{"id":"https://openalex.org/W2287704737","doi":"https://doi.org/10.1108/prog-02-2015-0021","title":"De-duplicating a large crowd-sourced catalogue of bibliographic records","display_name":"De-duplicating a large crowd-sourced catalogue of bibliographic records","publication_year":2016,"publication_date":"2016-03-21","ids":{"openalex":"https://openalex.org/W2287704737","doi":"https://doi.org/10.1108/prog-02-2015-0021","mag":"2287704737"},"language":"en","primary_location":{"id":"doi:10.1108/prog-02-2015-0021","is_oa":false,"landing_page_url":"https://doi.org/10.1108/prog-02-2015-0021","pdf_url":null,"source":{"id":"https://openalex.org/S152623109","display_name":"Program electronic library and information systems","issn_l":"0033-0337","issn":["0033-0337","1758-7301"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319811","host_organization_name":"Emerald Publishing Limited","host_organization_lineage":["https://openalex.org/P4310319811"],"host_organization_lineage_names":["Emerald Publishing Limited"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Program","raw_type":"journal-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/A5009860784","display_name":"Ilija Suba\u0161i\u0107","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Ilija Subasic","raw_affiliation_strings":["Gluru, London, UK"],"affiliations":[{"raw_affiliation_string":"Gluru, London, UK","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008319452","display_name":"Neboj\u0161a Gvozdenovi\u0107","orcid":"https://orcid.org/0000-0002-9230-9528"},"institutions":[{"id":"https://openalex.org/I170726198","display_name":"University of Novi Sad","ror":"https://ror.org/00xa57a59","country_code":"RS","type":"education","lineage":["https://openalex.org/I170726198"]}],"countries":["RS"],"is_corresponding":false,"raw_author_name":"Nebojsa Gvozdenovic","raw_affiliation_strings":["University of Novi Sad, Novi Sad, Serbia"],"affiliations":[{"raw_affiliation_string":"University of Novi Sad, Novi Sad, Serbia","institution_ids":["https://openalex.org/I170726198"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5009492024","display_name":"Kris Jack","orcid":"https://orcid.org/0000-0002-6740-4136"},"institutions":[{"id":"https://openalex.org/I4210106863","display_name":"Mendeley (United Kingdom)","ror":"https://ror.org/01t2a8a42","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210106863"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Kris Jack","raw_affiliation_strings":["Mendeley Ltd, London, UK"],"affiliations":[{"raw_affiliation_string":"Mendeley Ltd, London, UK","institution_ids":["https://openalex.org/I4210106863"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5009860784"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.0136481,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":"50","issue":"2","first_page":"138","last_page":"156"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11106","display_name":"Data Management and Algorithms","score":0.9922000169754028,"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/T11819","display_name":"Data-Driven Disease Surveillance","score":0.9905999898910522,"subfield":{"id":"https://openalex.org/subfields/2713","display_name":"Epidemiology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.711543083190918},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.6934905648231506},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.666752815246582},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.6374020576477051},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5642129182815552},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5236225724220276},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.489406019449234},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.45345398783683777},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.2548145055770874},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.22743433713912964},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.2093435525894165},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.10541906952857971},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.08345413208007812}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.711543083190918},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6934905648231506},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.666752815246582},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.6374020576477051},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5642129182815552},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5236225724220276},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.489406019449234},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.45345398783683777},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2548145055770874},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.22743433713912964},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.2093435525894165},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.10541906952857971},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.08345413208007812},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1108/prog-02-2015-0021","is_oa":false,"landing_page_url":"https://doi.org/10.1108/prog-02-2015-0021","pdf_url":null,"source":{"id":"https://openalex.org/S152623109","display_name":"Program electronic library and information systems","issn_l":"0033-0337","issn":["0033-0337","1758-7301"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319811","host_organization_name":"Emerald Publishing Limited","host_organization_lineage":["https://openalex.org/P4310319811"],"host_organization_lineage_names":["Emerald Publishing Limited"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Program","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9","score":0.5199999809265137}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W839173409","https://openalex.org/W1495061682","https://openalex.org/W1547612978","https://openalex.org/W1566413063","https://openalex.org/W1582775886","https://openalex.org/W1646278814","https://openalex.org/W1647671624","https://openalex.org/W1978394996","https://openalex.org/W1981590391","https://openalex.org/W1995099886","https://openalex.org/W2012833704","https://openalex.org/W2026265322","https://openalex.org/W2036216970","https://openalex.org/W2062028408","https://openalex.org/W2067566391","https://openalex.org/W2076915037","https://openalex.org/W2079971532","https://openalex.org/W2108991785","https://openalex.org/W2120058970","https://openalex.org/W2128600649","https://openalex.org/W2132069633","https://openalex.org/W2132399973","https://openalex.org/W2148885851","https://openalex.org/W2152526152","https://openalex.org/W2157236054","https://openalex.org/W2163972006","https://openalex.org/W2164456230","https://openalex.org/W2171574281","https://openalex.org/W2250682757","https://openalex.org/W2394984226","https://openalex.org/W3146259567","https://openalex.org/W4242744113","https://openalex.org/W6657299637","https://openalex.org/W6679663036","https://openalex.org/W6684499520","https://openalex.org/W6691937954"],"related_works":["https://openalex.org/W2378211422","https://openalex.org/W4321353415","https://openalex.org/W2130974462","https://openalex.org/W972276598","https://openalex.org/W2086519370","https://openalex.org/W2028665553","https://openalex.org/W2087343574","https://openalex.org/W2535915176","https://openalex.org/W2105860728","https://openalex.org/W4287657826"],"abstract_inverted_index":{"Purpose":[0],"\u2013":[1,47,98,167,194,227],"The":[2,48,64,99,116,285,305],"purpose":[3],"of":[4,17,33,77,94,125,161,177,180,218,245,254],"this":[5,172,199],"paper":[6,173,200],"is":[7,142,249],"to":[8,28,73,88,121,144,157,174,230,281],"describe":[9],"a":[10,15,23,41,81,132,202,208,221,242],"large-scale":[11,209],"algorithm":[12,52,79,129],"for":[13,36,149,206,236,251,290,302,321],"generating":[14,207],"catalogue":[16,190,211],"scientific":[18],"publication":[19],"records":[20,219,256],"(citations)":[21],"from":[22],"crowd-sourced":[24],"data,":[25],"demonstrate":[26,318],"how":[27,120,280],"learn":[29],"an":[30,109],"optimal":[31],"combination":[32],"distance":[34],"metrics":[35],"duplicate":[37,43,103,114,150,183,252,276,291,294,314],"detection":[38,104,253,292],"and":[39,53,80,92,152,185,223,278,293,296,317],"introduce":[40],"parallel":[42],"clustering":[44,295,300,315],"algorithm.":[45,96],"Design/methodology/approach":[46],"authors":[49,65,100,117,137,240,270,286],"developed":[50,235],"the":[51,61,75,90,123,136,140,145,178,239,269,298,308,313],"compared":[54],"it":[55,154],"with":[56,159,216,273],"state-of-the":[57,146],"art":[58,147],"systems":[59,148],"tackling":[60],"same":[62],"problem.":[63],"used":[66],"benchmark":[67],"data":[68,71,83,163],"sets":[69],"(3k":[70],"points)":[72],"test":[74,89],"effectiveness":[76],"our":[78,95],"real-life":[82,210],"(":[84],">":[85],"90":[86],"million)":[87],"efficiency":[91,124],"scalability":[93],"Findings":[97],"show":[101,119],"that":[102,139,153,214,248],"can":[105,155,170,197],"be":[106],"improved":[107],"by":[108,130,257,311],"additional":[110],"step":[111,316],"we":[112],"call":[113],"clustering.":[115,304],"also":[118],"improve":[122],"map/reduce":[126],"similarity":[127,232,246,325],"calculation":[128,233,247],"introducing":[131],"sampling":[133],"step.":[134],"Finally,":[135],"find":[138],"system":[141,213],"comparable":[143],"detection,":[151,184,277],"scale":[156],"deal":[158],"hundreds":[160],"million":[162],"points.":[164],"Research":[165],"limitations/implications":[166],"Academic":[168],"researchers":[169],"use":[171,198,203,297],"understand":[175],"some":[176],"issues":[179],"transitivity":[181],"in":[182,220],"its":[186],"effects":[187],"on":[188,263],"digital":[189],"generations.":[191],"Practical":[192],"implications":[193],"Industry":[195],"practitioners":[196],"as":[201],"case":[204],"study":[205],"generation":[212],"deals":[215],"millions":[217],"scalable":[222],"efficient":[224],"way.":[225],"Originality/value":[226],"In":[228,267],"contrast":[229],"other":[231],"algorithms":[234,289],"m/r":[237,324],"frameworks":[238],"present":[241],"specific":[243],"variant":[244],"optimized":[250],"bibliographic":[255],"extending":[258],"previously":[259],"proposed":[260],"e-algorithm":[261],"based":[262],"inverted":[264],"index":[265],"creation.":[266],"addition,":[268],"are":[271],"concerned":[272],"more":[274],"than":[275],"investigate":[279],"group":[282],"detected":[283],"duplicates.":[284],"develop":[287],"distinct":[288],"canopy":[299],"idea":[301],"multi-pass":[303],"work":[306],"extends":[307],"current":[309],"state-of-the-art":[310],"including":[312],"new":[319],"strategies":[320],"speeding":[322],"up":[323],"calculations.":[326]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}