{"id":"https://openalex.org/W4376139591","doi":"https://doi.org/10.1007/s00799-023-00358-1","title":"DETEXA: declarative extensible text exploration and analysis through SQL","display_name":"DETEXA: declarative extensible text exploration and analysis through SQL","publication_year":2023,"publication_date":"2023-05-10","ids":{"openalex":"https://openalex.org/W4376139591","doi":"https://doi.org/10.1007/s00799-023-00358-1","pmid":"https://pubmed.ncbi.nlm.nih.gov/37361128"},"language":"en","primary_location":{"id":"doi:10.1007/s00799-023-00358-1","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s00799-023-00358-1","pdf_url":"https://link.springer.com/content/pdf/10.1007/s00799-023-00358-1.pdf","source":{"id":"https://openalex.org/S110615584","display_name":"International Journal on Digital Libraries","issn_l":"1432-1300","issn":["1432-1300","1432-5012"],"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":"International Journal on Digital Libraries","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/s00799-023-00358-1.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5036614082","display_name":"Yannis Foufoulas","orcid":"https://orcid.org/0000-0002-2785-946X"},"institutions":[{"id":"https://openalex.org/I200777214","display_name":"National and Kapodistrian University of Athens","ror":"https://ror.org/04gnjpq42","country_code":"GR","type":"education","lineage":["https://openalex.org/I200777214"]},{"id":"https://openalex.org/I4210156054","display_name":"Athena Research and Innovation Center In Information Communication & Knowledge Technologies","ror":"https://ror.org/0576by029","country_code":"GR","type":"facility","lineage":["https://openalex.org/I4210156054"]}],"countries":["GR"],"is_corresponding":true,"raw_author_name":"Yannis Foufoulas","raw_affiliation_strings":["Athena Research Center, Artemidos 6 & Epidavrou, 15125 Marousi, Greece","Department of Informatics and Telecommunications, National and Kapodistrian University of Athens, Panepistimiopolis, 15784 Ilisia, Greece"],"affiliations":[{"raw_affiliation_string":"Athena Research Center, Artemidos 6 & Epidavrou, 15125 Marousi, Greece","institution_ids":["https://openalex.org/I4210156054"]},{"raw_affiliation_string":"Department of Informatics and Telecommunications, National and Kapodistrian University of Athens, Panepistimiopolis, 15784 Ilisia, Greece","institution_ids":["https://openalex.org/I200777214"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002984123","display_name":"Eleni Zacharia","orcid":"https://orcid.org/0000-0003-0426-337X"},"institutions":[{"id":"https://openalex.org/I200777214","display_name":"National and Kapodistrian University of Athens","ror":"https://ror.org/04gnjpq42","country_code":"GR","type":"education","lineage":["https://openalex.org/I200777214"]},{"id":"https://openalex.org/I4210156054","display_name":"Athena Research and Innovation Center In Information Communication & Knowledge Technologies","ror":"https://ror.org/0576by029","country_code":"GR","type":"facility","lineage":["https://openalex.org/I4210156054"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Eleni Zacharia","raw_affiliation_strings":["Athena Research Center, Artemidos 6 & Epidavrou, 15125 Marousi, Greece","Department of Informatics and Telecommunications, National and Kapodistrian University of Athens, Panepistimiopolis, 15784 Ilisia, Greece"],"affiliations":[{"raw_affiliation_string":"Athena Research Center, Artemidos 6 & Epidavrou, 15125 Marousi, Greece","institution_ids":["https://openalex.org/I4210156054"]},{"raw_affiliation_string":"Department of Informatics and Telecommunications, National and Kapodistrian University of Athens, Panepistimiopolis, 15784 Ilisia, Greece","institution_ids":["https://openalex.org/I200777214"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046161854","display_name":"Harry Dimitropoulos","orcid":"https://orcid.org/0000-0001-9791-587X"},"institutions":[{"id":"https://openalex.org/I200777214","display_name":"National and Kapodistrian University of Athens","ror":"https://ror.org/04gnjpq42","country_code":"GR","type":"education","lineage":["https://openalex.org/I200777214"]},{"id":"https://openalex.org/I4210156054","display_name":"Athena Research and Innovation Center In Information Communication & Knowledge Technologies","ror":"https://ror.org/0576by029","country_code":"GR","type":"facility","lineage":["https://openalex.org/I4210156054"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Harry Dimitropoulos","raw_affiliation_strings":["Athena Research Center, Artemidos 6 & Epidavrou, 15125 Marousi, Greece","Department of Informatics and Telecommunications, National and Kapodistrian University of Athens, Panepistimiopolis, 15784 Ilisia, Greece"],"affiliations":[{"raw_affiliation_string":"Athena Research Center, Artemidos 6 & Epidavrou, 15125 Marousi, Greece","institution_ids":["https://openalex.org/I4210156054"]},{"raw_affiliation_string":"Department of Informatics and Telecommunications, National and Kapodistrian University of Athens, Panepistimiopolis, 15784 Ilisia, Greece","institution_ids":["https://openalex.org/I200777214"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023115150","display_name":"Natalia Manola","orcid":"https://orcid.org/0000-0002-3477-3082"},"institutions":[{"id":"https://openalex.org/I200777214","display_name":"National and Kapodistrian University of Athens","ror":"https://ror.org/04gnjpq42","country_code":"GR","type":"education","lineage":["https://openalex.org/I200777214"]},{"id":"https://openalex.org/I4210156054","display_name":"Athena Research and Innovation Center In Information Communication & Knowledge Technologies","ror":"https://ror.org/0576by029","country_code":"GR","type":"facility","lineage":["https://openalex.org/I4210156054"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Natalia Manola","raw_affiliation_strings":["Athena Research Center, Artemidos 6 & Epidavrou, 15125 Marousi, Greece","Department of Informatics and Telecommunications, National and Kapodistrian University of Athens, Panepistimiopolis, 15784 Ilisia, Greece"],"affiliations":[{"raw_affiliation_string":"Athena Research Center, Artemidos 6 & Epidavrou, 15125 Marousi, Greece","institution_ids":["https://openalex.org/I4210156054"]},{"raw_affiliation_string":"Department of Informatics and Telecommunications, National and Kapodistrian University of Athens, Panepistimiopolis, 15784 Ilisia, Greece","institution_ids":["https://openalex.org/I200777214"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5084870386","display_name":"Yannis Ioannidis","orcid":"https://orcid.org/0000-0002-1705-8247"},"institutions":[{"id":"https://openalex.org/I200777214","display_name":"National and Kapodistrian University of Athens","ror":"https://ror.org/04gnjpq42","country_code":"GR","type":"education","lineage":["https://openalex.org/I200777214"]},{"id":"https://openalex.org/I4210156054","display_name":"Athena Research and Innovation Center In Information Communication & Knowledge Technologies","ror":"https://ror.org/0576by029","country_code":"GR","type":"facility","lineage":["https://openalex.org/I4210156054"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Yannis Ioannidis","raw_affiliation_strings":["Athena Research Center, Artemidos 6 & Epidavrou, 15125 Marousi, Greece","Department of Informatics and Telecommunications, National and Kapodistrian University of Athens, Panepistimiopolis, 15784 Ilisia, Greece"],"affiliations":[{"raw_affiliation_string":"Athena Research Center, Artemidos 6 & Epidavrou, 15125 Marousi, Greece","institution_ids":["https://openalex.org/I4210156054"]},{"raw_affiliation_string":"Department of Informatics and Telecommunications, National and Kapodistrian University of Athens, Panepistimiopolis, 15784 Ilisia, Greece","institution_ids":["https://openalex.org/I200777214"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5036614082"],"corresponding_institution_ids":["https://openalex.org/I200777214","https://openalex.org/I4210156054"],"apc_list":{"value":2290,"currency":"EUR","value_usd":2890},"apc_paid":{"value":2290,"currency":"EUR","value_usd":2890},"fwci":0.6959,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.74741692,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":"25","issue":"3","first_page":"457","last_page":"469"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13734","display_name":"Advanced Computational Techniques and Applications","score":0.9674999713897705,"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/T13734","display_name":"Advanced Computational Techniques and Applications","score":0.9674999713897705,"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/T13523","display_name":"Mathematics, Computing, and Information Processing","score":0.9549000263214111,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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":0.9532999992370605,"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/computer-science","display_name":"Computer science","score":0.8778523802757263},{"id":"https://openalex.org/keywords/sql","display_name":"SQL","score":0.6660014390945435},{"id":"https://openalex.org/keywords/extensibility","display_name":"Extensibility","score":0.6599307656288147},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.5687187314033508},{"id":"https://openalex.org/keywords/declarative-programming","display_name":"Declarative programming","score":0.4447849690914154},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.3516312837600708},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.34516066312789917},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.32938605546951294},{"id":"https://openalex.org/keywords/programming-paradigm","display_name":"Programming paradigm","score":0.10579100251197815},{"id":"https://openalex.org/keywords/inductive-programming","display_name":"Inductive programming","score":0.06718242168426514}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8778523802757263},{"id":"https://openalex.org/C510870499","wikidata":"https://www.wikidata.org/wiki/Q47607","display_name":"SQL","level":2,"score":0.6660014390945435},{"id":"https://openalex.org/C32833848","wikidata":"https://www.wikidata.org/wiki/Q4115054","display_name":"Extensibility","level":2,"score":0.6599307656288147},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.5687187314033508},{"id":"https://openalex.org/C146206909","wikidata":"https://www.wikidata.org/wiki/Q531152","display_name":"Declarative programming","level":4,"score":0.4447849690914154},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.3516312837600708},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.34516066312789917},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.32938605546951294},{"id":"https://openalex.org/C34165917","wikidata":"https://www.wikidata.org/wiki/Q188267","display_name":"Programming paradigm","level":2,"score":0.10579100251197815},{"id":"https://openalex.org/C50033165","wikidata":"https://www.wikidata.org/wiki/Q15712089","display_name":"Inductive programming","level":3,"score":0.06718242168426514}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1007/s00799-023-00358-1","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s00799-023-00358-1","pdf_url":"https://link.springer.com/content/pdf/10.1007/s00799-023-00358-1.pdf","source":{"id":"https://openalex.org/S110615584","display_name":"International Journal on Digital Libraries","issn_l":"1432-1300","issn":["1432-1300","1432-5012"],"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":"International Journal on Digital Libraries","raw_type":"journal-article"},{"id":"pmid:37361128","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/37361128","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":"International journal on digital libraries","raw_type":null},{"id":"pmh:oai:pubmedcentral.nih.gov:10170051","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/10170051","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC10170051/pdf/799_2023_Article_358.pdf","source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Int J Digit Libr","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1007/s00799-023-00358-1","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s00799-023-00358-1","pdf_url":"https://link.springer.com/content/pdf/10.1007/s00799-023-00358-1.pdf","source":{"id":"https://openalex.org/S110615584","display_name":"International Journal on Digital Libraries","issn_l":"1432-1300","issn":["1432-1300","1432-5012"],"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":"International Journal on Digital Libraries","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","score":0.4300000071525574,"id":"https://metadata.un.org/sdg/9"}],"awards":[{"id":"https://openalex.org/G5644912080","display_name":null,"funder_award_id":"101017452","funder_id":"https://openalex.org/F4320332999","funder_display_name":"Horizon 2020 Framework Programme"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320318628","display_name":"Hellenic Academic Libraries Link","ror":null},{"id":"https://openalex.org/F4320332999","display_name":"Horizon 2020 Framework Programme","ror":"https://ror.org/00k4n6c32"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4376139591.pdf"},"referenced_works_count":10,"referenced_works":["https://openalex.org/W1087666452","https://openalex.org/W2046797729","https://openalex.org/W2182129314","https://openalex.org/W2244501064","https://openalex.org/W2294745660","https://openalex.org/W2753880770","https://openalex.org/W2908675229","https://openalex.org/W4248146143","https://openalex.org/W4294904087","https://openalex.org/W4376139591"],"related_works":["https://openalex.org/W625381833","https://openalex.org/W2117326768","https://openalex.org/W3009891130","https://openalex.org/W4287829362","https://openalex.org/W3018143143","https://openalex.org/W2758245007","https://openalex.org/W2962849695","https://openalex.org/W1592890940","https://openalex.org/W2198404527","https://openalex.org/W2090182820"],"abstract_inverted_index":{"Metadata":[0],"enrichment":[1],"through":[2],"text":[3,49,80,90,118],"mining":[4,81,119],"techniques":[5],"is":[6,71,95,133],"becoming":[7],"one":[8],"of":[9,22,61,68],"the":[10,19,58,74,107,130],"most":[11],"significant":[12,138],"tasks":[13],"in":[14,53,145],"digital":[15],"libraries.":[16],"Due":[17],"to":[18,72,76,98,109,141,150],"exponential":[20],"increase":[21],"open":[23],"access":[24],"publications,":[25],"several":[26],"new":[27],"challenges":[28],"have":[29],"emerged.":[30],"Raw":[31],"data":[32,41,85],"are":[33],"usually":[34],"big,":[35],"unstructured,":[36],"and":[37,89,106,136],"come":[38],"from":[39],"heterogeneous":[40],"sources.":[42],"In":[43],"this":[44,69],"paper,":[45],"we":[46],"introduce":[47],"a":[48],"analysis":[50,91,127],"framework":[51,70,132],"implemented":[52],"extended":[54],"SQL":[55,94],"that":[56,113,129],"exploits":[57],"scalability":[59],"characteristics":[60],"modern":[62],"database":[63],"management":[64],"systems.":[65],"The":[66],"purpose":[67],"provide":[73],"opportunity":[75],"build":[77,110],"performant":[78],"end-to-end":[79],"pipelines":[82],"which":[83,102],"include":[84],"harvesting,":[86],"cleaning,":[87],"processing,":[88],"at":[92],"once.":[93],"selected":[96],"due":[97],"its":[99],"declarative":[100],"nature":[101],"offers":[103],"fast":[104],"experimentation":[105],"ability":[108],"APIs":[111],"so":[112],"domain":[114],"experts":[115],"can":[116],"edit":[117],"workflows":[120],"via":[121],"easy-to-use":[122],"graphical":[123],"interfaces.":[124],"Our":[125],"experimental":[126],"demonstrates":[128],"proposed":[131],"very":[134],"effective":[135],"achieves":[137],"speedup,":[139],"up":[140],"three":[142],"times":[143],"faster,":[144],"common":[146],"use":[147],"cases":[148],"compared":[149],"other":[151],"popular":[152],"approaches.":[153]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}
