{"id":"https://openalex.org/W2798299346","doi":"https://doi.org/10.1145/3183713.3183757","title":"Big Data Linkage for Product Specification Pages","display_name":"Big Data Linkage for Product Specification Pages","publication_year":2018,"publication_date":"2018-05-25","ids":{"openalex":"https://openalex.org/W2798299346","doi":"https://doi.org/10.1145/3183713.3183757","mag":"2798299346"},"language":"en","primary_location":{"id":"doi:10.1145/3183713.3183757","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3183713.3183757","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2018 International Conference on Management of Data","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/A5028754236","display_name":"Disheng Qiu","orcid":null},"institutions":[{"id":"https://openalex.org/I119003972","display_name":"Roma Tre University","ror":"https://ror.org/05vf0dg29","country_code":"IT","type":"education","lineage":["https://openalex.org/I119003972"]}],"countries":["IT"],"is_corresponding":true,"raw_author_name":"Disheng Qiu","raw_affiliation_strings":["Universit\u00e0 Roma Tre, Roma, Italy"],"affiliations":[{"raw_affiliation_string":"Universit\u00e0 Roma Tre, Roma, Italy","institution_ids":["https://openalex.org/I119003972"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000683692","display_name":"Luciano Barbosa","orcid":"https://orcid.org/0000-0002-6858-4773"},"institutions":[{"id":"https://openalex.org/I25112270","display_name":"Universidade Federal de Pernambuco","ror":"https://ror.org/047908t24","country_code":"BR","type":"education","lineage":["https://openalex.org/I25112270"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Luciano Barbosa","raw_affiliation_strings":["Universidade Federal de Pernambuco, Pernabuco, Brazil"],"affiliations":[{"raw_affiliation_string":"Universidade Federal de Pernambuco, Pernabuco, Brazil","institution_ids":["https://openalex.org/I25112270"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030700727","display_name":"Valter Crescenzi","orcid":null},"institutions":[{"id":"https://openalex.org/I119003972","display_name":"Roma Tre University","ror":"https://ror.org/05vf0dg29","country_code":"IT","type":"education","lineage":["https://openalex.org/I119003972"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Valter Crescenzi","raw_affiliation_strings":["Universit\u00e0 Roma Tre, Roma, Italy"],"affiliations":[{"raw_affiliation_string":"Universit\u00e0 Roma Tre, Roma, Italy","institution_ids":["https://openalex.org/I119003972"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022736687","display_name":"Paolo Merialdo","orcid":"https://orcid.org/0000-0002-3852-8092"},"institutions":[{"id":"https://openalex.org/I119003972","display_name":"Roma Tre University","ror":"https://ror.org/05vf0dg29","country_code":"IT","type":"education","lineage":["https://openalex.org/I119003972"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Paolo Merialdo","raw_affiliation_strings":["Universit\u00e0 Roma Tre, Roma, Italy"],"affiliations":[{"raw_affiliation_string":"Universit\u00e0 Roma Tre, Roma, Italy","institution_ids":["https://openalex.org/I119003972"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088315797","display_name":"Divesh Srivastava","orcid":"https://orcid.org/0000-0002-7609-9217"},"institutions":[{"id":"https://openalex.org/I1283103587","display_name":"AT&T (United States)","ror":"https://ror.org/02bbd5539","country_code":"US","type":"company","lineage":["https://openalex.org/I1283103587"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Divesh Srivastava","raw_affiliation_strings":["AT&T Labs - Research, Bedminster, NJ, USA"],"affiliations":[{"raw_affiliation_string":"AT&T Labs - Research, Bedminster, NJ, USA","institution_ids":["https://openalex.org/I1283103587"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5028754236"],"corresponding_institution_ids":["https://openalex.org/I119003972"],"apc_list":null,"apc_paid":null,"fwci":0.2205,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.57436638,"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":"67","last_page":"81"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9995999932289124,"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":0.9995999932289124,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9984999895095825,"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/T10215","display_name":"Semantic Web and Ontologies","score":0.9929999709129333,"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/linkage","display_name":"Linkage (software)","score":0.778519868850708},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7270420789718628},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.618725061416626},{"id":"https://openalex.org/keywords/product","display_name":"Product (mathematics)","score":0.5382694005966187},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.38208630681037903},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.33311882615089417},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.32117676734924316},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.1636354923248291},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.05735692381858826}],"concepts":[{"id":"https://openalex.org/C31266012","wikidata":"https://www.wikidata.org/wiki/Q6554340","display_name":"Linkage (software)","level":3,"score":0.778519868850708},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7270420789718628},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.618725061416626},{"id":"https://openalex.org/C90673727","wikidata":"https://www.wikidata.org/wiki/Q901718","display_name":"Product (mathematics)","level":2,"score":0.5382694005966187},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.38208630681037903},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.33311882615089417},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.32117676734924316},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.1636354923248291},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.05735692381858826},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3183713.3183757","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3183713.3183757","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2018 International Conference on Management of Data","raw_type":"proceedings-article"},{"id":"pmh:oai:iris.uniroma3.it:11590/338653","is_oa":false,"landing_page_url":"http://hdl.handle.net/11590/338653","pdf_url":null,"source":{"id":"https://openalex.org/S4377196120","display_name":"Iris (Roma Tre University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I119003972","host_organization_name":"Roma Tre University","host_organization_lineage":["https://openalex.org/I119003972"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","score":0.4699999988079071,"id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W155236017","https://openalex.org/W1595854491","https://openalex.org/W1984911948","https://openalex.org/W2002956097","https://openalex.org/W2016753842","https://openalex.org/W2024105308","https://openalex.org/W2031250218","https://openalex.org/W2043437843","https://openalex.org/W2045968013","https://openalex.org/W2092590954","https://openalex.org/W2097002571","https://openalex.org/W2097874932","https://openalex.org/W2101654853","https://openalex.org/W2122865749","https://openalex.org/W2131681506","https://openalex.org/W2138621811","https://openalex.org/W2149364369","https://openalex.org/W2150721933","https://openalex.org/W2158420658","https://openalex.org/W2163072729","https://openalex.org/W2168320385","https://openalex.org/W2169753664","https://openalex.org/W2295639288","https://openalex.org/W2296045323","https://openalex.org/W2501300562","https://openalex.org/W2559870814","https://openalex.org/W2962805116","https://openalex.org/W3099768174"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W2808989540","https://openalex.org/W2617449561","https://openalex.org/W2397053934","https://openalex.org/W1039292361","https://openalex.org/W2767632110","https://openalex.org/W2551093110","https://openalex.org/W2148016376","https://openalex.org/W1996408511","https://openalex.org/W2900330755"],"abstract_inverted_index":{"An":[0],"increasing":[1],"number":[2],"of":[3,10,50,68,99,151,162,165,174,189,191,198,209,220,227],"product":[4,26,56,92,103,138,156,222],"pages":[5,126,190,223],"are":[6],"available":[7,216],"from":[8,224],"thousands":[9,197],"web":[11],"sources,":[12],"each":[13],"page":[14,107],"associated":[15],"with":[16],"a":[17,168,205],"product,":[18],"containing":[19],"its":[20,232],"attributes":[21],"and":[22,123,171,176,185,193,200,230],"one":[23],"or":[24],"more":[25],"identifiers.":[27],"The":[28],"sources":[29,54,64,226],"provide":[30],"overlapping":[31],"information":[32],"about":[33],"the":[34,51,66,69,97,101,106,115,121,133,149,163,172,179,214],"products,":[35],"using":[36,213],"diverse":[37],"schemas,":[38],"making":[39],"web-scale":[40],"integration":[41,71],"extremely":[42],"challenging.":[43],"In":[44],"this":[45,78],"paper,":[46],"we":[47],"take":[48],"advantage":[49,161],"opportunity":[52],"that":[53],"publish":[55],"identifiers":[57,86,124,136,166],"to":[58,83,88,109,128,148,183],"perform":[59,204],"big":[60,152],"data":[61,70,153],"linkage":[62,154],"across":[63,125,137,196],"at":[65,167,178],"beginning":[67],"pipeline,":[72],"before":[73],"schema":[74],"alignment.":[75],"To":[76],"realize":[77],"opportunity,":[79],"several":[80],"challenges":[81],"need":[82,87,127],"be":[84,89,110],"addressed:":[85],"discovered":[90],"on":[91,105,120],"pages,":[93,158],"made":[94,112,130],"difficult":[95,113,131],"by":[96,114,132],"diversity":[98],"identifiers;":[100],"main":[102],"identifier":[104],"needs":[108],"identified,":[111],"many":[116],"related":[117],"products":[118,195],"presented":[119],"page;":[122],"beresolved,":[129],"ambiguity":[134],"between":[135],"categories.":[139],"We":[140,203],"present":[141],"our":[142,210],"RaF":[143,211],"(Redundancy":[144],"as":[145],"Friend)":[146],"solution":[147],"problem":[150],"for":[155],"specification":[157],"which":[159],"takes":[160],"redundancy":[164],"global":[169],"level,":[170,182],"homogeneity":[173],"structure":[175],"semantics":[177],"local":[180],"source":[181],"effectively":[184],"efficiently":[186],"link":[187],"millions":[188],"head":[192,199],"tail":[194,201],"sources.":[202],"thorough":[206],"empirical":[207],"evaluation":[208],"approach":[212],"publicly":[215],"Dexter":[217],"dataset":[218],"consisting":[219],"1.9M":[221],"7.1k":[225],"3.5k":[228],"websites,":[229],"demonstrate":[231],"effectiveness":[233],"in":[234],"practice.":[235]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2019,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}