{"id":"https://openalex.org/W3126190835","doi":"https://doi.org/10.24251/hicss.2021.118","title":"IRIS-DS: A New Approach for Identifiers and References Discovery in Document Stores","display_name":"IRIS-DS: A New Approach for Identifiers and References Discovery in Document Stores","publication_year":2021,"publication_date":"2021-01-01","ids":{"openalex":"https://openalex.org/W3126190835","doi":"https://doi.org/10.24251/hicss.2021.118","mag":"3126190835"},"language":"en","primary_location":{"id":"doi:10.24251/hicss.2021.118","doi":"https://doi.org/10.24251/hicss.2021.118","is_oa":true,"landing_page_url":"https://doi.org/10.24251/hicss.2021.118","pdf_url":"http://scholarspace.manoa.hawaii.edu/bitstream/10125/70730/1/0096.pdf","source":{"id":"https://openalex.org/S4210195248","display_name":"Hawaii International Conference on System Sciences (HICSS)","issn_l":"1530-1605","issn":["1530-1605","2572-6862"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-1","norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"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 Annual Hawaii International Conference on System Sciences","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"http://scholarspace.manoa.hawaii.edu/bitstream/10125/70730/1/0096.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5043291882","display_name":"Manel Souibgui","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I124158823","display_name":"Conservatoire National des Arts et M\u00e9tiers","ror":"https://ror.org/0175hh227","country_code":"FR","type":"education","lineage":["https://openalex.org/I124158823","https://openalex.org/I4210134562"]},{"id":"https://openalex.org/I4210145724","display_name":"Centre d'\u00e9tudes et de recherche en informatique et communications","ror":"https://ror.org/044j5mm75","country_code":"FR","type":"facility","lineage":["https://openalex.org/I124158823","https://openalex.org/I4210134562","https://openalex.org/I4210145724"]},{"id":"https://openalex.org/I63596082","display_name":"Tunis El Manar University","ror":"https://ror.org/029cgt552","country_code":"TN","type":"education","lineage":["https://openalex.org/I63596082"]}],"countries":["FR","TN"],"is_corresponding":false,"raw_author_name":"Manel Souibgui","raw_affiliation_strings":["Conservatoire National des Arts et M\u00e9tiers , CEDRIC-CNAM , France","University of Tunis El Manar , Faculty of Sciences of Tunis , LIPAH , Tunisia","Centre d'\u00e9tudes et de recherche en informatique et communications"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Conservatoire National des Arts et M\u00e9tiers , CEDRIC-CNAM , France","institution_ids":["https://openalex.org/I124158823","https://openalex.org/I4210145724"]},{"raw_affiliation_string":"University of Tunis El Manar , Faculty of Sciences of Tunis , LIPAH , Tunisia","institution_ids":["https://openalex.org/I63596082"]},{"raw_affiliation_string":"Centre d'\u00e9tudes et de recherche en informatique et communications","institution_ids":["https://openalex.org/I4210145724"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049049023","display_name":"Faten Atigui","orcid":"https://orcid.org/0009-0000-1100-5489","observed_orcids":["https://orcid.org/0009-0000-1100-5489"]},"institutions":[{"id":"https://openalex.org/I124158823","display_name":"Conservatoire National des Arts et M\u00e9tiers","ror":"https://ror.org/0175hh227","country_code":"FR","type":"education","lineage":["https://openalex.org/I124158823","https://openalex.org/I4210134562"]},{"id":"https://openalex.org/I4210145724","display_name":"Centre d'\u00e9tudes et de recherche en informatique et communications","ror":"https://ror.org/044j5mm75","country_code":"FR","type":"facility","lineage":["https://openalex.org/I124158823","https://openalex.org/I4210134562","https://openalex.org/I4210145724"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Faten Atigui","raw_affiliation_strings":["Conservatoire National des Arts et M\u00e9tiers , CEDRIC-CNAM , France","CEDRIC. Ing\u00e9nierie des Syst\u00e8mes d'Information et de D\u00e9cision"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Conservatoire National des Arts et M\u00e9tiers , CEDRIC-CNAM , France","institution_ids":["https://openalex.org/I124158823","https://openalex.org/I4210145724"]},{"raw_affiliation_string":"CEDRIC. Ing\u00e9nierie des Syst\u00e8mes d'Information et de D\u00e9cision","institution_ids":["https://openalex.org/I4210145724"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070511935","display_name":"Sadok Ben Yahia","orcid":"https://orcid.org/0000-0001-8939-8948","observed_orcids":["https://orcid.org/0000-0001-8939-8948"]},"institutions":[{"id":"https://openalex.org/I111112146","display_name":"Tallinn University of Technology","ror":"https://ror.org/0443cwa12","country_code":"EE","type":"education","lineage":["https://openalex.org/I111112146"]},{"id":"https://openalex.org/I63596082","display_name":"Tunis El Manar University","ror":"https://ror.org/029cgt552","country_code":"TN","type":"education","lineage":["https://openalex.org/I63596082"]}],"countries":["EE","TN"],"is_corresponding":false,"raw_author_name":"Sadok Ben Yahia","raw_affiliation_strings":["Department of Software Science , Tallinn University of Technology , Estonia","University of Tunis El Manar , Faculty of Sciences of Tunis , LIPAH , Tunisia","Universit\u00e9 de Tunis El Manar"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Software Science , Tallinn University of Technology , Estonia","institution_ids":["https://openalex.org/I111112146"]},{"raw_affiliation_string":"University of Tunis El Manar , Faculty of Sciences of Tunis , LIPAH , Tunisia","institution_ids":["https://openalex.org/I63596082"]},{"raw_affiliation_string":"Universit\u00e9 de Tunis El Manar","institution_ids":["https://openalex.org/I63596082"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5065070982","display_name":"Samira Si-Sa\u00efd Cherfi","orcid":"https://orcid.org/0000-0002-5989-5529","observed_orcids":["https://orcid.org/0000-0002-5989-5529"]},"institutions":[{"id":"https://openalex.org/I124158823","display_name":"Conservatoire National des Arts et M\u00e9tiers","ror":"https://ror.org/0175hh227","country_code":"FR","type":"education","lineage":["https://openalex.org/I124158823","https://openalex.org/I4210134562"]},{"id":"https://openalex.org/I4210145724","display_name":"Centre d'\u00e9tudes et de recherche en informatique et communications","ror":"https://ror.org/044j5mm75","country_code":"FR","type":"facility","lineage":["https://openalex.org/I124158823","https://openalex.org/I4210134562","https://openalex.org/I4210145724"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Samira Si-Said Cherfi","raw_affiliation_strings":["Conservatoire National des Arts et M\u00e9tiers , CEDRIC-CNAM , France","CEDRIC. Ing\u00e9nierie des Syst\u00e8mes d'Information et de D\u00e9cision"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Conservatoire National des Arts et M\u00e9tiers , CEDRIC-CNAM , France","institution_ids":["https://openalex.org/I124158823","https://openalex.org/I4210145724"]},{"raw_affiliation_string":"CEDRIC. Ing\u00e9nierie des Syst\u00e8mes d'Information et de D\u00e9cision","institution_ids":["https://openalex.org/I4210145724"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.6733,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":{"value":0.63561271,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"970","last_page":"979"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.8295999765396118,"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/T11719","display_name":"Data Quality and Management","score":0.8295999765396118,"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.1339000016450882,"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/T10538","display_name":"Data Mining Algorithms and Applications","score":0.003599999938160181,"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/document-oriented-databases","display_name":"document-oriented databases","score":0.7889999747276306},{"id":"https://openalex.org/keywords/nosql-databases","display_name":"NoSQL databases","score":0.8500000238418579},{"id":"https://openalex.org/keywords/extract-transform-load","display_name":"extract-transform-load","score":0.8619999885559082},{"id":"https://openalex.org/keywords/business-intelligence","display_name":"business intelligence","score":0.6830000281333923},{"id":"https://openalex.org/keywords/data-integration","display_name":"data integration","score":0.45500001311302185},{"id":"https://openalex.org/keywords/candidate-pruning","display_name":"candidate pruning","score":0.5149999856948853}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8669650554656982},{"id":"https://openalex.org/C154504017","wikidata":"https://www.wikidata.org/wiki/Q853614","display_name":"Identifier","level":2,"score":0.799446702003479},{"id":"https://openalex.org/C52146309","wikidata":"https://www.wikidata.org/wiki/Q7431116","display_name":"Schema (genetic algorithms)","level":2,"score":0.6865984797477722},{"id":"https://openalex.org/C119839945","wikidata":"https://www.wikidata.org/wiki/Q6545185","display_name":"Unique identifier","level":3,"score":0.5898755788803101},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5706470608711243},{"id":"https://openalex.org/C2779599972","wikidata":"https://www.wikidata.org/wiki/Q82231","display_name":"NoSQL","level":3,"score":0.5487386584281921},{"id":"https://openalex.org/C79158427","wikidata":"https://www.wikidata.org/wiki/Q485396","display_name":"Analytics","level":2,"score":0.4744756519794464},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.46429142355918884},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4546050429344177},{"id":"https://openalex.org/C135572916","wikidata":"https://www.wikidata.org/wiki/Q193351","display_name":"Data warehouse","level":2,"score":0.4527077078819275},{"id":"https://openalex.org/C2767350","wikidata":"https://www.wikidata.org/wiki/Q6662173","display_name":"Business intelligence","level":2,"score":0.4402965307235718},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.43204301595687866},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.41876956820487976},{"id":"https://openalex.org/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.24251/hicss.2021.118","doi":"https://doi.org/10.24251/hicss.2021.118","is_oa":true,"landing_page_url":"https://doi.org/10.24251/hicss.2021.118","pdf_url":"http://scholarspace.manoa.hawaii.edu/bitstream/10125/70730/1/0096.pdf","source":{"id":"https://openalex.org/S4210195248","display_name":"Hawaii International Conference on System Sciences (HICSS)","issn_l":"1530-1605","issn":["1530-1605","2572-6862"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-1","norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"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 Annual Hawaii International Conference on System Sciences","raw_type":"proceedings-article"},{"id":"pmh:oai:scholarspace.manoa.hawaii.edu:10125/70730","doi":null,"is_oa":true,"landing_page_url":"http://hdl.handle.net/10125/70730","pdf_url":"https://scholarspace.manoa.hawaii.edu/bitstreams/d390fb82-4f67-4ad9-a47e-b535d95b7eaf/download","source":{"id":"https://openalex.org/S4306401722","display_name":"ScholarSpace (University of Hawaii at Manoa)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I117965899","host_organization_name":"University of Hawai\u02bbi at M\u0101noa","host_organization_lineage":["https://openalex.org/I117965899"],"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":null},{"id":"pmh:oai:HAL:hal-03184465v1","doi":null,"is_oa":true,"landing_page_url":"https://hal.science/hal-03184465","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I4405252976","host_organization_name":"Centre pour la Communication Scientifique Directe","host_organization_lineage":["https://openalex.org/I4405252976"],"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":"https://scholarspace.manoa.hawaii.edu/handle/10125/72112","raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"pmh:oai:aisel.aisnet.org:hicss-54-1599","doi":null,"is_oa":false,"landing_page_url":"https://aisel.aisnet.org/hicss-54/da/big_data_and_analytics/5","pdf_url":null,"source":{"id":"https://openalex.org/S30879505","display_name":"Journal of the Association for Information Systems","issn_l":"1536-9323","issn":["1536-9323"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["abdc-a-star","anvur-scientific","cwts-core","dongbi-a","fnege-1","jufo-3","norway-2","poland-140","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310321080","host_organization_name":"Association for Information Systems","host_organization_lineage":["https://openalex.org/P4310321080"],"host_organization_lineage_names":["Association for Information Systems"],"type":"journal"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Hawaii International Conference on System Sciences 2021 (HICSS-54)","raw_type":"text"}],"best_oa_location":{"id":"doi:10.24251/hicss.2021.118","doi":"https://doi.org/10.24251/hicss.2021.118","is_oa":true,"landing_page_url":"https://doi.org/10.24251/hicss.2021.118","pdf_url":"http://scholarspace.manoa.hawaii.edu/bitstream/10125/70730/1/0096.pdf","source":{"id":"https://openalex.org/S4210195248","display_name":"Hawaii International Conference on System Sciences (HICSS)","issn_l":"1530-1605","issn":["1530-1605","2572-6862"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-1","norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"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 Annual Hawaii International Conference on System Sciences","raw_type":"proceedings-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3126190835.pdf","grobid_xml":"https://content.openalex.org/works/W3126190835.grobid-xml"},"referenced_works_count":19,"referenced_works":["https://openalex.org/W2112129552","https://openalex.org/W2125980212","https://openalex.org/W2244913846","https://openalex.org/W2404159982","https://openalex.org/W2604250586","https://openalex.org/W2741482120","https://openalex.org/W2750514106","https://openalex.org/W2769536418","https://openalex.org/W2793317603","https://openalex.org/W2889062015","https://openalex.org/W2907544011","https://openalex.org/W2935009408","https://openalex.org/W2952611840","https://openalex.org/W2962207144","https://openalex.org/W2967928177","https://openalex.org/W2980728347","https://openalex.org/W2981075922","https://openalex.org/W3037995288","https://openalex.org/W3084518455"],"related_works":["https://openalex.org/W4220850847","https://openalex.org/W4392220166","https://openalex.org/W3037995288","https://openalex.org/W7162407310","https://openalex.org/W4205951478","https://openalex.org/W4301667371","https://openalex.org/W2265048516","https://openalex.org/W2942152870","https://openalex.org/W4387848992","https://openalex.org/W7098097965"],"abstract_inverted_index":{"NoSQL":[0],"stores":[1],"offer":[2],"a":[3,33,66,74,163],"new":[4],"cost-effective":[5],"and":[6,83,86,104,112,133,140,147,154],"schema-free":[7,26],"system.":[8],"Although":[9],"it":[10,36],"is":[11,31,73,81],"widely":[12],"accepted":[13],"today,":[14],"Business":[15],"Intelligence":[16],"&":[17],"Analytics":[18],"(BI&A)":[19],"remains":[20],"associated":[21],"with":[22,65],"relational":[23],"databases.":[24],"Exploiting":[25],"data":[27,51],"for":[28],"analytical":[29],"purposes":[30],"issuing":[32],"challenge":[34],"since":[35],"requires":[37],"reviewing":[38],"all":[39],"the":[40,44,57,60,97],"BI&A":[41],"phases,":[42],"particularly":[43],"Extract-Transform-Load":[45],"(ETL)":[46],"process,":[47,59],"to":[48,108,157],"fit":[49],"big":[50],"sources":[52],"as":[53],"document":[54,116],"stores.":[55,117],"In":[56,92],"ETL":[58],"join":[61,71,101],"of":[62,68,99,121,130,138,166],"several":[63,115],"collections,":[64],"lack":[67],"explicitly":[69],"known":[70],"fields,":[72],"significant":[75],"challenge.":[76],"Detecting":[77],"these":[78],"fields":[79,102],"manually":[80],"time":[82],"effort":[84],"consuming,":[85],"even":[87],"infeasible":[88],"in":[89],"large-scale":[90],"datasets.":[91],"this":[93],"paper,":[94],"we":[95,170],"study":[96],"problem":[98],"discovering":[100],"automatically,":[103],"introduce":[105],"an":[106],"algorithm":[107],"detect":[109],"both":[110,152],"identifiers":[111],"references":[113],"on":[114,151],"The":[118],"modus":[119],"operandi":[120],"our":[122,172],"approach":[123],"underscores":[124],"two":[125],"core":[126],"stages:":[127],"(i)":[128],"discovery":[129],"identifier":[131,139],"candidates;":[132],"(ii)":[134],"identifying":[135],"candidate":[136],"pairs":[137],"reference":[141],"fields.":[142],"We":[143],"use":[144],"scoring":[145],"features":[146],"pruning":[148],"rules":[149],"based":[150],"syntactic":[153],"semantic":[155],"aspects":[156],"efficiently":[158],"discover":[159],"true":[160],"candidates":[161],"from":[162],"huge":[164],"number":[165],"initial":[167],"ones.":[168],"Finally,":[169],"report":[171],"experimental":[173],"findings":[174],"that":[175],"show":[176],"very":[177],"promising":[178],"results.":[179]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2021-02-15T00:00:00"}
