{"id":"https://openalex.org/W2892044369","doi":"https://doi.org/10.1145/3243082.3264609","title":"Dealing with Data from Multiple Web Sources","display_name":"Dealing with Data from Multiple Web Sources","publication_year":2018,"publication_date":"2018-09-19","ids":{"openalex":"https://openalex.org/W2892044369","doi":"https://doi.org/10.1145/3243082.3264609","mag":"2892044369"},"language":"en","primary_location":{"id":"doi:10.1145/3243082.3264609","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3243082.3264609","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 24th Brazilian Symposium on Multimedia and the Web","raw_type":"proceedings-article"},"type":"conference-paper","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/A5083964070","display_name":"Nat\u00e9rcia A. Batista","orcid":"https://orcid.org/0000-0001-6035-2620"},"institutions":[{"id":"https://openalex.org/I110200422","display_name":"Universidade Federal de Minas Gerais","ror":"https://ror.org/0176yjw32","country_code":"BR","type":"education","lineage":["https://openalex.org/I110200422"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Nat\u00e9rcia A. Batista","raw_affiliation_strings":["Universidade Federal de Minas Gerais, Belo Horizonte, Minas Gerais, Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universidade Federal de Minas Gerais, Belo Horizonte, Minas Gerais, Brazil","institution_ids":["https://openalex.org/I110200422"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054180602","display_name":"Michele A. Brand\u00e3o","orcid":"https://orcid.org/0000-0001-7808-9357"},"institutions":[{"id":"https://openalex.org/I110200422","display_name":"Universidade Federal de Minas Gerais","ror":"https://ror.org/0176yjw32","country_code":"BR","type":"education","lineage":["https://openalex.org/I110200422"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Michele A. Brand\u00e3o","raw_affiliation_strings":["Universidade Federal de Minas Gerais, Belo Horizonte, Minas Gerais, Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universidade Federal de Minas Gerais, Belo Horizonte, Minas Gerais, Brazil","institution_ids":["https://openalex.org/I110200422"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013669701","display_name":"Michele Brito Pinheiro","orcid":"https://orcid.org/0000-0001-7646-1944"},"institutions":[{"id":"https://openalex.org/I110200422","display_name":"Universidade Federal de Minas Gerais","ror":"https://ror.org/0176yjw32","country_code":"BR","type":"education","lineage":["https://openalex.org/I110200422"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Michele B. Pinheiro","raw_affiliation_strings":["Universidade Federal de Minas Gerais, Belo Horizonte, Minas Gerais, Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universidade Federal de Minas Gerais, Belo Horizonte, Minas Gerais, Brazil","institution_ids":["https://openalex.org/I110200422"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074870464","display_name":"Daniel H. Dalip","orcid":"https://orcid.org/0000-0002-8532-7701"},"institutions":[{"id":"https://openalex.org/I4210136482","display_name":"Federal Center for Technological Education of Minas Gerais","ror":"https://ror.org/04ch49185","country_code":"BR","type":"education","lineage":["https://openalex.org/I4210136482"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Daniel H. Dalip","raw_affiliation_strings":["Centro Federal de Educa\u00e7\u00e3o, Tecnol\u00f3gica de Minas Gerais, Belo Horizonte, Minas Gerais, Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centro Federal de Educa\u00e7\u00e3o, Tecnol\u00f3gica de Minas Gerais, Belo Horizonte, Minas Gerais, Brazil","institution_ids":["https://openalex.org/I4210136482"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5035882771","display_name":"Mirella M. Moro","orcid":"https://orcid.org/0000-0002-0545-2001"},"institutions":[{"id":"https://openalex.org/I110200422","display_name":"Universidade Federal de Minas Gerais","ror":"https://ror.org/0176yjw32","country_code":"BR","type":"education","lineage":["https://openalex.org/I110200422"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Mirella M. Moro","raw_affiliation_strings":["Universidade Federal de Minas Gerais, Belo Horizonte, Minas Gerais, Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universidade Federal de Minas Gerais, Belo Horizonte, Minas Gerais, Brazil","institution_ids":["https://openalex.org/I110200422"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.2075,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.49148215,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"3","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9998000264167786,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9998000264167786,"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.998199999332428,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T11719","display_name":"Data Quality and Management","score":0.9975000023841858,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8570836782455444},{"id":"https://openalex.org/keywords/crawling","display_name":"Crawling","score":0.8321692943572998},{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.7015314102172852},{"id":"https://openalex.org/keywords/data-pre-processing","display_name":"Data pre-processing","score":0.6068018078804016},{"id":"https://openalex.org/keywords/data-integration","display_name":"Data integration","score":0.5980877876281738},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.514426052570343},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5058133602142334},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.4832630753517151},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4498818516731262},{"id":"https://openalex.org/keywords/web-application","display_name":"Web application","score":0.42492204904556274},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.41301584243774414},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.3090139627456665},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.2412232756614685},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.15075567364692688}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8570836782455444},{"id":"https://openalex.org/C100368936","wikidata":"https://www.wikidata.org/wiki/Q1411725","display_name":"Crawling","level":2,"score":0.8321692943572998},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.7015314102172852},{"id":"https://openalex.org/C10551718","wikidata":"https://www.wikidata.org/wiki/Q5227332","display_name":"Data pre-processing","level":2,"score":0.6068018078804016},{"id":"https://openalex.org/C72634772","wikidata":"https://www.wikidata.org/wiki/Q386824","display_name":"Data integration","level":2,"score":0.5980877876281738},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.514426052570343},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5058133602142334},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.4832630753517151},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4498818516731262},{"id":"https://openalex.org/C118643609","wikidata":"https://www.wikidata.org/wiki/Q189210","display_name":"Web application","level":2,"score":0.42492204904556274},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.41301584243774414},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.3090139627456665},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.2412232756614685},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.15075567364692688},{"id":"https://openalex.org/C105702510","wikidata":"https://www.wikidata.org/wiki/Q514","display_name":"Anatomy","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3243082.3264609","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3243082.3264609","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 24th Brazilian Symposium on Multimedia and the Web","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320322025","display_name":"Conselho Nacional de Desenvolvimento Cient\u00edfico e Tecnol\u00f3gico","ror":"https://ror.org/03swz6y49"},{"id":"https://openalex.org/F4320322980","display_name":"Funda\u00e7\u00e3o de Amparo \u00e0 Pesquisa do Estado de Minas Gerais","ror":"https://ror.org/00nc55f03"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W1577231857","https://openalex.org/W1594004601","https://openalex.org/W1847724720","https://openalex.org/W1975143876","https://openalex.org/W2000445859","https://openalex.org/W2069680311","https://openalex.org/W2111355355","https://openalex.org/W2137135938","https://openalex.org/W2612325126","https://openalex.org/W2618923818","https://openalex.org/W2743185377","https://openalex.org/W2743605915","https://openalex.org/W2782978053","https://openalex.org/W2788448133","https://openalex.org/W2791195120","https://openalex.org/W2792609618","https://openalex.org/W2807567790","https://openalex.org/W2951074736","https://openalex.org/W4247640718"],"related_works":["https://openalex.org/W2989490741","https://openalex.org/W3092506759","https://openalex.org/W2367545121","https://openalex.org/W4248881655","https://openalex.org/W2482165163","https://openalex.org/W3010890513","https://openalex.org/W120741642","https://openalex.org/W138569904","https://openalex.org/W2390914021","https://openalex.org/W2389417819"],"abstract_inverted_index":{"Web":[0],"data":[1,10,44,53,64],"are":[2,17,28,37,55],"heterogeneous":[3],"and":[4,13,50,62,85],"unstructured,":[5],"which":[6],"defines":[7],"challenges":[8,84],"for":[9,70],"crawling,":[11,60],"integration":[12],"preprocessing.":[14],"Different":[15],"studies":[16],"\"data-oriented\"":[18],"(i.e.":[19],"based":[20],"on":[21],"the":[22],"available":[23],"data)":[24],"but":[25],"their":[26,31],"results":[27],"restricted":[29],"to":[30,41,47,67],"specific":[32],"data.":[33],"In":[34,57],"contrast,":[35],"there":[36],"various":[38],"problems":[39],"prior":[40],"identifying":[42],"what":[43],"is":[45],"needed":[46],"solve":[48],"them,":[49],"often":[51],"multiple":[52],"sources":[54],"needed.":[56],"this":[58,75],"context,":[59],"integrating":[61],"preprocessing":[63],"appropriately":[65],"enables":[66],"create":[68],"datasets":[69],"solving":[71],"such":[72],"problems.":[73],"Therefore,":[74],"short":[76],"course":[77],"addresses":[78],"these":[79],"three":[80],"activities":[81],"by":[82],"discussing":[83],"practical":[86],"solutions.":[87]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
