{"id":"https://openalex.org/W3038174874","doi":"https://doi.org/10.1108/dta-09-2019-0163","title":"Entity deduplication in big data graphs for scholarly communication","display_name":"Entity deduplication in big data graphs for scholarly communication","publication_year":2020,"publication_date":"2020-06-26","ids":{"openalex":"https://openalex.org/W3038174874","doi":"https://doi.org/10.1108/dta-09-2019-0163","mag":"3038174874"},"language":"en","primary_location":{"id":"doi:10.1108/dta-09-2019-0163","is_oa":true,"landing_page_url":"https://doi.org/10.1108/dta-09-2019-0163","pdf_url":"https://www.emerald.com/insight/content/doi/10.1108/DTA-09-2019-0163/full/pdf?title=entity-deduplication-in-big-data-graphs-for-scholarly-communication","source":{"id":"https://openalex.org/S4210171756","display_name":"Data Technologies and Applications","issn_l":"2514-9288","issn":["2514-9288","2514-9318"],"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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Data Technologies and Applications","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://www.emerald.com/insight/content/doi/10.1108/DTA-09-2019-0163/full/pdf?title=entity-deduplication-in-big-data-graphs-for-scholarly-communication","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5087882533","display_name":"Paolo Manghi","orcid":"https://orcid.org/0000-0001-7291-3210"},"institutions":[{"id":"https://openalex.org/I122991210","display_name":"Istituto di Scienza e Tecnologie dell'Informazione \"Alessandro Faedo\"","ror":"https://ror.org/05kacka20","country_code":"IT","type":"facility","lineage":["https://openalex.org/I122991210","https://openalex.org/I4210155236"]},{"id":"https://openalex.org/I4210155236","display_name":"National Research Council","ror":"https://ror.org/04zaypm56","country_code":"IT","type":"nonprofit","lineage":["https://openalex.org/I4210155236"]}],"countries":["IT"],"is_corresponding":true,"raw_author_name":"Paolo Manghi","raw_affiliation_strings":["Istituto di Scienza e Tecnologie dell'Informazione, National Research Council, Pisa, Italy"],"affiliations":[{"raw_affiliation_string":"Istituto di Scienza e Tecnologie dell'Informazione, National Research Council, Pisa, Italy","institution_ids":["https://openalex.org/I122991210","https://openalex.org/I4210155236"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029247934","display_name":"Claudio Atzori","orcid":"https://orcid.org/0000-0001-9613-6639"},"institutions":[{"id":"https://openalex.org/I122991210","display_name":"Istituto di Scienza e Tecnologie dell'Informazione \"Alessandro Faedo\"","ror":"https://ror.org/05kacka20","country_code":"IT","type":"facility","lineage":["https://openalex.org/I122991210","https://openalex.org/I4210155236"]},{"id":"https://openalex.org/I4210155236","display_name":"National Research Council","ror":"https://ror.org/04zaypm56","country_code":"IT","type":"nonprofit","lineage":["https://openalex.org/I4210155236"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Claudio Atzori","raw_affiliation_strings":["Istituto di Scienza e Tecnologie dell'Informazione, National Research Council, Pisa, Italy"],"affiliations":[{"raw_affiliation_string":"Istituto di Scienza e Tecnologie dell'Informazione, National Research Council, Pisa, Italy","institution_ids":["https://openalex.org/I122991210","https://openalex.org/I4210155236"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043605025","display_name":"Michele De Bonis","orcid":"https://orcid.org/0000-0003-2347-6012"},"institutions":[{"id":"https://openalex.org/I122991210","display_name":"Istituto di Scienza e Tecnologie dell'Informazione \"Alessandro Faedo\"","ror":"https://ror.org/05kacka20","country_code":"IT","type":"facility","lineage":["https://openalex.org/I122991210","https://openalex.org/I4210155236"]},{"id":"https://openalex.org/I4210155236","display_name":"National Research Council","ror":"https://ror.org/04zaypm56","country_code":"IT","type":"nonprofit","lineage":["https://openalex.org/I4210155236"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Michele De Bonis","raw_affiliation_strings":["Istituto di Scienza e Tecnologie dell'Informazione, National Research Council, Pisa, Italy"],"affiliations":[{"raw_affiliation_string":"Istituto di Scienza e Tecnologie dell'Informazione, National Research Council, Pisa, Italy","institution_ids":["https://openalex.org/I122991210","https://openalex.org/I4210155236"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5078026154","display_name":"Alessia Bardi","orcid":"https://orcid.org/0000-0002-1112-1292"},"institutions":[{"id":"https://openalex.org/I122991210","display_name":"Istituto di Scienza e Tecnologie dell'Informazione \"Alessandro Faedo\"","ror":"https://ror.org/05kacka20","country_code":"IT","type":"facility","lineage":["https://openalex.org/I122991210","https://openalex.org/I4210155236"]},{"id":"https://openalex.org/I4210155236","display_name":"National Research Council","ror":"https://ror.org/04zaypm56","country_code":"IT","type":"nonprofit","lineage":["https://openalex.org/I4210155236"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Alessia Bardi","raw_affiliation_strings":["Istituto di Scienza e Tecnologie dell'Informazione, National Research Council, Pisa, Italy"],"affiliations":[{"raw_affiliation_string":"Istituto di Scienza e Tecnologie dell'Informazione, National Research Council, Pisa, Italy","institution_ids":["https://openalex.org/I122991210","https://openalex.org/I4210155236"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5087882533"],"corresponding_institution_ids":["https://openalex.org/I122991210","https://openalex.org/I4210155236"],"apc_list":null,"apc_paid":null,"fwci":1.3,"has_fulltext":true,"cited_by_count":10,"citation_normalized_percentile":{"value":0.8236271,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":97},"biblio":{"volume":"54","issue":"4","first_page":"409","last_page":"435"},"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/T10215","display_name":"Semantic Web and Ontologies","score":0.9696000218391418,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9605000019073486,"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/data-deduplication","display_name":"Data deduplication","score":0.8898975253105164},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8308017253875732},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.7701507806777954},{"id":"https://openalex.org/keywords/workflow","display_name":"Workflow","score":0.6799763441085815},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.5595730543136597},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.46328654885292053},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.41289791464805603},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.40801113843917847},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.2964388132095337},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.28197816014289856},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.2726172208786011}],"concepts":[{"id":"https://openalex.org/C32587265","wikidata":"https://www.wikidata.org/wiki/Q1182260","display_name":"Data deduplication","level":2,"score":0.8898975253105164},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8308017253875732},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.7701507806777954},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.6799763441085815},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.5595730543136597},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.46328654885292053},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.41289791464805603},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.40801113843917847},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.2964388132095337},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.28197816014289856},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2726172208786011}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1108/dta-09-2019-0163","is_oa":true,"landing_page_url":"https://doi.org/10.1108/dta-09-2019-0163","pdf_url":"https://www.emerald.com/insight/content/doi/10.1108/DTA-09-2019-0163/full/pdf?title=entity-deduplication-in-big-data-graphs-for-scholarly-communication","source":{"id":"https://openalex.org/S4210171756","display_name":"Data Technologies and Applications","issn_l":"2514-9288","issn":["2514-9288","2514-9318"],"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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Data Technologies and Applications","raw_type":"journal-article"},{"id":"pmh:oai:dnet:people______::b6441082805923f03cffc4fb512d2e72","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S7407055261","display_name":"ISTI Open Portal","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":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"DATA TECHNOLOGIES AND APPLICATIONS, vol. 54, pp. 409-435","raw_type":"Journal article"}],"best_oa_location":{"id":"doi:10.1108/dta-09-2019-0163","is_oa":true,"landing_page_url":"https://doi.org/10.1108/dta-09-2019-0163","pdf_url":"https://www.emerald.com/insight/content/doi/10.1108/DTA-09-2019-0163/full/pdf?title=entity-deduplication-in-big-data-graphs-for-scholarly-communication","source":{"id":"https://openalex.org/S4210171756","display_name":"Data Technologies and Applications","issn_l":"2514-9288","issn":["2514-9288","2514-9318"],"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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Data Technologies and Applications","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure","score":0.6200000047683716}],"awards":[{"id":"https://openalex.org/G1973319722","display_name":null,"funder_award_id":"777541","funder_id":"https://openalex.org/F4320332999","funder_display_name":"Horizon 2020 Framework Programme"}],"funders":[{"id":"https://openalex.org/F4320332999","display_name":"Horizon 2020 Framework Programme","ror":"https://ror.org/00k4n6c32"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3038174874.pdf","grobid_xml":"https://content.openalex.org/works/W3038174874.grobid-xml"},"referenced_works_count":31,"referenced_works":["https://openalex.org/W509898","https://openalex.org/W9784843","https://openalex.org/W61311756","https://openalex.org/W92903312","https://openalex.org/W198971967","https://openalex.org/W758106613","https://openalex.org/W1567659667","https://openalex.org/W1942676048","https://openalex.org/W1981420413","https://openalex.org/W1981590391","https://openalex.org/W1997927541","https://openalex.org/W2020302654","https://openalex.org/W2025151282","https://openalex.org/W2036216970","https://openalex.org/W2044936152","https://openalex.org/W2073471108","https://openalex.org/W2079971532","https://openalex.org/W2118791211","https://openalex.org/W2138591041","https://openalex.org/W2164625277","https://openalex.org/W2173213060","https://openalex.org/W2182703380","https://openalex.org/W2570427954","https://openalex.org/W2624304035","https://openalex.org/W2791720749","https://openalex.org/W2808973857","https://openalex.org/W2895787212","https://openalex.org/W2911151835","https://openalex.org/W4245044315","https://openalex.org/W6893191166","https://openalex.org/W6912503356"],"related_works":["https://openalex.org/W3144870715","https://openalex.org/W3142319788","https://openalex.org/W2587188779","https://openalex.org/W3132870970","https://openalex.org/W2943088381","https://openalex.org/W4296125805","https://openalex.org/W4385804830","https://openalex.org/W2144348063","https://openalex.org/W2074021203","https://openalex.org/W12581771"],"abstract_inverted_index":{"Purpose":[0],"Several":[1],"online":[2],"services":[3],"offer":[4],"functionalities":[5,157],"to":[6,47,90,122,159,191],"access":[7,39],"information":[8,128],"from":[9,42,72,181],"\u201cbig":[10],"research":[11],"graphs\u201d":[12],"(e.g.":[13],"Google":[14],"Scholar,":[15],"OpenAIRE,":[16],"Microsoft":[17],"Academic":[18],"Graph),":[19],"which":[20,240],"correlate":[21],"scholarly/scientific":[22],"communication":[23],"entities":[24],"such":[25],"as":[26,64,138],"publications,":[27],"authors,":[28],"datasets,":[29],"organizations,":[30],"projects,":[31],"funders,":[32],"etc.":[33],"Depending":[34],"on":[35,94,245],"the":[36,48,143,156,203,207,217,231,235,248],"target":[37],"users,":[38],"can":[40,119],"vary":[41],"search":[43],"and":[44,54,69,83,100,147,184,188,213,253],"browse":[45],"content":[46],"consumption":[49],"of":[50,56,66,78,150,179,230,234,247],"statistics":[51],"for":[52,186,216],"monitoring":[53],"provision":[55],"feedback.":[57],"Such":[58],"graphs":[59,79],"are":[60,88],"populated":[61],"over":[62,125,166],"time":[63],"aggregations":[65],"multiple":[67],"sources":[68],"therefore":[70,102],"suffer":[71],"major":[73],"entity-duplication":[74],"problems.":[75],"Although":[76],"deduplication":[77,124,164,218],"is":[80,202,227],"a":[81,139,161,167],"known":[82],"actual":[84],"problem,":[85],"existing":[86],"solutions":[87],"dedicated":[89],"specific":[91],"scenarios,":[92],"operate":[93],"flat":[95],"collections,":[96],"local":[97],"topology-drive":[98],"challenges":[99],"cannot":[101],"be":[103,120],"re-used":[104],"in":[105,206],"other":[106],"contexts.":[107],"Design/methodology/approach":[108],"This":[109],"work":[110],"presents":[111,132],"GDup,":[112],"an":[113,193,211],"integrated,":[114],"scalable,":[115],"general-purpose":[116,214],"system":[117,146,172,205],"that":[118,209],"customized":[121],"address":[123],"arbitrary":[126],"large":[127],"graphs.":[129],"The":[130,171],"paper":[131],"its":[133,136],"high-level":[134],"architecture,":[135],"implementation":[137],"service":[140],"used":[141],"within":[142],"OpenAIRE":[144,236],"infrastructure":[145,237],"reports":[148],"numbers":[149],"real-case":[151],"experiments.":[152],"Findings":[153],"GDup":[154,201,226],"provides":[155],"required":[158],"deliver":[160],"fully-fledged":[162],"entity":[163],"workflow":[165],"generic":[168],"input":[169],"graph.":[170,196],"offers":[173,210],"out-of-the-box":[174],"Ground":[175],"Truth":[176],"management,":[177],"acquisition":[178],"feedback":[180],"data":[182,223],"curators":[183],"algorithms":[185],"identifying":[187],"merging":[189],"duplicates,":[190],"obtain":[192],"output":[194],"disambiguated":[195],"Originality/value":[197],"To":[198],"our":[199],"knowledge":[200],"only":[204],"literature":[208],"integrated":[212],"solution":[215],"graphs,":[219],"while":[220],"targeting":[221],"big":[222],"scalability":[224],"issues.":[225],"today":[228],"one":[229],"key":[232],"modules":[233],"production":[238],"system,":[239],"monitors":[241],"Open":[242],"Science":[243],"trends":[244],"behalf":[246],"European":[249],"Commission,":[250],"National":[251],"funders":[252],"institutions.":[254]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":3}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}
