{"id":"https://openalex.org/W4400604911","doi":"https://doi.org/10.5220/0012718000003756","title":"BeRTo: An Efficient Spark-Based Tool for Linking Business Registries in Big Data Environments","display_name":"BeRTo: An Efficient Spark-Based Tool for Linking Business Registries in Big Data Environments","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4400604911","doi":"https://doi.org/10.5220/0012718000003756"},"language":"en","primary_location":{"id":"doi:10.5220/0012718000003756","is_oa":true,"landing_page_url":"https://doi.org/10.5220/0012718000003756","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 13th International Conference on Data Science, Technology and Applications","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.5220/0012718000003756","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5103815839","display_name":"Andrea Colombo","orcid":null},"institutions":[{"id":"https://openalex.org/I93860229","display_name":"Politecnico di Milano","ror":"https://ror.org/01nffqt88","country_code":"IT","type":"education","lineage":["https://openalex.org/I93860229"]}],"countries":["IT"],"is_corresponding":true,"raw_author_name":"Andrea Colombo","raw_affiliation_strings":["Dipartimento di Elettronica, Informazione e Bioingegeneria, Politecnico di Milano, Via G. Ponzio 34, Milan, Italy","Dipartimento di Elettronica, Informazione e Bioingegeneria, Politecnico di Milano, Via G. Ponzio 34, Milan, Italy, --- Select a Country ---"],"affiliations":[{"raw_affiliation_string":"Dipartimento di Elettronica, Informazione e Bioingegeneria, Politecnico di Milano, Via G. Ponzio 34, Milan, Italy","institution_ids":["https://openalex.org/I93860229"]},{"raw_affiliation_string":"Dipartimento di Elettronica, Informazione e Bioingegeneria, Politecnico di Milano, Via G. Ponzio 34, Milan, Italy, --- Select a Country ---","institution_ids":["https://openalex.org/I93860229"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5092006341","display_name":"Francesco Invernici","orcid":"https://orcid.org/0009-0002-5423-6978"},"institutions":[{"id":"https://openalex.org/I93860229","display_name":"Politecnico di Milano","ror":"https://ror.org/01nffqt88","country_code":"IT","type":"education","lineage":["https://openalex.org/I93860229"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Francesco Invernici","raw_affiliation_strings":["Dipartimento di Elettronica, Informazione e Bioingegeneria, Politecnico di Milano, Via G. Ponzio 34, Milan, Italy","Dipartimento di Elettronica, Informazione e Bioingegeneria, Politecnico di Milano, Via G. Ponzio 34, Milan, Italy, --- Select a Country ---"],"affiliations":[{"raw_affiliation_string":"Dipartimento di Elettronica, Informazione e Bioingegeneria, Politecnico di Milano, Via G. Ponzio 34, Milan, Italy","institution_ids":["https://openalex.org/I93860229"]},{"raw_affiliation_string":"Dipartimento di Elettronica, Informazione e Bioingegeneria, Politecnico di Milano, Via G. Ponzio 34, Milan, Italy, --- Select a Country ---","institution_ids":["https://openalex.org/I93860229"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5103815839"],"corresponding_institution_ids":["https://openalex.org/I93860229"],"apc_list":null,"apc_paid":null,"fwci":0.7931,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.76847203,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"259","last_page":"268"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.9405999779701233,"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"}},"topics":[{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.9405999779701233,"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/T11478","display_name":"Caching and Content Delivery","score":0.9230999946594238,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T10742","display_name":"Peer-to-Peer Network Technologies","score":0.9120000004768372,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/spark","display_name":"SPARK (programming language)","score":0.781883955001831},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.6600050330162048},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5403476357460022},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.41387850046157837},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.11592715978622437}],"concepts":[{"id":"https://openalex.org/C2781215313","wikidata":"https://www.wikidata.org/wiki/Q3493345","display_name":"SPARK (programming language)","level":2,"score":0.781883955001831},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.6600050330162048},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5403476357460022},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.41387850046157837},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.11592715978622437},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.5220/0012718000003756","is_oa":true,"landing_page_url":"https://doi.org/10.5220/0012718000003756","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 13th International Conference on Data Science, Technology and Applications","raw_type":"proceedings-article"},{"id":"pmh:oai:re.public.polimi.it:11311/1269602","is_oa":true,"landing_page_url":"https://hdl.handle.net/11311/1269602","pdf_url":"https://re.public.polimi.it/bitstream/11311/1269602/1/DATA_2024_33_CR.pdf","source":{"id":"https://openalex.org/S4306400312","display_name":"Virtual Community of Pathological Anatomy (University of Castilla La Mancha)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I79189158","host_organization_name":"University of Castilla-La Mancha","host_organization_lineage":["https://openalex.org/I79189158"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"doi:10.5220/0012718000003756","is_oa":true,"landing_page_url":"https://doi.org/10.5220/0012718000003756","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 13th International Conference on Data Science, Technology and Applications","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9","score":0.46000000834465027}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2766461310","https://openalex.org/W4247566972","https://openalex.org/W4388692845","https://openalex.org/W3202731209","https://openalex.org/W3211874991","https://openalex.org/W4322629366","https://openalex.org/W2808989540","https://openalex.org/W2397053934","https://openalex.org/W1039292361","https://openalex.org/W2551093110"],"abstract_inverted_index":{"Linking":[0],"entities":[1,17],"from":[2,99],"different":[3],"datasets":[4],"is":[5],"a":[6,64,75,84,93,105,117,145,173],"crucial":[7],"task":[8],"for":[9],"the":[10,27,43,46,60,67,70,113,163,169,183],"success":[11,68],"of":[12,69,95,115,120,150],"modern":[13,88],"businesses.":[14],"However,":[15],"aligning":[16],"becomes":[18],"challenging":[19],"as":[20,35,155],"common":[21],"identifiers":[22],"might":[23],"be":[24],"missing.":[25],"Therefore,":[26],"process":[28],"should":[29],"rely":[30],"on":[31,77,160,194],"string-based":[32],"attributes,":[33],"such":[34],"names":[36],"or":[37,196],"addresses,":[38],"thus":[39],"harming":[40],"precision":[41,151],"in":[42,66,87,138,148,168],"matching.":[44],"At":[45],"same":[47,170],"time,":[48],"powerful":[49],"general-purpose":[50],"record":[51,107],"linkage":[52,108],"tools":[53],"require":[54],"users":[55,179],"to":[56,143,181,192],"clean":[57],"and":[58,74,130,165,186],"pre-process":[59],"initial":[61],"data,":[62],"introducing":[63],"bottleneck":[65],"data":[71,90,96,121,185],"integration":[72],"activity":[73],"burden":[76],"actual":[78],"users.":[79],"Furthermore,":[80],"scalability":[81],"has":[82,157],"become":[83],"relevant":[85],"issue":[86],"big":[89],"environments,":[91],"where":[92],"lot":[94],"flows":[97],"daily":[98],"external":[100],"sources.":[101],"This":[102],"work":[103],"presents":[104],"novel":[106],"tool,":[109],"BeRTo,":[110],"that":[111,177],"addresses":[112],"problem":[114],"linking":[116],"specific":[118],"type":[119],"source,":[122],"i.e.,":[123],"business":[124],"registries,":[125],"containing":[126],"information":[127],"about":[128],"companies":[129],"corporations.":[131],"While":[132],"being":[133],"domain-specific":[134],"harms":[135],"its":[136],"usability":[137],"other":[139],"contexts,":[140],"it":[141,156],"manages":[142],"reach":[144],"new":[146],"frontier":[147],"terms":[149],"but":[152],"also":[153],"scalability,":[154],"been":[158],"built":[159],"Spark.":[161],"Integrating":[162],"pre-processing":[164],"cleaning":[166],"steps":[167],"tool":[171],"creates":[172],"user-friendly":[174],"end-to-end":[175],"pipeline":[176],"requires":[178],"only":[180],"input":[182],"raw":[184],"set":[187],"their":[188],"preferred":[189],"configuration,":[190],"allowing":[191],"focus":[193],"recall":[195],"precision.":[197]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}