{"id":"https://openalex.org/W184453455","doi":null,"title":"Fuzzy semantic-based string similarity for extrinsic plagiarism detection: Lab report for PAN at CLEF 2010","display_name":"Fuzzy semantic-based string similarity for extrinsic plagiarism detection: Lab report for PAN at CLEF 2010","publication_year":2010,"publication_date":"2010-01-01","ids":{"openalex":"https://openalex.org/W184453455","mag":"184453455"},"language":"en","primary_location":{"id":"pmh:oai:CiteSeerX.psu:10.1.1.174.2871","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.174.2871","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://clef2010.org/resources/proceedings/clef2010labs_submission_21.pdf","raw_type":"text"},"volume":null,"type":"article","indexed_in":[],"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/A5064370497","display_name":"Salha M. Alzahrani","orcid":"https://orcid.org/0000-0001-7785-6980","observed_orcids":["https://orcid.org/0000-0001-7785-6980"]},"institutions":[{"id":"https://openalex.org/I179331831","display_name":"Taif University","ror":"https://ror.org/014g1a453","country_code":"SA","type":"education","lineage":["https://openalex.org/I179331831"]}],"countries":["SA"],"is_corresponding":false,"raw_author_name":"Salha M. Alzahrani","raw_affiliation_strings":["TAIF University"],"raw_orcid":"https://orcid.org/0000-0001-7785-6980","affiliations":[{"raw_affiliation_string":"TAIF University","institution_ids":["https://openalex.org/I179331831"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5012641332","display_name":"Naomie Binti Salim","orcid":"https://orcid.org/0000-0001-8509-3055","observed_orcids":["https://orcid.org/0000-0001-8509-3055"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Naomie Salim","raw_affiliation_strings":["Department of Information System"],"raw_orcid":"https://orcid.org/0000-0001-8509-3055","affiliations":[{"raw_affiliation_string":"Department of Information System","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":12.5801,"has_fulltext":false,"cited_by_count":57,"citation_normalized_percentile":{"value":0.98206043,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11492","display_name":"Academic integrity and plagiarism","score":0.9541000127792358,"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":0.9541000127792358,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.007199999876320362,"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/T10260","display_name":"Software Engineering Research","score":0.006399999838322401,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/plagiarism-detection","display_name":"plagiarism detection","score":0.847000002861023},{"id":"https://openalex.org/keywords/string-similarity","display_name":"string similarity","score":0.9409999847412109},{"id":"https://openalex.org/keywords/shingling","display_name":"shingling","score":0.7409999966621399},{"id":"https://openalex.org/keywords/jaccard-similarity","display_name":"Jaccard similarity","score":0.9900000095367432},{"id":"https://openalex.org/keywords/text-obfuscation","display_name":"text obfuscation","score":0.5649999976158142}],"concepts":[{"id":"https://openalex.org/C107763842","wikidata":"https://www.wikidata.org/wiki/Q181040","display_name":"Clef","level":3,"score":0.8659985661506653},{"id":"https://openalex.org/C2780907237","wikidata":"https://www.wikidata.org/wiki/Q2986238","display_name":"Plagiarism detection","level":2,"score":0.7311916351318359},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5855592489242554},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.545362114906311},{"id":"https://openalex.org/C157486923","wikidata":"https://www.wikidata.org/wiki/Q1376436","display_name":"String (physics)","level":2,"score":0.537445604801178},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5166788101196289},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.4603775143623352},{"id":"https://openalex.org/C130318100","wikidata":"https://www.wikidata.org/wiki/Q2268914","display_name":"Semantic similarity","level":2,"score":0.4584940969944},{"id":"https://openalex.org/C58166","wikidata":"https://www.wikidata.org/wiki/Q224821","display_name":"Fuzzy logic","level":2,"score":0.4141940772533417},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3620383143424988},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.26931941509246826},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1595940887928009},{"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/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.0},{"id":"https://openalex.org/C37914503","wikidata":"https://www.wikidata.org/wiki/Q156495","display_name":"Mathematical physics","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:CiteSeerX.psu:10.1.1.174.2871","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.174.2871","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://clef2010.org/resources/proceedings/clef2010labs_submission_21.pdf","raw_type":"text"},{"id":"mag:184453455","doi":null,"is_oa":false,"landing_page_url":"http://ceur-ws.org/Vol-1176/CLEF2010wn-PAN-AlzahraniEt2010.pdf","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":6,"referenced_works":["https://openalex.org/W1548134554","https://openalex.org/W1555539059","https://openalex.org/W2081580037","https://openalex.org/W2098162425","https://openalex.org/W2099416135","https://openalex.org/W2121184547"],"related_works":["https://openalex.org/W190068516","https://openalex.org/W3005292403","https://openalex.org/W2072423339","https://openalex.org/W2186084918","https://openalex.org/W2252096547","https://openalex.org/W2295559484","https://openalex.org/W2915062925","https://openalex.org/W1141215409","https://openalex.org/W2603144157","https://openalex.org/W7099002927"],"abstract_inverted_index":{"Abstract.":[0],"This":[1,61],"report":[2],"explains":[3],"our":[4,141,178,190],"plagiarism":[5,129,153,182],"detection":[6,130,183,216],"method":[7,193],"using":[8,45],"fuzzy":[9,67,99,191],"semantic-based":[10,192],"string":[11],"similarity":[12,70,100],"approach.":[13],"The":[14,106,155],"algorithm":[15,179],"was":[16],"developed":[17],"through":[18],"four":[19],"main":[20],"stages.":[21],"First":[22],"is":[23,34,109,162,210],"pre-processing":[24],"which":[25],"includes":[26],"tokenisation,":[27],"stemming":[28],"and":[29,47,81,218],"stop":[30],"words":[31],"removing.":[32],"Second":[33],"retrieving":[35],"a":[36,98,103],"list":[37],"of":[38,66,69,140,151,198],"candidate":[39,59],"documents":[40,51],"for":[41,77,83,127,214],"each":[42],"suspicious":[43],"document":[44],"shingling":[46],"Jaccard":[48],"coefficient.":[49],"Suspicious":[50],"are":[52,89,114,143],"then":[53],"compared":[54],"sentence-wise":[55],"with":[56],"the":[57,64,152,175,228],"associated":[58],"documents.":[60],"stage":[62,230],"entails":[63],"computation":[65],"degree":[68],"that":[71,136,177],"ranges":[72],"between":[73],"two":[74],"edges:":[75],"0":[76],"completely":[78],"different":[79],"sentences":[80,88,113],"1":[82,236],"exactly":[84],"identical":[85],"sentences.":[86],"Two":[87],"marked":[90],"as":[91],"similar":[92],"(i.e.":[93],"plagiarised)":[94],"if":[95],"they":[96],"gain":[97,232],"score":[101],"above":[102],"certain":[104],"threshold.":[105],"last":[107],"step":[108],"post-processing":[110,229],"whereby":[111],"consecutive":[112],"joined":[115],"to":[116,174,211,226,231],"form":[117],"single":[118],"paragraphs/sections.":[119],"Our":[120,207],"performance":[121,156],"measures":[122,157],"on":[123,158],"PAN\u201909":[124],"training":[125],"corpus":[126],"external":[128,181],"task":[131],"(recall=0.3097,":[132],"precision=0.5424,":[133],"granularity=7.8867)":[134],"indicates":[135],"about":[137],"54":[138],"%":[139,150],"detections":[142],"correct":[144],"while":[145],"we":[146,224],"detect":[147,195],"only":[148],"30":[149],"cases.":[154],"PAN\u201910":[159],"test":[160],"collection":[161],"less":[163,219],"(recall":[164],"=":[165,168,171],"0.1259,":[166],"precision":[167],"0.5761,":[169],"granularity":[170],"3.5828),":[172],"due":[173],"fact":[176],"handles":[180],"but":[184],"neither":[185],"intrinsic":[186],"nor":[187],"cross-lingual.":[188],"Although":[189],"can":[194],"some":[196],"means":[197],"obfuscation,":[199],"it":[200,213],"might":[201],"not":[202],"work":[203,209],"at":[204],"all":[205],"levels.":[206],"future":[208],"improve":[212],"more":[215,233],"efficiency":[217],"time":[220],"complexity.":[221],"In":[222],"particular,":[223],"need":[225],"advance":[227],"ideal":[234],"granularity.":[235]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":6},{"year":2018,"cited_by_count":5},{"year":2017,"cited_by_count":9},{"year":2016,"cited_by_count":6},{"year":2015,"cited_by_count":7},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":5},{"year":2012,"cited_by_count":5}],"updated_date":"2026-09-22T06:50:58.402377","created_date":"2016-06-24T00:00:00"}