{"id":"https://openalex.org/W2947952067","doi":"https://doi.org/10.5220/0007720301900199","title":"Extraction and Multidimensional Analysis of Data from Unstructured Data Sources: A Case Study","display_name":"Extraction and Multidimensional Analysis of Data from Unstructured Data Sources: A Case Study","publication_year":2019,"publication_date":"2019-01-01","ids":{"openalex":"https://openalex.org/W2947952067","doi":"https://doi.org/10.5220/0007720301900199","mag":"2947952067"},"language":"en","primary_location":{"id":"doi:10.5220/0007720301900199","is_oa":true,"landing_page_url":"https://doi.org/10.5220/0007720301900199","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 21st International Conference on Enterprise Information Systems","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.5220/0007720301900199","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5053345866","display_name":"Rui Lima","orcid":"https://orcid.org/0000-0002-9452-7887"},"institutions":[{"id":"https://openalex.org/I192341844","display_name":"Polytechnic Institute of Viana do Castelo","ror":"https://ror.org/03w6kry90","country_code":"PT","type":"education","lineage":["https://openalex.org/I192341844"]}],"countries":["PT"],"is_corresponding":false,"raw_author_name":"Rui Lima","raw_affiliation_strings":["ARC4DigiT - Applied Research Centre for Digital Transformation, Instituto Polit\u00e9cnico de Viana do Castelo and Portugal, --- Select a Country ---"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ARC4DigiT - Applied Research Centre for Digital Transformation, Instituto Polit\u00e9cnico de Viana do Castelo and Portugal, --- Select a Country ---","institution_ids":["https://openalex.org/I192341844"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019180093","display_name":"Estrela Ferreira Cruz","orcid":"https://orcid.org/0000-0001-6426-9939"},"institutions":[{"id":"https://openalex.org/I192341844","display_name":"Polytechnic Institute of Viana do Castelo","ror":"https://ror.org/03w6kry90","country_code":"PT","type":"education","lineage":["https://openalex.org/I192341844"]},{"id":"https://openalex.org/I99682543","display_name":"University of Minho","ror":"https://ror.org/037wpkx04","country_code":"PT","type":"education","lineage":["https://openalex.org/I99682543"]}],"countries":["PT"],"is_corresponding":false,"raw_author_name":"Estrela Cruz","raw_affiliation_strings":["ARC4DigiT - Applied Research Centre for Digital Transformation, Instituto Polit\u00e9cnico de Viana do Castelo, Portugal, ALGORITMI Research Centre, Escola de Engenharia, Universidade do Minho, Guimar\u00e3es and Portugal, --- Select a Country ---"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ARC4DigiT - Applied Research Centre for Digital Transformation, Instituto Polit\u00e9cnico de Viana do Castelo, Portugal, ALGORITMI Research Centre, Escola de Engenharia, Universidade do Minho, Guimar\u00e3es and Portugal, --- Select a Country ---","institution_ids":["https://openalex.org/I192341844","https://openalex.org/I99682543"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.06626703,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"190","last_page":"199"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9681000113487244,"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"}},"topics":[{"id":"https://openalex.org/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9681000113487244,"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/T12205","display_name":"Time Series Analysis and Forecasting","score":0.9546999931335449,"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/T11106","display_name":"Data Management and Algorithms","score":0.9456999897956848,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7707558870315552},{"id":"https://openalex.org/keywords/data-warehouse","display_name":"Data warehouse","score":0.6274105310440063},{"id":"https://openalex.org/keywords/data-extraction","display_name":"Data extraction","score":0.627128005027771},{"id":"https://openalex.org/keywords/unstructured-data","display_name":"Unstructured data","score":0.6062175631523132},{"id":"https://openalex.org/keywords/aggregate","display_name":"Aggregate (composite)","score":0.5529317855834961},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.5325241088867188},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5149539113044739},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5062927007675171},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.49580153822898865},{"id":"https://openalex.org/keywords/business-intelligence","display_name":"Business intelligence","score":0.47538983821868896},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.4627630114555359},{"id":"https://openalex.org/keywords/data-source","display_name":"Data source","score":0.4324050843715668},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.4047905206680298},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.21902874112129211}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7707558870315552},{"id":"https://openalex.org/C135572916","wikidata":"https://www.wikidata.org/wiki/Q193351","display_name":"Data warehouse","level":2,"score":0.6274105310440063},{"id":"https://openalex.org/C2777466982","wikidata":"https://www.wikidata.org/wiki/Q5227287","display_name":"Data extraction","level":3,"score":0.627128005027771},{"id":"https://openalex.org/C2781252014","wikidata":"https://www.wikidata.org/wiki/Q1141900","display_name":"Unstructured data","level":3,"score":0.6062175631523132},{"id":"https://openalex.org/C4679612","wikidata":"https://www.wikidata.org/wiki/Q866298","display_name":"Aggregate (composite)","level":2,"score":0.5529317855834961},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.5325241088867188},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5149539113044739},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5062927007675171},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.49580153822898865},{"id":"https://openalex.org/C2767350","wikidata":"https://www.wikidata.org/wiki/Q6662173","display_name":"Business intelligence","level":2,"score":0.47538983821868896},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.4627630114555359},{"id":"https://openalex.org/C2983685735","wikidata":"https://www.wikidata.org/wiki/Q5227355","display_name":"Data source","level":2,"score":0.4324050843715668},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.4047905206680298},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.21902874112129211},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","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/C2779473830","wikidata":"https://www.wikidata.org/wiki/Q1540899","display_name":"MEDLINE","level":2,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.5220/0007720301900199","is_oa":true,"landing_page_url":"https://doi.org/10.5220/0007720301900199","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 21st International Conference on Enterprise Information Systems","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.5220/0007720301900199","is_oa":true,"landing_page_url":"https://doi.org/10.5220/0007720301900199","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 21st International Conference on Enterprise Information Systems","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2030910246","https://openalex.org/W4389912246","https://openalex.org/W2982149480","https://openalex.org/W4205553786","https://openalex.org/W4389221653","https://openalex.org/W2372366649","https://openalex.org/W4316660311","https://openalex.org/W3155464240","https://openalex.org/W4362731990","https://openalex.org/W4206851959"],"abstract_inverted_index":{"This":[0],"paper":[1],"proposes":[2,153],"an":[3,154],"approach":[4],"to":[5,17,72,76,93,173],"detect":[6],"and":[7,22,28,30,54,80,83,138,166,175,180],"extract":[8],"data":[9,12,33,60],"from":[10],"unstructured":[11],"source":[13],"(about":[14],"the":[15,32,51,74,78,107,121,124,170,178,185,189],"subject":[16],"be":[18,62],"studied)":[19],"available":[20,117],"online":[21],"spread":[23,119],"by":[24,67,98,120,188],"several":[25,125],"Web":[26],"pages":[27],"aggregate":[29],"store":[31],"in":[34,70,104,106,133,184],"a":[35,94],"Data":[36,43,55],"Warehouse":[37,44],"properly":[38],"designed":[39],"for":[40,50],"it.":[41],"The":[42,58,87,111,149],"repository":[45],"will":[46],"serve":[47],"as":[48],"basis":[49],"Business":[52],"Intelligence":[53],"Mining":[56],"analysis.":[57],"extracted":[59],"may":[61],"complemented":[63],"with":[64,143,162],"information":[65,75],"provided":[66],"other":[68],"sources":[69],"order":[71],"enrich":[73],"enhance":[77],"analysis":[79],"draw":[81],"new":[82],"more":[84],"interesting":[85],"conclusions.":[86],"proposed":[88],"process":[89],"is":[90],"then":[91],"applied":[92],"case":[95,150],"study":[96,151],"composed":[97],"results":[99,158,186],"of":[100,123,159,169],"athletics":[101,126,160],"events":[102,161,171],"realized":[103],"Portugal":[105],"last":[108],"12":[109],"years.":[110],"files,":[112],"about":[113],"competition":[114],"results,":[115],"are":[116,131],"online,":[118],"websites":[122],"associations.":[127],"Almost":[128],"all":[129],"files":[130,142],"published":[132],"portable":[134],"document":[135],"format":[136],"(PDF)":[137],"each":[139],"association":[140],"provides":[141],"its":[144],"own":[145],"different":[146],"internal":[147],"format.":[148],"also":[152],"integrating":[155],"mechanism":[156],"between":[157],"their":[163],"geographic":[164],"location":[165],"atmospheric":[167,179],"conditions":[168,182],"allowing":[172],"assess":[174],"analyze":[176],"how":[177],"geographical":[181],"interfere":[183],"achieved":[187],"athletes.":[190]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
