{"id":"https://openalex.org/W3158161591","doi":"https://doi.org/10.5220/0010524503590366","title":"Automated Data Extraction from PDF Documents: Application to Large Sets of Educational Tests","display_name":"Automated Data Extraction from PDF Documents: Application to Large Sets of Educational Tests","publication_year":2021,"publication_date":"2021-01-01","ids":{"openalex":"https://openalex.org/W3158161591","doi":"https://doi.org/10.5220/0010524503590366","mag":"3158161591"},"language":"en","primary_location":{"id":"doi:10.5220/0010524503590366","is_oa":false,"landing_page_url":"https://doi.org/10.5220/0010524503590366","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 23rd International Conference on Enterprise Information Systems","raw_type":"proceedings-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/A5018381202","display_name":"Karina Wiechork","orcid":null},"institutions":[{"id":"https://openalex.org/I33501960","display_name":"Universidade Federal de Santa Maria","ror":"https://ror.org/01b78mz79","country_code":"BR","type":"education","lineage":["https://openalex.org/I33501960"]},{"id":"https://openalex.org/I4210147797","display_name":"Instituto Federal Farroupilha","ror":"https://ror.org/04eq71r04","country_code":"BR","type":"education","lineage":["https://openalex.org/I4210147797"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Karina Wiechork","raw_affiliation_strings":["Department of Languages and Computer Systems, Federal University of Santa Maria, Santa Maria, Brazil, --- Select a Country ---","Information Technology Coordination, Federal Institute of Education Science and Technology Farroupilha, Frederico Westphalen, Brazil, --- Select a Country ---"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Languages and Computer Systems, Federal University of Santa Maria, Santa Maria, Brazil, --- Select a Country ---","institution_ids":["https://openalex.org/I33501960"]},{"raw_affiliation_string":"Information Technology Coordination, Federal Institute of Education Science and Technology Farroupilha, Frederico Westphalen, Brazil, --- Select a Country ---","institution_ids":["https://openalex.org/I4210147797"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5058784082","display_name":"Andr\u00e9a Schwertner Char\u00e3o","orcid":"https://orcid.org/0000-0003-3695-8547"},"institutions":[{"id":"https://openalex.org/I33501960","display_name":"Universidade Federal de Santa Maria","ror":"https://ror.org/01b78mz79","country_code":"BR","type":"education","lineage":["https://openalex.org/I33501960"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Andrea Char\u00e3o","raw_affiliation_strings":["Department of Languages and Computer Systems, Federal University of Santa Maria, Santa Maria, Brazil, --- Select a Country ---"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Languages and Computer Systems, Federal University of Santa Maria, Santa Maria, Brazil, --- Select a Country ---","institution_ids":["https://openalex.org/I33501960"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.6089,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.71670279,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"359","last_page":"366"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13523","display_name":"Mathematics, Computing, and Information Processing","score":0.9534000158309937,"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"}},"topics":[{"id":"https://openalex.org/T13523","display_name":"Mathematics, Computing, and Information Processing","score":0.9534000158309937,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9426000118255615,"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"}},{"id":"https://openalex.org/T11122","display_name":"Online Learning and Analytics","score":0.9348999857902527,"subfield":{"id":"https://openalex.org/subfields/1706","display_name":"Computer Science Applications"},"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":0.777957558631897},{"id":"https://openalex.org/keywords/extraction","display_name":"Extraction (chemistry)","score":0.4872671365737915},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4665778577327728},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3703632652759552},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.3492405414581299}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.777957558631897},{"id":"https://openalex.org/C4725764","wikidata":"https://www.wikidata.org/wiki/Q844704","display_name":"Extraction (chemistry)","level":2,"score":0.4872671365737915},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4665778577327728},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3703632652759552},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.3492405414581299},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.5220/0010524503590366","is_oa":false,"landing_page_url":"https://doi.org/10.5220/0010524503590366","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 23rd International Conference on Enterprise Information Systems","raw_type":"proceedings-article"},{"id":"pmh:oai:repositorio.ufsm.br:1/23130","is_oa":false,"landing_page_url":"http://repositorio.ufsm.br/handle/1/23130","pdf_url":null,"source":{"id":"https://openalex.org/S4306402641","display_name":"LA Referencia (Red Federada de Repositorios Institucionales de Publicaciones Cient\u00edficas)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4383465926","host_organization_name":"LA Referencia","host_organization_lineage":["https://openalex.org/I4383465926"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"instacron:UFSM","raw_type":"info:eu-repo/semantics/masterThesis"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.6499999761581421,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W2382290278","https://openalex.org/W2478288626","https://openalex.org/W2350741829","https://openalex.org/W2530322880","https://openalex.org/W1596801655"],"abstract_inverted_index":{"The":[0,138,225,270],"massive":[1],"production":[2],"of":[3,13,42,53,56,66,96,170,188,212,216,221,223,227,239,244,246],"documents":[4,97],"in":[5,16,25,45,63,117,153,173,190,204,234,241,252,259,267,288,309],"PDF":[6,26,46,112,205],"has":[7],"motivated":[8],"research":[9,33],"on":[10,262],"automated":[11],"extraction":[12,114],"data":[14,113,202,272],"contained":[15],"these":[17,292],"files.":[18],"Many":[19],"educational":[20,119,125],"tests":[21,23,126],"use":[22,291],"available":[24,116],"format,":[27],"which":[28,276],"serve":[29],"as":[30,50,297,299],"study":[31,283],"and":[32,37,69,73,79,150,219,254],"material.":[34],"Segmenting,":[35],"identifying":[36,253],"automatically":[38],"extracting":[39,255],"the":[40,51,64,124,133,142,164,168,174,176,186,194,228,237,247,250,263],"content":[41,218],"a":[43,48,93,100],"test":[44,120],"represents":[47],"challenge,":[49],"layout":[52,240],"this":[54,86],"type":[55],"document":[57,67],"can":[58,82,277],"have":[59,76],"many":[60],"variations.":[61],"Research":[62],"areas":[65],"analysis":[68],"recognition,":[70],"computer":[71],"vision":[72],"information":[74],"retrieval":[75],"produced":[77],"algorithms":[78],"tools":[80,197],"that":[81,200],"be":[83],"applied":[84,127],"to":[85,108,136,155,184,236,282,290,303],"task,":[87],"but":[88],"determining":[89],"their":[90],"effectiveness":[91],"for":[92,141,208,284,294],"given":[94],"set":[95],"is":[98,183],"not":[99],"trivial":[101],"task.":[102],"This":[103],"work":[104],"proposes":[105],"an":[106],"approach":[107],"evaluate":[109],"native":[110],"digital":[111],"tools,":[115],"large":[118],"repositories.":[121],"For":[122,167,193],"this,":[123],"at":[128],"Enade":[129,248],"were":[130,198],"used,":[131,180],"between":[132],"years":[134],"2004":[135],"2019.":[137],"files":[139],"used":[140,199],"evaluation":[143],"comprise":[144],"343":[145],"tests,":[146,175,286],"with":[147,159],"11.196":[148],"objective":[149],"discursive":[151],"questions,":[152],"addition":[154],"all":[156],"396":[157],"answers,":[158],"14.475":[160],"alternatives":[161],"extracted":[162,271],"from":[163,307],"questions":[165,256,293,308],"objectives.":[166],"construction":[169],"ground":[171],"truth":[172],"Aletheia":[177],"tool":[178],"was":[179],"whose":[181],"purpose":[182],"define":[185],"regions":[187,222],"interest":[189],"each":[191,242],"question.":[192],"extractions,":[195],"existing":[196],"perform":[201],"extractions":[203,211,215,220,229],"files,":[206],"defined":[207],"three":[209],"categories:":[210],"tabular":[213],"data,":[214],"textual":[217],"interest.":[224],"results":[226],"point":[230],"out":[231],"some":[232],"limitations":[233],"relation":[235],"diversity":[238],"year":[243],"application":[245],"test,":[249],"difficulty":[251],"when":[257],"arranged":[258],"two":[260],"columns":[261],"same":[264],"page":[265],"or":[266],"multiple":[268],"columns.":[269],"provide":[273],"useful":[274],"information,":[275],"assist":[278],"students":[279],"who":[280],"intend":[281],"other":[285],"teachers":[287],"order":[289],"classroom":[295],"exercises,":[296],"well":[298],"course":[300],"coordinators":[301],"helping":[302],"map":[304],"students\u2019":[305],"difficulties":[306],"reports.":[310]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
