{"id":"https://openalex.org/W4382372461","doi":"https://doi.org/10.3390/informatics10020042","title":"Genealogical Data Mining from Historical Archives: The Case of the Jewish Community in Pisa","display_name":"Genealogical Data Mining from Historical Archives: The Case of the Jewish Community in Pisa","publication_year":2023,"publication_date":"2023-05-11","ids":{"openalex":"https://openalex.org/W4382372461","doi":"https://doi.org/10.3390/informatics10020042"},"language":"en","primary_location":{"id":"doi:10.3390/informatics10020042","is_oa":true,"landing_page_url":"https://doi.org/10.3390/informatics10020042","pdf_url":"https://www.mdpi.com/2227-9709/10/2/42/pdf?version=1683865233","source":{"id":"https://openalex.org/S2738238905","display_name":"Informatics","issn_l":"2227-9709","issn":["2227-9709"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Informatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.mdpi.com/2227-9709/10/2/42/pdf?version=1683865233","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5047460283","display_name":"Angelica Lo Duca","orcid":"https://orcid.org/0000-0002-5252-6966"},"institutions":[{"id":"https://openalex.org/I4210130157","display_name":"Institute of Informatics and Telematics","ror":"https://ror.org/02gdcn153","country_code":"IT","type":"facility","lineage":["https://openalex.org/I4210130157","https://openalex.org/I4210155236"]},{"id":"https://openalex.org/I4210155236","display_name":"National Research Council","ror":"https://ror.org/04zaypm56","country_code":"IT","type":"nonprofit","lineage":["https://openalex.org/I4210155236"]}],"countries":["IT"],"is_corresponding":true,"raw_author_name":"Angelica Lo Duca","raw_affiliation_strings":["Institute of Informatics and Telematics, National Research Council, 56124 Pisa, Italy","Institute of Informatics and Telematics, National Research Council, 56124 Pisa, Italy;"],"raw_orcid":"https://orcid.org/0000-0002-5252-6966","affiliations":[{"raw_affiliation_string":"Institute of Informatics and Telematics, National Research Council, 56124 Pisa, Italy","institution_ids":["https://openalex.org/I4210130157","https://openalex.org/I4210155236"]},{"raw_affiliation_string":"Institute of Informatics and Telematics, National Research Council, 56124 Pisa, Italy;","institution_ids":["https://openalex.org/I4210130157","https://openalex.org/I4210155236"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008264110","display_name":"Andrea Marchetti","orcid":"https://orcid.org/0000-0003-4512-1642"},"institutions":[{"id":"https://openalex.org/I4210130157","display_name":"Institute of Informatics and Telematics","ror":"https://ror.org/02gdcn153","country_code":"IT","type":"facility","lineage":["https://openalex.org/I4210130157","https://openalex.org/I4210155236"]},{"id":"https://openalex.org/I4210155236","display_name":"National Research Council","ror":"https://ror.org/04zaypm56","country_code":"IT","type":"nonprofit","lineage":["https://openalex.org/I4210155236"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Andrea Marchetti","raw_affiliation_strings":["Institute of Informatics and Telematics, National Research Council, 56124 Pisa, Italy","Institute of Informatics and Telematics, National Research Council, 56124 Pisa, Italy;"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Informatics and Telematics, National Research Council, 56124 Pisa, Italy","institution_ids":["https://openalex.org/I4210130157","https://openalex.org/I4210155236"]},{"raw_affiliation_string":"Institute of Informatics and Telematics, National Research Council, 56124 Pisa, Italy;","institution_ids":["https://openalex.org/I4210130157","https://openalex.org/I4210155236"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103500812","display_name":"Manuela Moretti","orcid":null},"institutions":[{"id":"https://openalex.org/I4210130157","display_name":"Institute of Informatics and Telematics","ror":"https://ror.org/02gdcn153","country_code":"IT","type":"facility","lineage":["https://openalex.org/I4210130157","https://openalex.org/I4210155236"]},{"id":"https://openalex.org/I4210155236","display_name":"National Research Council","ror":"https://ror.org/04zaypm56","country_code":"IT","type":"nonprofit","lineage":["https://openalex.org/I4210155236"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Manuela Moretti","raw_affiliation_strings":["Institute of Informatics and Telematics, National Research Council, 56124 Pisa, Italy","Institute of Informatics and Telematics, National Research Council, 56124 Pisa, Italy;"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Informatics and Telematics, National Research Council, 56124 Pisa, Italy","institution_ids":["https://openalex.org/I4210130157","https://openalex.org/I4210155236"]},{"raw_affiliation_string":"Institute of Informatics and Telematics, National Research Council, 56124 Pisa, Italy;","institution_ids":["https://openalex.org/I4210130157","https://openalex.org/I4210155236"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067729495","display_name":"Francesca Diana","orcid":null},"institutions":[{"id":"https://openalex.org/I108290504","display_name":"University of Pisa","ror":"https://ror.org/03ad39j10","country_code":"IT","type":"education","lineage":["https://openalex.org/I108290504"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Francesca Diana","raw_affiliation_strings":["Department of Civilisation and Forms of Knowledge, University of Pisa, 56100 Pisa, Italy","Department of Civilisation and Forms of Knowledge, University of Pisa, 56100 Pisa, Italy;"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Civilisation and Forms of Knowledge, University of Pisa, 56100 Pisa, Italy","institution_ids":["https://openalex.org/I108290504"]},{"raw_affiliation_string":"Department of Civilisation and Forms of Knowledge, University of Pisa, 56100 Pisa, Italy;","institution_ids":["https://openalex.org/I108290504"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009011835","display_name":"Mafalda Toniazzi","orcid":"https://orcid.org/0000-0003-3869-7301"},"institutions":[{"id":"https://openalex.org/I108290504","display_name":"University of Pisa","ror":"https://ror.org/03ad39j10","country_code":"IT","type":"education","lineage":["https://openalex.org/I108290504"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Mafalda Toniazzi","raw_affiliation_strings":["Department of Civilisation and Forms of Knowledge, University of Pisa, 56100 Pisa, Italy","Department of Civilisation and Forms of Knowledge, University of Pisa, 56100 Pisa, Italy;"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Civilisation and Forms of Knowledge, University of Pisa, 56100 Pisa, Italy","institution_ids":["https://openalex.org/I108290504"]},{"raw_affiliation_string":"Department of Civilisation and Forms of Knowledge, University of Pisa, 56100 Pisa, Italy;","institution_ids":["https://openalex.org/I108290504"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5060189442","display_name":"Andrea D\u2019Errico","orcid":null},"institutions":[{"id":"https://openalex.org/I4210130157","display_name":"Institute of Informatics and Telematics","ror":"https://ror.org/02gdcn153","country_code":"IT","type":"facility","lineage":["https://openalex.org/I4210130157","https://openalex.org/I4210155236"]},{"id":"https://openalex.org/I4210155236","display_name":"National Research Council","ror":"https://ror.org/04zaypm56","country_code":"IT","type":"nonprofit","lineage":["https://openalex.org/I4210155236"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Andrea D\u2019Errico","raw_affiliation_strings":["Institute of Informatics and Telematics, National Research Council, 56124 Pisa, Italy","Institute of Informatics and Telematics, National Research Council, 56124 Pisa, Italy;"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Informatics and Telematics, National Research Council, 56124 Pisa, Italy","institution_ids":["https://openalex.org/I4210130157","https://openalex.org/I4210155236"]},{"raw_affiliation_string":"Institute of Informatics and Telematics, National Research Council, 56124 Pisa, Italy;","institution_ids":["https://openalex.org/I4210130157","https://openalex.org/I4210155236"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5047460283"],"corresponding_institution_ids":["https://openalex.org/I4210130157","https://openalex.org/I4210155236"],"apc_list":{"value":1600,"currency":"CHF","value_usd":1732},"apc_paid":{"value":1600,"currency":"CHF","value_usd":1732},"fwci":1.2328,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":{"value":0.80993796,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":"10","issue":"2","first_page":"42","last_page":"42"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9907000064849854,"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":0.9907000064849854,"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/T10028","display_name":"Topic Modeling","score":0.9876000285148621,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9864000082015991,"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/digitization","display_name":"Digitization","score":0.7527291774749756},{"id":"https://openalex.org/keywords/judaism","display_name":"Judaism","score":0.6156697273254395},{"id":"https://openalex.org/keywords/genealogy","display_name":"Genealogy","score":0.5089821815490723},{"id":"https://openalex.org/keywords/history","display_name":"History","score":0.36926376819610596},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.3674473762512207},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.295085072517395},{"id":"https://openalex.org/keywords/archaeology","display_name":"Archaeology","score":0.21606513857841492}],"concepts":[{"id":"https://openalex.org/C2779308522","wikidata":"https://www.wikidata.org/wiki/Q843958","display_name":"Digitization","level":2,"score":0.7527291774749756},{"id":"https://openalex.org/C150152722","wikidata":"https://www.wikidata.org/wiki/Q9268","display_name":"Judaism","level":2,"score":0.6156697273254395},{"id":"https://openalex.org/C53553401","wikidata":"https://www.wikidata.org/wiki/Q47307","display_name":"Genealogy","level":1,"score":0.5089821815490723},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.36926376819610596},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.3674473762512207},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.295085072517395},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.21606513857841492},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.3390/informatics10020042","is_oa":true,"landing_page_url":"https://doi.org/10.3390/informatics10020042","pdf_url":"https://www.mdpi.com/2227-9709/10/2/42/pdf?version=1683865233","source":{"id":"https://openalex.org/S2738238905","display_name":"Informatics","issn_l":"2227-9709","issn":["2227-9709"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Informatics","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:a3cf855bb7734ec38b4f2b7ea106f4a0","is_oa":true,"landing_page_url":"https://doaj.org/article/a3cf855bb7734ec38b4f2b7ea106f4a0","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Informatics, Vol 10, Iss 2, p 42 (2023)","raw_type":"article"},{"id":"pmh:oai:mdpi.com:/2227-9709/10/2/42/","is_oa":true,"landing_page_url":"https://dx.doi.org/10.3390/informatics10020042","pdf_url":null,"source":{"id":"https://openalex.org/S4306400947","display_name":"MDPI (MDPI AG)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210097602","host_organization_name":"Multidisciplinary Digital Publishing Institute (Switzerland)","host_organization_lineage":["https://openalex.org/I4210097602"],"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":"Informatics; Volume 10; Issue 2; Pages: 42","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.3390/informatics10020042","is_oa":true,"landing_page_url":"https://doi.org/10.3390/informatics10020042","pdf_url":"https://www.mdpi.com/2227-9709/10/2/42/pdf?version=1683865233","source":{"id":"https://openalex.org/S2738238905","display_name":"Informatics","issn_l":"2227-9709","issn":["2227-9709"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Informatics","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/5","display_name":"Gender equality","score":0.5299999713897705}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4382372461.pdf"},"referenced_works_count":13,"referenced_works":["https://openalex.org/W2032464653","https://openalex.org/W2116904179","https://openalex.org/W2345020996","https://openalex.org/W2609949944","https://openalex.org/W2896441583","https://openalex.org/W2913201142","https://openalex.org/W2946728200","https://openalex.org/W3090717980","https://openalex.org/W3108342895","https://openalex.org/W3214186955","https://openalex.org/W4247537847","https://openalex.org/W4282597027","https://openalex.org/W6691480349"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W1539704186","https://openalex.org/W4254109238","https://openalex.org/W2399890175","https://openalex.org/W4308177873","https://openalex.org/W3202479762","https://openalex.org/W2480493049","https://openalex.org/W4322582183","https://openalex.org/W2592115649","https://openalex.org/W1937392525"],"abstract_inverted_index":{"The":[0,69,88,121],"Jewish":[1,84],"community":[2,85],"archive":[3],"in":[4,66,86],"Pisa":[5,46],"owns":[6],"a":[7,50,91,129,133,137],"vast":[8],"collection":[9],"of":[10,38,55,76,94,146],"documents":[11,19,158],"and":[12,27,79,97,112,115,132,149,159],"manuscripts":[13],"that":[14],"date":[15],"back":[16],"centuries.":[17],"These":[18],"contain":[20],"valuable":[21,154],"genealogical":[22,134,162],"information,":[23],"including":[24],"birth,":[25],"marriage,":[26],"death":[28,113],"records.":[29],"This":[30,141],"paper":[31],"aims":[32],"to":[33,103,127,152,160],"describe":[34],"the":[35,39,53,58,67,83,144],"preliminary":[36],"results":[37],"Archivio":[40],"Storico":[41],"della":[42],"Comunita":[43],"Ebraica":[44],"di":[45],"(ASCEPI)":[47],"project,":[48],"with":[49],"focus":[51],"on":[52],"extraction":[54],"data":[56,106,123],"from":[57,118,156],"Nati,":[59],"Morti":[60],"e":[61],"Ballottati":[62],"(NMB)":[63],"Registry":[64,71],"document":[65],"archive.":[68],"NMB":[70],"contains":[72],"about":[73],"1900":[74],"records":[75],"births,":[77],"deaths,":[78],"balloted":[80],"individuals":[81],"within":[82],"Pisa.":[87],"study":[89,142],"uses":[90],"semiautomatic":[92],"pipeline":[93],"digitization,":[95],"transcription,":[96],"Natural":[98],"Language":[99],"Processing":[100],"(NLP)":[101],"techniques":[102,151],"extract":[104,153],"personal":[105],"such":[107],"as":[108],"names,":[109],"surnames,":[110],"birth":[111],"dates,":[114],"parental":[116],"names":[117],"each":[119],"record.":[120],"extracted":[122],"are":[124],"then":[125],"used":[126],"build":[128],"knowledge":[130],"base":[131],"tree":[135],"for":[136],"representative":[138],"family,":[139],"Supino.":[140],"demonstrates":[143],"potential":[145],"using":[147],"NLP":[148],"rule-based":[150],"information":[155],"historical":[157],"construct":[161],"trees.":[163]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1}],"updated_date":"2026-01-20T17:24:06.736184","created_date":"2025-10-10T00:00:00"}
