://openalex.org/W2787894218","https://openalex.org/W2911964244","https://openalex.org/W2997591727","https://openalex.org/W4302313152","https://openalex.org/W6603477831","https://openalex.org/W6607717345","https://openalex.org/W6607922304","https://openalex.org/W6677877803","https://openalex.org/W6986298011"],"related_works":["https://openalex.org/W3168266056","https://openalex.org/W4287126803","https://openalex.org/W2112890327","https://openalex.org/W4250737080","https://openalex.org/W2735162248","https://openalex.org/W311440260","https://openalex.org/W2945111072","https://openalex.org/W4379381520","https://openalex.org/W2127423266","https://openalex.org/W4301519770"],"abstract_inverted_index":{"Source":[0],"retrieval":[1,62],"for":[2,16,60,138],"plagiarism":[3,15,43,76],"detection":[4],"involves":[5],"using":[6,84],"a":[7,17,101],"search":[8,66,80,90,139,148],"engine":[9],"to":[10,39,49,100,106,111,116,124,130,152],"retrieve":[11],"candidate":[12],"sources":[13,41,74],"of":[14,42,53,75,94,133],"given":[18],"suspicious":[19],"document":[20,146],"so":[21,47],"that":[22,33,36],"more":[23],"accurate":[24],"comparisons":[25,55],"can":[26],"be":[27,40,45,153],"made.":[28,56],"An":[29],"important":[30,137],"consideration":[31],"is":[32,63,98],"only":[34,85],"documents":[35,82],"are":[37,68,128,135],"likely":[38],"should":[44],"retrieved":[46],"as":[48,72],"minimize":[50],"the":[51,79,86,95,119,154],"number":[52],"unnecessary":[54],"A":[57],"supervised":[58,96],"strategy":[59],"source":[61],"described":[64],"whereby":[65],"results":[67],"classified":[69],"and":[70,83,104,118,147],"ranked":[71],"potential":[73],"without":[77],"retrieving":[78],"result":[81,140,149],"information":[87],"available":[88],"at":[89],"time.":[91],"The":[92],"performance":[93],"method":[97,103],"compared":[99],"baseline":[102],"shown":[105],"improve":[107],"precision":[108],"by":[109,114,122],"up":[110,115,123],"3.28%,":[112],"recall":[113],"2.6%":[117],"F1":[120],"score":[121],"3.37%.":[125],"Furthermore,":[126],"features":[127,143],"analyzed":[129],"determine":[131],"which":[132],"them":[134],"most":[136,155],"classification":[141],"with":[142],"based":[144],"on":[145],"similarity":[150],"appearing":[151],"important.":[156]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}