{"id":"https://openalex.org/W4406696541","doi":"https://doi.org/10.1007/s10618-024-01074-3","title":"Missing value replacement in strings and applications","display_name":"Missing value replacement in strings and applications","publication_year":2025,"publication_date":"2025-01-22","ids":{"openalex":"https://openalex.org/W4406696541","doi":"https://doi.org/10.1007/s10618-024-01074-3","pmid":"https://pubmed.ncbi.nlm.nih.gov/39867462"},"language":"en","primary_location":{"id":"doi:10.1007/s10618-024-01074-3","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10618-024-01074-3","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10618-024-01074-3.pdf","source":{"id":"https://openalex.org/S121920818","display_name":"Data Mining and Knowledge Discovery","issn_l":"1384-5810","issn":["1384-5810","1573-756X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Data Mining and Knowledge Discovery","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s10618-024-01074-3.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5085190716","display_name":"Giulia Bernardini","orcid":"https://orcid.org/0000-0001-6647-088X"},"institutions":[{"id":"https://openalex.org/I142444530","display_name":"University of Trieste","ror":"https://ror.org/02n742c10","country_code":"IT","type":"education","lineage":["https://openalex.org/I142444530"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Giulia Bernardini","raw_affiliation_strings":["Department of Mathematics, Informatics and Geosciences, University of Trieste, Trieste, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Mathematics, Informatics and Geosciences, University of Trieste, Trieste, Italy","institution_ids":["https://openalex.org/I142444530"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100353222","display_name":"Chang Liu","orcid":"https://orcid.org/0000-0002-2837-7737"},"institutions":[{"id":"https://openalex.org/I114539943","display_name":"Zhejiang Chinese Medical University","ror":"https://ror.org/04epb4p87","country_code":"CN","type":"education","lineage":["https://openalex.org/I114539943"]},{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chang Liu","raw_affiliation_strings":["Medical Center, Zhejiang University, Zhejiang, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Medical Center, Zhejiang University, Zhejiang, China","institution_ids":["https://openalex.org/I114539943","https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065416953","display_name":"Grigorios Loukides","orcid":"https://orcid.org/0000-0003-0888-5061"},"institutions":[{"id":"https://openalex.org/I183935753","display_name":"King's College London","ror":"https://ror.org/0220mzb33","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I183935753"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Grigorios Loukides","raw_affiliation_strings":["Department of Informatics, King's College London, London, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Informatics, King's College London, London, UK","institution_ids":["https://openalex.org/I183935753"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064823807","display_name":"Alberto Marchetti-Spaccamela","orcid":"https://orcid.org/0000-0002-7991-4416"},"institutions":[{"id":"https://openalex.org/I861853513","display_name":"Sapienza University of Rome","ror":"https://ror.org/02be6w209","country_code":"IT","type":"education","lineage":["https://openalex.org/I861853513"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Alberto Marchetti-Spaccamela","raw_affiliation_strings":["Department of Computer, Automatic and Management Engineering, La Sapienza University of Rome, Rome, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer, Automatic and Management Engineering, La Sapienza University of Rome, Rome, Italy","institution_ids":["https://openalex.org/I861853513"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051275317","display_name":"Solon P. Pissis","orcid":"https://orcid.org/0000-0002-1445-1932"},"institutions":[{"id":"https://openalex.org/I1341640284","display_name":"Centrum Wiskunde & Informatica","ror":"https://ror.org/00x7ekv49","country_code":"NL","type":"facility","lineage":["https://openalex.org/I1341640284","https://openalex.org/I2800991832","https://openalex.org/I4405262988"]},{"id":"https://openalex.org/I865915315","display_name":"Vrije Universiteit Amsterdam","ror":"https://ror.org/008xxew50","country_code":"NL","type":"education","lineage":["https://openalex.org/I865915315"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Solon P. Pissis","raw_affiliation_strings":["CWI, Amsterdam, The Netherlands","ERABLE Team, Lyon, France","Faculty of Science, Vrije Universiteit, Amsterdam, The Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CWI, Amsterdam, The Netherlands","institution_ids":["https://openalex.org/I1341640284"]},{"raw_affiliation_string":"ERABLE Team, Lyon, France","institution_ids":[]},{"raw_affiliation_string":"Faculty of Science, Vrije Universiteit, Amsterdam, The Netherlands","institution_ids":["https://openalex.org/I865915315"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044184077","display_name":"Leen Stougie","orcid":"https://orcid.org/0000-0001-6938-8902"},"institutions":[{"id":"https://openalex.org/I1341640284","display_name":"Centrum Wiskunde & Informatica","ror":"https://ror.org/00x7ekv49","country_code":"NL","type":"facility","lineage":["https://openalex.org/I1341640284","https://openalex.org/I2800991832","https://openalex.org/I4405262988"]},{"id":"https://openalex.org/I865915315","display_name":"Vrije Universiteit Amsterdam","ror":"https://ror.org/008xxew50","country_code":"NL","type":"education","lineage":["https://openalex.org/I865915315"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Leen Stougie","raw_affiliation_strings":["CWI, Amsterdam, The Netherlands","ERABLE Team, Lyon, France","School of Business and Economics, Vrije Universiteit, Amsterdam, The Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CWI, Amsterdam, The Netherlands","institution_ids":["https://openalex.org/I1341640284"]},{"raw_affiliation_string":"ERABLE Team, Lyon, France","institution_ids":[]},{"raw_affiliation_string":"School of Business and Economics, Vrije Universiteit, Amsterdam, The Netherlands","institution_ids":["https://openalex.org/I865915315"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5029963514","display_name":"Michelle Sweering","orcid":"https://orcid.org/0000-0003-1200-6015"},"institutions":[{"id":"https://openalex.org/I1341640284","display_name":"Centrum Wiskunde & Informatica","ror":"https://ror.org/00x7ekv49","country_code":"NL","type":"facility","lineage":["https://openalex.org/I1341640284","https://openalex.org/I2800991832","https://openalex.org/I4405262988"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Michelle Sweering","raw_affiliation_strings":["CWI, Amsterdam, The Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CWI, Amsterdam, The Netherlands","institution_ids":["https://openalex.org/I1341640284"]}]}],"institutions":[],"countries_distinct_count":4,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5065416953"],"corresponding_institution_ids":["https://openalex.org/I183935753"],"apc_list":{"value":2390,"currency":"EUR","value_usd":2990},"apc_paid":{"value":2390,"currency":"EUR","value_usd":2990},"fwci":2.0951,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.86666365,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":"39","issue":"2","first_page":"12","last_page":"12"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9983999729156494,"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"}},"topics":[{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9983999729156494,"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/T11106","display_name":"Data Management and Algorithms","score":0.9976000189781189,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.9975000023841858,"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/string","display_name":"String (physics)","score":0.6878436207771301},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6379866003990173},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6058242917060852},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.5993523001670837},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.566792368888855},{"id":"https://openalex.org/keywords/measure","display_name":"Measure (data warehouse)","score":0.5087917447090149},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.4912394881248474},{"id":"https://openalex.org/keywords/edit-distance","display_name":"Edit distance","score":0.4761747717857361},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.46030309796333313},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.43165695667266846},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.42978203296661377},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.41274744272232056},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.39234864711761475},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.243831604719162},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.21663767099380493}],"concepts":[{"id":"https://openalex.org/C157486923","wikidata":"https://www.wikidata.org/wiki/Q1376436","display_name":"String (physics)","level":2,"score":0.6878436207771301},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6379866003990173},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6058242917060852},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.5993523001670837},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.566792368888855},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.5087917447090149},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.4912394881248474},{"id":"https://openalex.org/C44359876","wikidata":"https://www.wikidata.org/wiki/Q5338467","display_name":"Edit distance","level":2,"score":0.4761747717857361},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.46030309796333313},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.43165695667266846},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.42978203296661377},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.41274744272232056},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.39234864711761475},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.243831604719162},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.21663767099380493},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C37914503","wikidata":"https://www.wikidata.org/wiki/Q156495","display_name":"Mathematical physics","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","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},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0}],"mesh":[],"locations_count":8,"locations":[{"id":"doi:10.1007/s10618-024-01074-3","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10618-024-01074-3","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10618-024-01074-3.pdf","source":{"id":"https://openalex.org/S121920818","display_name":"Data Mining and Knowledge Discovery","issn_l":"1384-5810","issn":["1384-5810","1573-756X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Data Mining and Knowledge Discovery","raw_type":"journal-article"},{"id":"pmid:39867462","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/39867462","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Data mining and knowledge discovery","raw_type":null},{"id":"pmh:oai:kclpure.kcl.ac.uk:openaire/79702cbb-9dff-46c6-8f61-5bb9be1236c2","is_oa":false,"landing_page_url":"https://kclpure.kcl.ac.uk/portal/en/publications/79702cbb-9dff-46c6-8f61-5bb9be1236c2","pdf_url":null,"source":{"id":"https://openalex.org/S4306400216","display_name":"Research Portal (King's College London)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I183935753","host_organization_name":"King's College London","host_organization_lineage":["https://openalex.org/I183935753"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bernardini, G, Liu, C, Loukidis, G, Marchetti-Spaccamela, A, Pissis, S P, Stougie, L & Sweering, M 2025, 'Missing Value Replacement in Strings and Applications', DATA MINING AND KNOWLEDGE DISCOVERY, vol. 39, 12. https://doi.org/10.1007/s10618-024-01074-3","raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"pmh:oai:research.vu.nl:openaire_cris_publications/8a02a50e-06d3-4836-aac0-8c0e0992a4bd","is_oa":true,"landing_page_url":"https://research.vu.nl/en/publications/8a02a50e-06d3-4836-aac0-8c0e0992a4bd","pdf_url":null,"source":{"id":"https://openalex.org/S4306401107","display_name":"VU Research Portal","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I865915315","host_organization_name":"Vrije Universiteit Amsterdam","host_organization_lineage":["https://openalex.org/I865915315"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bernardini, G, Liu, C, Loukides, G, Marchetti-Spaccamela, A, Pissis, S P, Stougie, L & Sweering, M 2025, 'Missing value replacement in strings and applications', Data Mining and Knowledge Discovery, vol. 39, no. 2, 12, pp. 1-50. https://doi.org/10.1007/s10618-024-01074-3","raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"pmh:oai:HAL:hal-05435081v1","is_oa":true,"landing_page_url":"https://inria.hal.science/hal-05435081","pdf_url":"https://inria.hal.science/hal-05435081/document","source":{"id":"https://openalex.org/S4406922466","display_name":"SPIRE - Sciences Po Institutional REpository","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Data Mining and Knowledge Discovery, 2025, 39 (2), pp.12. ⟨10.1007/s10618-024-01074-3⟩","raw_type":"Journal articles"},{"id":"pmh:oai:pubmedcentral.nih.gov:11754389","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/11754389","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC11754389/pdf/10618_2024_Article_1074.pdf","source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Data Min Knowl Discov","raw_type":"Text"},{"id":"pmh:oai:air.unimi.it:2434/1138695","is_oa":true,"landing_page_url":"https://hdl.handle.net/2434/1138695","pdf_url":null,"source":{"id":"https://openalex.org/S4306400516","display_name":"Archivio Istituzionale della Ricerca (Universita Degli Studi Di Milano)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I189158943","host_organization_name":"University of Milan","host_organization_lineage":["https://openalex.org/I189158943"],"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":null,"raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:oai:research.vu.nl:openaire/8a02a50e-06d3-4836-aac0-8c0e0992a4bd","is_oa":true,"landing_page_url":"https://hdl.handle.net/1871.1/8a02a50e-06d3-4836-aac0-8c0e0992a4bd","pdf_url":null,"source":{"id":"https://openalex.org/S4306401107","display_name":"VU Research Portal","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I865915315","host_organization_name":"Vrije Universiteit Amsterdam","host_organization_lineage":["https://openalex.org/I865915315"],"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":"Bernardini, G, Liu, C, Loukides, G, Marchetti-Spaccamela, A, Pissis, S P, Stougie, L & Sweering, M 2025, 'Missing value replacement in strings and applications', Data Mining and Knowledge Discovery, vol. 39, no. 2, 12, pp. 1-50. https://doi.org/10.1007/s10618-024-01074-3","raw_type":"info:eu-repo/semantics/publishedVersion"}],"best_oa_location":{"id":"doi:10.1007/s10618-024-01074-3","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10618-024-01074-3","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10618-024-01074-3.pdf","source":{"id":"https://openalex.org/S121920818","display_name":"Data Mining and Knowledge Discovery","issn_l":"1384-5810","issn":["1384-5810","1573-756X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Data Mining and Knowledge Discovery","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.7699999809265137,"id":"https://metadata.un.org/sdg/16"}],"awards":[{"id":"https://openalex.org/G7830895999","display_name":null,"funder_award_id":"024.002.003","funder_id":"https://openalex.org/F4320321800","funder_display_name":"Nederlandse Organisatie voor Wetenschappelijk Onderzoek"}],"funders":[{"id":"https://openalex.org/F4320321800","display_name":"Nederlandse Organisatie voor Wetenschappelijk Onderzoek","ror":"https://ror.org/04jsz6e67"},{"id":"https://openalex.org/F4320334678","display_name":"European Research Council","ror":"https://ror.org/0472cxd90"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4406696541.pdf","grobid_xml":"https://content.openalex.org/works/W4406696541.grobid-xml"},"referenced_works_count":109,"referenced_works":["https://openalex.org/W40976687","https://openalex.org/W298212978","https://openalex.org/W865976024","https://openalex.org/W895625386","https://openalex.org/W1490591387","https://openalex.org/W1540089290","https://openalex.org/W1557073126","https://openalex.org/W1610612296","https://openalex.org/W1909629542","https://openalex.org/W1972418517","https://openalex.org/W1981383465","https://openalex.org/W1984953641","https://openalex.org/W1985514943","https://openalex.org/W1995725694","https://openalex.org/W2010808181","https://openalex.org/W2015439533","https://openalex.org/W2017332377","https://openalex.org/W2017952818","https://openalex.org/W2028020328","https://openalex.org/W2035564383","https://openalex.org/W2036527143","https://openalex.org/W2039059619","https://openalex.org/W2043481183","https://openalex.org/W2052987310","https://openalex.org/W2054973636","https://openalex.org/W2059513841","https://openalex.org/W2064186732","https://openalex.org/W2077451659","https://openalex.org/W2080535496","https://openalex.org/W2082995364","https://openalex.org/W2084246508","https://openalex.org/W2096863518","https://openalex.org/W2097341408","https://openalex.org/W2102461176","https://openalex.org/W2103441770","https://openalex.org/W2104264891","https://openalex.org/W2107079154","https://openalex.org/W2115098571","https://openalex.org/W2118502261","https://openalex.org/W2119894516","https://openalex.org/W2127395777","https://openalex.org/W2130735255","https://openalex.org/W2137536943","https://openalex.org/W2144326136","https://openalex.org/W2148361370","https://openalex.org/W2152331922","https://openalex.org/W2156345098","https://openalex.org/W2157305458","https://openalex.org/W2159073939","https://openalex.org/W2162833336","https://openalex.org/W2165621523","https://openalex.org/W2165924229","https://openalex.org/W2166647826","https://openalex.org/W2167686542","https://openalex.org/W2168093996","https://openalex.org/W2169273428","https://openalex.org/W2191907956","https://openalex.org/W2270418173","https://openalex.org/W2332955060","https://openalex.org/W2345982775","https://openalex.org/W2401393052","https://openalex.org/W2513739156","https://openalex.org/W2555737796","https://openalex.org/W2581082906","https://openalex.org/W2585199909","https://openalex.org/W2591700809","https://openalex.org/W2605046998","https://openalex.org/W2606984267","https://openalex.org/W2612379539","https://openalex.org/W2620598837","https://openalex.org/W2756169797","https://openalex.org/W2810672408","https://openalex.org/W2887498618","https://openalex.org/W2897852178","https://openalex.org/W2911964244","https://openalex.org/W2912116129","https://openalex.org/W2926585089","https://openalex.org/W2953008890","https://openalex.org/W2953263404","https://openalex.org/W2989589450","https://openalex.org/W3013655789","https://openalex.org/W3026263360","https://openalex.org/W3034305000","https://openalex.org/W3034536504","https://openalex.org/W3043814971","https://openalex.org/W3048451018","https://openalex.org/W3090342467","https://openalex.org/W3091142854","https://openalex.org/W3091533194","https://openalex.org/W3110665143","https://openalex.org/W3115571444","https://openalex.org/W3141915782","https://openalex.org/W3164387821","https://openalex.org/W3184490376","https://openalex.org/W3184971117","https://openalex.org/W3197374172","https://openalex.org/W3197494818","https://openalex.org/W3198445485","https://openalex.org/W4200551502","https://openalex.org/W4206306045","https://openalex.org/W4206633088","https://openalex.org/W4226226456","https://openalex.org/W4231916799","https://openalex.org/W4235936977","https://openalex.org/W4247053599","https://openalex.org/W4249444195","https://openalex.org/W4254652536","https://openalex.org/W4281753295","https://openalex.org/W6969227564"],"related_works":["https://openalex.org/W3044917232","https://openalex.org/W1498160656","https://openalex.org/W2119149496","https://openalex.org/W2055693471","https://openalex.org/W4295101776","https://openalex.org/W2139858675","https://openalex.org/W2952580779","https://openalex.org/W1537327044","https://openalex.org/W2007540612","https://openalex.org/W2054882906"],"abstract_inverted_index":{"sanitize":[0,57],"a":[1,8,21,27,58],"private":[2,30,61],"string":[3],"in":[4],"the":[5,68,71],"presence":[6],"of":[7,10,29,60,70],"set":[9],"fixed-length":[11],"forbidden":[12],"patterns":[13],"[Bernardini":[14],"et":[15],"al.":[16],"2021a];":[17],"(3)":[18],"we":[19,46,81],"propose":[20],"methodology":[22,54],"for":[23],"sanitizing":[24],"and":[25,36,39,44,73,87],"clustering":[26,65],"collection":[28,59],"strings":[31,62],"that":[32,52],"utilizes":[33],"our":[34,53,78],"algorithm":[35],"an":[37],"effective":[38],"efficiently":[40,56],"computable":[41],"distance":[42],"measure;":[43],"(4)":[45],"present":[47],"extensive":[48],"experimental":[49],"results":[50],"showing":[51],"can":[55],"while":[63],"preserving":[64],"quality,":[66],"outperforming":[67],"state":[69],"art":[72],"baselines.":[74],"To":[75],"arrive":[76],"at":[77],"theoretical":[79],"results,":[80],"employ":[82],"techniques":[83],"from":[84],"formal":[85],"languages":[86],"combinatorial":[88],"pattern":[89],"matching.":[90]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-05-05T08:41:31.759640","created_date":"2025-10-10T00:00:00"}