{"id":"https://openalex.org/W3174885571","doi":"https://doi.org/10.3390/data6070071","title":"An Annotated Corpus of Crime-Related Portuguese Documents for NLP and Machine Learning Processing","display_name":"An Annotated Corpus of Crime-Related Portuguese Documents for NLP and Machine Learning Processing","publication_year":2021,"publication_date":"2021-06-26","ids":{"openalex":"https://openalex.org/W3174885571","doi":"https://doi.org/10.3390/data6070071","mag":"3174885571"},"language":"en","primary_location":{"id":"doi:10.3390/data6070071","is_oa":true,"landing_page_url":"https://doi.org/10.3390/data6070071","pdf_url":"https://www.mdpi.com/2306-5729/6/7/71/pdf?version=1624864915","source":{"id":"https://openalex.org/S4210226510","display_name":"Data","issn_l":"2306-5729","issn":["2306-5729"],"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":"Data","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.mdpi.com/2306-5729/6/7/71/pdf?version=1624864915","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5017024705","display_name":"Gon\u00e7alo Carnaz","orcid":"https://orcid.org/0000-0001-8285-7005"},"institutions":[{"id":"https://openalex.org/I21803372","display_name":"University of \u00c9vora","ror":"https://ror.org/02gyps716","country_code":"PT","type":"education","lineage":["https://openalex.org/I21803372"]}],"countries":["PT"],"is_corresponding":true,"raw_author_name":"Gon\u00e7alo Carnaz","raw_affiliation_strings":["Informatics Departament, University of \u00c9vora, 7002-554 \u00c9vora, Portugal"],"affiliations":[{"raw_affiliation_string":"Informatics Departament, University of \u00c9vora, 7002-554 \u00c9vora, Portugal","institution_ids":["https://openalex.org/I21803372"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085602004","display_name":"M\u00e1rio Antunes","orcid":"https://orcid.org/0000-0003-3448-6726"},"institutions":[{"id":"https://openalex.org/I169427155","display_name":"Instituto Polit\u00e9cnico de Leiria","ror":"https://ror.org/010dvvh94","country_code":"PT","type":"education","lineage":["https://openalex.org/I169427155"]},{"id":"https://openalex.org/I4210166615","display_name":"INESC TEC","ror":"https://ror.org/05fa8ka61","country_code":"PT","type":"nonprofit","lineage":["https://openalex.org/I4210125590","https://openalex.org/I4210166615"]}],"countries":["PT"],"is_corresponding":false,"raw_author_name":"M\u00e1rio Antunes","raw_affiliation_strings":["Computer Science and Communication Research Centre (CIIC), School of Technology and Management, Polytechnic of Leiria, 2411-901 Leiria, Portugal","INESC TEC, CRACS, 4200-465 Porto, Portugal"],"affiliations":[{"raw_affiliation_string":"Computer Science and Communication Research Centre (CIIC), School of Technology and Management, Polytechnic of Leiria, 2411-901 Leiria, Portugal","institution_ids":["https://openalex.org/I169427155"]},{"raw_affiliation_string":"INESC TEC, CRACS, 4200-465 Porto, Portugal","institution_ids":["https://openalex.org/I4210166615"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001771757","display_name":"V\u00edtor Nogueira","orcid":"https://orcid.org/0000-0002-0793-0003"},"institutions":[{"id":"https://openalex.org/I21803372","display_name":"University of \u00c9vora","ror":"https://ror.org/02gyps716","country_code":"PT","type":"education","lineage":["https://openalex.org/I21803372"]}],"countries":["PT"],"is_corresponding":false,"raw_author_name":"Vitor Beires Nogueira","raw_affiliation_strings":["Informatics Departament, University of \u00c9vora, 7002-554 \u00c9vora, Portugal"],"affiliations":[{"raw_affiliation_string":"Informatics Departament, University of \u00c9vora, 7002-554 \u00c9vora, Portugal","institution_ids":["https://openalex.org/I21803372"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5017024705"],"corresponding_institution_ids":["https://openalex.org/I21803372"],"apc_list":{"value":1600,"currency":"CHF","value_usd":1732},"apc_paid":{"value":1600,"currency":"CHF","value_usd":1732},"fwci":0.6998,"has_fulltext":true,"cited_by_count":8,"citation_normalized_percentile":{"value":0.7602059,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"6","issue":"7","first_page":"71","last_page":"71"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9962000250816345,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9962000250816345,"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/T10028","display_name":"Topic Modeling","score":0.9940999746322632,"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/T12034","display_name":"Digital and Cyber Forensics","score":0.991100013256073,"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":0.7676244974136353},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.657335638999939},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.6558147072792053},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6525148153305054},{"id":"https://openalex.org/keywords/digital-forensics","display_name":"Digital forensics","score":0.49574264883995056},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4853273928165436},{"id":"https://openalex.org/keywords/precision-and-recall","display_name":"Precision and recall","score":0.47735002636909485},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.46070945262908936},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.45549237728118896},{"id":"https://openalex.org/keywords/portuguese","display_name":"Portuguese","score":0.4456709027290344},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.11912694573402405}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7676244974136353},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.657335638999939},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.6558147072792053},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6525148153305054},{"id":"https://openalex.org/C84418412","wikidata":"https://www.wikidata.org/wiki/Q3246940","display_name":"Digital forensics","level":2,"score":0.49574264883995056},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4853273928165436},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.47735002636909485},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.46070945262908936},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.45549237728118896},{"id":"https://openalex.org/C35219183","wikidata":"https://www.wikidata.org/wiki/Q5146","display_name":"Portuguese","level":2,"score":0.4456709027290344},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.11912694573402405},{"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.3390/data6070071","is_oa":true,"landing_page_url":"https://doi.org/10.3390/data6070071","pdf_url":"https://www.mdpi.com/2306-5729/6/7/71/pdf?version=1624864915","source":{"id":"https://openalex.org/S4210226510","display_name":"Data","issn_l":"2306-5729","issn":["2306-5729"],"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":"Data","raw_type":"journal-article"},{"id":"pmh:oai:RePEc:gam:jdataj:v:6:y:2021:i:7:p:71-:d:582700","is_oa":false,"landing_page_url":"https://www.mdpi.com/2306-5729/6/7/71/","pdf_url":null,"source":{"id":"https://openalex.org/S4306401271","display_name":"RePEc: Research Papers in Economics","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I77793887","host_organization_name":"Federal Reserve Bank of St. Louis","host_organization_lineage":["https://openalex.org/I77793887"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},{"id":"pmh:oai:doaj.org/article:3e7b233000eb4b468fd97b74daae58fc","is_oa":true,"landing_page_url":"https://doaj.org/article/3e7b233000eb4b468fd97b74daae58fc","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-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Data, Vol 6, Iss 7, p 71 (2021)","raw_type":"article"},{"id":"pmh:oai:dspace.uevora.pt:10174/34695","is_oa":true,"landing_page_url":"http://hdl.handle.net/10174/34695","pdf_url":null,"source":{"id":"https://openalex.org/S4306401462","display_name":"Repositorio Universidade de \u00c9vora (Universidade de \u00c9vora)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I21803372","host_organization_name":"University of \u00c9vora","host_organization_lineage":["https://openalex.org/I21803372"],"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":"journal article"},{"id":"pmh:oai:mdpi.com:/2306-5729/6/7/71/","is_oa":true,"landing_page_url":"https://dx.doi.org/10.3390/data6070071","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":"Data; Volume 6; Issue 7; Pages: 71","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.3390/data6070071","is_oa":true,"landing_page_url":"https://doi.org/10.3390/data6070071","pdf_url":"https://www.mdpi.com/2306-5729/6/7/71/pdf?version=1624864915","source":{"id":"https://openalex.org/S4210226510","display_name":"Data","issn_l":"2306-5729","issn":["2306-5729"],"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":"Data","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.7200000286102295,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3174885571.pdf","grobid_xml":"https://content.openalex.org/works/W3174885571.grobid-xml"},"referenced_works_count":23,"referenced_works":["https://openalex.org/W1958417223","https://openalex.org/W2000621030","https://openalex.org/W2028401451","https://openalex.org/W2074952134","https://openalex.org/W2165662062","https://openalex.org/W2186832478","https://openalex.org/W2263493467","https://openalex.org/W2734366781","https://openalex.org/W2791442904","https://openalex.org/W2795766013","https://openalex.org/W2891320405","https://openalex.org/W2898895568","https://openalex.org/W2964018178","https://openalex.org/W2966180739","https://openalex.org/W3161659865","https://openalex.org/W3168066948","https://openalex.org/W6640884837","https://openalex.org/W6650448872","https://openalex.org/W6686767719","https://openalex.org/W6692953190","https://openalex.org/W6741187777","https://openalex.org/W6756204902","https://openalex.org/W6795224647"],"related_works":["https://openalex.org/W2357241418","https://openalex.org/W2590076418","https://openalex.org/W2789919619","https://openalex.org/W2086064646","https://openalex.org/W2001121861","https://openalex.org/W154076710","https://openalex.org/W2010727036","https://openalex.org/W1640588838","https://openalex.org/W1983267954","https://openalex.org/W2737136173"],"abstract_inverted_index":{"Criminal":[0],"investigations":[1],"collect":[2,184],"and":[3,27,42,45,54,66,73,104,169,189,197,206,234,240,244,257],"analyze":[4],"the":[5,13,38,80,93,99,137,177,213,216,221,248,263],"facts":[6],"related":[7,261],"to":[8,18,59,63,92,112,132,183,229,242,262],"a":[9,25,89,117,126,158,198],"crime,":[10],"from":[11,167,187],"which":[12,30,110,164],"investigators":[14],"can":[15,226],"deduce":[16],"evidence":[17,34],"be":[19,60,227],"used":[20],"in":[21,79,136,220,247],"court.":[22],"It":[23],"is":[24,88],"multidisciplinary":[26],"applied":[28],"science,":[29],"includes":[31],"interviews,":[32],"interrogations,":[33],"collection,":[35],"preservation":[36],"of":[37,40,47,85,102,109,120,157,160,179,201,204,208,215,259],"chain":[39],"custody,":[41],"other":[43,74],"methods":[44,239],"techniques":[46,50],"investigation.":[48,81],"These":[49],"produce":[51],"both":[52],"digital":[53],"paper":[55,151],"documents":[56,87],"that":[57,76,145],"have":[58,125],"carefully":[61],"analyzed":[62],"identify":[64,113],"correlations":[65],"interactions":[67],"among":[68],"suspects,":[69],"places,":[70],"license":[71],"plates,":[72],"entities":[75,103,246],"are":[77,130,252],"mentioned":[78],"The":[82,172,193],"computerized":[83],"processing":[84],"these":[86],"helping":[90],"hand":[91],"criminal":[94,134,264],"investigation,":[95],"as":[96,140,176],"it":[97],"allows":[98],"automatic":[100],"identification":[101,258],"their":[105],"relations,":[106],"being":[107],"some":[108],"difficult":[111],"manually.":[114],"There":[115],"exists":[116],"wide":[118],"set":[119],"dedicated":[121],"tools,":[122],"but":[123],"they":[124,129],"major":[127],"limitation:":[128],"unable":[131],"process":[133],"reports":[135],"Portuguese":[138],"language,":[139],"an":[141,153,180],"annotated":[142,154,217],"corpus":[143,225],"for":[144],"purpose":[146],"does":[147],"not":[148],"exist.":[149],"This":[150,224],"presents":[152],"corpus,":[155],"composed":[156],"collection":[159],"anonymized":[161],"crime-related":[162,185,222],"documents,":[163],"were":[165,210],"extracted":[166],"official":[168],"open":[170],"sources.":[171],"dataset":[173,194],"was":[174,195],"produced":[175],"result":[178],"exploratory":[181],"initiative":[182],"data":[186],"websites":[188],"conditioned-access":[190],"police":[191],"reports.":[192],"evaluated":[196],"mean":[199],"precision":[200],"0.808,":[202],"recall":[203],"0.722,":[205],"F1-score":[207],"0.733":[209],"obtained":[211],"with":[212],"classification":[214],"named-entities":[218],"present":[219],"documents.":[223,249],"employed":[228],"benchmark":[230],"Machine":[231],"Learning":[232],"(ML)":[233],"Natural":[235],"Language":[236],"Processing":[237],"(NLP)":[238],"tools":[241],"detect":[243],"correlate":[245],"Some":[250],"examples":[251],"sentence":[253],"detection,":[254],"named-entity":[255],"recognition,":[256],"terms":[260],"domain.":[265]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}
