{"id":"https://openalex.org/W4408576924","doi":"https://doi.org/10.1142/s0218194025500111","title":"Scalable Instance Matching Using Lucene and Mongodb","display_name":"Scalable Instance Matching Using Lucene and Mongodb","publication_year":2025,"publication_date":"2025-03-01","ids":{"openalex":"https://openalex.org/W4408576924","doi":"https://doi.org/10.1142/s0218194025500111"},"language":"en","primary_location":{"id":"doi:10.1142/s0218194025500111","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s0218194025500111","pdf_url":null,"source":{"id":"https://openalex.org/S131442419","display_name":"International Journal of Software Engineering and Knowledge Engineering","issn_l":"0218-1940","issn":["0218-1940","1793-6403"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319815","host_organization_name":"World Scientific","host_organization_lineage":["https://openalex.org/P4310319815"],"host_organization_lineage_names":["World Scientific"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Software Engineering and Knowledge Engineering","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/A5032080255","display_name":"Siham Amrouch","orcid":"https://orcid.org/0009-0008-6112-0141"},"institutions":[{"id":"https://openalex.org/I1288970718","display_name":"Mohamed-Cherif Messaadia University","ror":"https://ror.org/04pn9tn44","country_code":"DZ","type":"education","lineage":["https://openalex.org/I1288970718"]}],"countries":["DZ"],"is_corresponding":true,"raw_author_name":"Siham Amrouch","raw_affiliation_strings":["LIM Laboratory, Computer Science Department, Mohamed Cherif Messaadia University, Souk Ahras, Algeria"],"affiliations":[{"raw_affiliation_string":"LIM Laboratory, Computer Science Department, Mohamed Cherif Messaadia University, Souk Ahras, Algeria","institution_ids":["https://openalex.org/I1288970718"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012546072","display_name":"Guefrouchi Ryma","orcid":"https://orcid.org/0000-0002-1756-1256"},"institutions":[{"id":"https://openalex.org/I4210160465","display_name":"Universit\u00e9 Constantine 2","ror":"https://ror.org/056mctw68","country_code":"DZ","type":"education","lineage":["https://openalex.org/I4210160465"]}],"countries":["DZ"],"is_corresponding":false,"raw_author_name":"Ryma Guefrouchi","raw_affiliation_strings":["MISC Laboratory, Abdelhamid Mehri Constantine2 University, Constantine, Algeria"],"affiliations":[{"raw_affiliation_string":"MISC Laboratory, Abdelhamid Mehri Constantine2 University, Constantine, Algeria","institution_ids":["https://openalex.org/I4210160465"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021773371","display_name":"Nawel Zemmal","orcid":"https://orcid.org/0000-0003-2827-4946"},"institutions":[{"id":"https://openalex.org/I108754898","display_name":"Badji Mokhtar University","ror":"https://ror.org/03sf55932","country_code":"DZ","type":"education","lineage":["https://openalex.org/I108754898"]},{"id":"https://openalex.org/I1288970718","display_name":"Mohamed-Cherif Messaadia University","ror":"https://ror.org/04pn9tn44","country_code":"DZ","type":"education","lineage":["https://openalex.org/I1288970718"]}],"countries":["DZ"],"is_corresponding":false,"raw_author_name":"Nawel Zemmal","raw_affiliation_strings":["Computer Science Department, Mohamed Cherif Messaadia University, Souk Ahras, Algeria","LabGED Laboratory, Computer Science Department, Badji Mokhtar University, Annaba, Algeria"],"affiliations":[{"raw_affiliation_string":"Computer Science Department, Mohamed Cherif Messaadia University, Souk Ahras, Algeria","institution_ids":["https://openalex.org/I1288970718"]},{"raw_affiliation_string":"LabGED Laboratory, Computer Science Department, Badji Mokhtar University, Annaba, Algeria","institution_ids":["https://openalex.org/I108754898"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5070511935","display_name":"Sadok Ben Yahia","orcid":"https://orcid.org/0000-0001-8939-8948"},"institutions":[{"id":"https://openalex.org/I177969490","display_name":"University of Southern Denmark","ror":"https://ror.org/03yrrjy16","country_code":"DK","type":"education","lineage":["https://openalex.org/I177969490"]},{"id":"https://openalex.org/I184886455","display_name":"Maersk (Denmark)","ror":"https://ror.org/046gbzb64","country_code":"DK","type":"company","lineage":["https://openalex.org/I184886455"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Sadok Ben Yahia","raw_affiliation_strings":["The Maersk Mc-Kinney Moller Institute, Centre for Industrial Software (CIS), University of Southern Denmark, Denmark"],"affiliations":[{"raw_affiliation_string":"The Maersk Mc-Kinney Moller Institute, Centre for Industrial Software (CIS), University of Southern Denmark, Denmark","institution_ids":["https://openalex.org/I184886455","https://openalex.org/I177969490"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5032080255"],"corresponding_institution_ids":["https://openalex.org/I1288970718"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.06552953,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"35","issue":"03","first_page":"421","last_page":"440"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9990000128746033,"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":0.9973999857902527,"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/computer-science","display_name":"Computer science","score":0.7419979572296143},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5628443956375122},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.469596266746521},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.4377436935901642},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.43659907579421997},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.32185807824134827},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09149664640426636},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.08584466576576233}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7419979572296143},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5628443956375122},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.469596266746521},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.4377436935901642},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.43659907579421997},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.32185807824134827},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09149664640426636},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.08584466576576233}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1142/s0218194025500111","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s0218194025500111","pdf_url":null,"source":{"id":"https://openalex.org/S131442419","display_name":"International Journal of Software Engineering and Knowledge Engineering","issn_l":"0218-1940","issn":["0218-1940","1793-6403"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319815","host_organization_name":"World Scientific","host_organization_lineage":["https://openalex.org/P4310319815"],"host_organization_lineage_names":["World Scientific"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Software Engineering and Knowledge Engineering","raw_type":"journal-article"},{"id":"pmh:oai:sdu.dk:openaire_cris_publications/d4409d12-a33d-4bb7-96d1-78f48fd4aba9","is_oa":false,"landing_page_url":"https://portal.findresearcher.sdu.dk/da/publications/d4409d12-a33d-4bb7-96d1-78f48fd4aba9","pdf_url":null,"source":{"id":"https://openalex.org/S4306400423","display_name":"University of Southern Denmark Research Portal (University of Southern Denmark)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I177969490","host_organization_name":"University of Southern Denmark","host_organization_lineage":["https://openalex.org/I177969490"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Amrouch, S, Guefrouchi, R, Zemmal, N & Ben Yahia, S 2025, 'Scalable Instance Matching Using Lucene and Mongodb', International Journal of Software Engineering and Knowledge Engineering, vol. 35, no. 3, pp. 421-440. https://doi.org/10.1142/S0218194025500111","raw_type":"info:eu-repo/semantics/publishedVersion"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W44468461","https://openalex.org/W66673523","https://openalex.org/W102861580","https://openalex.org/W1520740445","https://openalex.org/W1526669747","https://openalex.org/W1597082186","https://openalex.org/W1666220597","https://openalex.org/W1967208734","https://openalex.org/W2015191210","https://openalex.org/W2047029075","https://openalex.org/W2056099064","https://openalex.org/W2059917770","https://openalex.org/W2114538147","https://openalex.org/W2132497731","https://openalex.org/W2138662031","https://openalex.org/W2157896838","https://openalex.org/W2239873446","https://openalex.org/W2295925036","https://openalex.org/W2995624592","https://openalex.org/W3092962901","https://openalex.org/W3146259567","https://openalex.org/W3154675738","https://openalex.org/W3161220674","https://openalex.org/W4205941705","https://openalex.org/W4411323189"],"related_works":["https://openalex.org/W2389214306","https://openalex.org/W2965083567","https://openalex.org/W4235240664","https://openalex.org/W1838576100","https://openalex.org/W2095886385","https://openalex.org/W2889616422","https://openalex.org/W2089704382","https://openalex.org/W1983399550","https://openalex.org/W97075385","https://openalex.org/W2357523926"],"abstract_inverted_index":{"The":[0],"advancement":[1],"of":[2,19,89,149],"the":[3,15,30,39,86,130,135,146,151,185],"semantic":[4],"web":[5],"and":[6,17,48,103,111,119,164,179,190],"Linked":[7],"Open":[8],"Data":[9],"(LOD)":[10],"cloud":[11],"has":[12,55],"led":[13],"to":[14,38,43,80,124,213],"creation":[16],"integration":[18,47],"various":[20],"knowledge":[21,200],"bases":[22,201],"defined":[23],"by":[24],"ontologies.":[25],"A":[26],"significant":[27],"challenge":[28],"within":[29],"LOD":[31],"paradigm":[32],"is":[33,96],"identifying":[34],"resources":[35],"that":[36,142],"refer":[37],"same":[40],"real-world":[41],"object":[42],"enable":[44],"large-scale":[45],"data":[46,66],"sharing.":[49],"In":[50],"this":[51],"context,":[52],"instance":[53,94,131],"matching":[54,76,126,132],"emerged":[56],"as":[57],"a":[58,101],"key":[59],"solution,":[60],"linking":[61],"co-referent":[62],"instances":[63,115],"from":[64,134,202],"heterogeneous":[65],"sources":[67],"using":[68,107],"owl:sameAs":[69],"links.":[70],"Traditional":[71],"approaches":[72],"focus":[73],"on":[74,129,198],"schema-level":[75],"but":[77],"often":[78],"fail":[79],"address":[81],"property-level":[82],"heterogeneity.":[83],"Moreover,":[84,193],"given":[85],"large":[87],"scale":[88,118],"instances,":[90],"examining":[91],"all":[92,158],"possible":[93],"pairs":[95],"impractical.":[97],"This":[98],"paper":[99],"proposes":[100],"scalable":[102],"efficient":[104],"instance-matching":[105],"approach":[106,144,197,207],"MongoDb":[108,113],"(Humongous":[109],"database)":[110],"Lucene.":[112],"stores":[114],"at":[116],"any":[117],"Lucene":[120],"uses":[121],"inverted":[122],"indexes":[123],"identify":[125],"candidates.":[127],"Experiments":[128],"track":[133],"Ontology":[136],"Alignment":[137],"Evaluation":[138],"Initiative":[139],"(OAEI\u20192022)":[140],"show":[141],"our":[143,196,206],"matches":[145],"F-measure":[147],"score":[148],"RE-Miner,":[150,173],"top":[152],"performer":[153],"in":[154,161,187],"OAEI\u20192020,":[155,162,188],"while":[156],"surpassing":[157],"other":[159,199],"participants":[160],"2021":[163,189],"2022.":[165],"Additionally,":[166],"it":[167],"operates":[168],"17":[169],"times":[170,175,181],"faster":[171,176,182],"than":[172,177,183],"four":[174],"Lily":[178],"15":[180],"LogMap,":[184],"fastest":[186],"2022,":[191],"respectively.":[192],"we":[194],"evaluate":[195],"OAEI\u20192010.":[203],"Once":[204],"again,":[205],"gets":[208],"highly":[209],"competitive":[210],"resuts":[211],"compared":[212],"state-of-the-art":[214],"approaches.":[215]},"counts_by_year":[],"updated_date":"2025-12-21T01:58:51.020947","created_date":"2025-10-10T00:00:00"}
