{"id":"https://openalex.org/W2024384623","doi":"https://doi.org/10.1145/2533888.2533939","title":"Semantic extraction of geographic data from web tables for big data integration","display_name":"Semantic extraction of geographic data from web tables for big data integration","publication_year":2013,"publication_date":"2013-11-05","ids":{"openalex":"https://openalex.org/W2024384623","doi":"https://doi.org/10.1145/2533888.2533939","mag":"2024384623"},"language":"en","primary_location":{"id":"doi:10.1145/2533888.2533939","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2533888.2533939","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 7th Workshop on Geographic Information Retrieval","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/A5104780631","display_name":"Isabel F. Cruz","orcid":null},"institutions":[{"id":"https://openalex.org/I39422238","display_name":"University of Illinois Chicago","ror":"https://ror.org/02mpq6x41","country_code":"US","type":"education","lineage":["https://openalex.org/I39422238"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Isabel F. Cruz","raw_affiliation_strings":["University of Illinois at Chicago"],"affiliations":[{"raw_affiliation_string":"University of Illinois at Chicago","institution_ids":["https://openalex.org/I39422238"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006546640","display_name":"Venkat R. Ganesh","orcid":null},"institutions":[{"id":"https://openalex.org/I39422238","display_name":"University of Illinois Chicago","ror":"https://ror.org/02mpq6x41","country_code":"US","type":"education","lineage":["https://openalex.org/I39422238"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Venkat R. Ganesh","raw_affiliation_strings":["University of Illinois at Chicago"],"affiliations":[{"raw_affiliation_string":"University of Illinois at Chicago","institution_ids":["https://openalex.org/I39422238"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5053121488","display_name":"Seyed Iman Mirrezaei","orcid":null},"institutions":[{"id":"https://openalex.org/I39422238","display_name":"University of Illinois Chicago","ror":"https://ror.org/02mpq6x41","country_code":"US","type":"education","lineage":["https://openalex.org/I39422238"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Seyed Iman Mirrezaei","raw_affiliation_strings":["University of Illinois at Chicago"],"affiliations":[{"raw_affiliation_string":"University of Illinois at Chicago","institution_ids":["https://openalex.org/I39422238"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5104780631"],"corresponding_institution_ids":["https://openalex.org/I39422238"],"apc_list":null,"apc_paid":null,"fwci":2.561,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":{"value":0.89939351,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"19","last_page":"26"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9961000084877014,"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":0.9961000084877014,"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/T11106","display_name":"Data Management and Algorithms","score":0.9955999851226807,"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/T10757","display_name":"Geographic Information Systems Studies","score":0.995199978351593,"subfield":{"id":"https://openalex.org/subfields/3305","display_name":"Geography, Planning and Development"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/geocoding","display_name":"Geocoding","score":0.7931075096130371},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7714823484420776},{"id":"https://openalex.org/keywords/metadata","display_name":"Metadata","score":0.6713874340057373},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6088204979896545},{"id":"https://openalex.org/keywords/geographic-information-system","display_name":"Geographic information system","score":0.5287810564041138},{"id":"https://openalex.org/keywords/rdf","display_name":"RDF","score":0.52717125415802},{"id":"https://openalex.org/keywords/schema","display_name":"Schema (genetic algorithms)","score":0.519790530204773},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.4688979685306549},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4345468282699585},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.4224667251110077},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.41463056206703186},{"id":"https://openalex.org/keywords/semantic-web","display_name":"Semantic Web","score":0.4011392295360565},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.30753448605537415},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.21124404668807983},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.13423845171928406},{"id":"https://openalex.org/keywords/cartography","display_name":"Cartography","score":0.09854140877723694}],"concepts":[{"id":"https://openalex.org/C42629822","wikidata":"https://www.wikidata.org/wiki/Q1346408","display_name":"Geocoding","level":2,"score":0.7931075096130371},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7714823484420776},{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.6713874340057373},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6088204979896545},{"id":"https://openalex.org/C41856607","wikidata":"https://www.wikidata.org/wiki/Q483130","display_name":"Geographic information system","level":2,"score":0.5287810564041138},{"id":"https://openalex.org/C147497476","wikidata":"https://www.wikidata.org/wiki/Q54872","display_name":"RDF","level":3,"score":0.52717125415802},{"id":"https://openalex.org/C52146309","wikidata":"https://www.wikidata.org/wiki/Q7431116","display_name":"Schema (genetic algorithms)","level":2,"score":0.519790530204773},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.4688979685306549},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4345468282699585},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.4224667251110077},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.41463056206703186},{"id":"https://openalex.org/C2129575","wikidata":"https://www.wikidata.org/wiki/Q54837","display_name":"Semantic Web","level":2,"score":0.4011392295360565},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.30753448605537415},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.21124404668807983},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.13423845171928406},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.09854140877723694}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2533888.2533939","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2533888.2533939","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 7th Workshop on Geographic Information Retrieval","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5099999904632568,"id":"https://metadata.un.org/sdg/11","display_name":"Sustainable cities and communities"}],"awards":[{"id":"https://openalex.org/G6988739170","display_name":null,"funder_award_id":"CCF-1331800, IIS-1213013, IIS-1143926, IIS-0812258","funder_id":"https://openalex.org/F4320337387","funder_display_name":"Division of Computing and Communication Foundations"},{"id":"https://openalex.org/G8909055554","display_name":null,"funder_award_id":"CCF-1331800, IIS-1213013, IIS-1143926, IIS-0812258","funder_id":"https://openalex.org/F4320337389","funder_display_name":"Division of Information and Intelligent Systems"}],"funders":[{"id":"https://openalex.org/F4320337387","display_name":"Division of Computing and Communication Foundations","ror":"https://ror.org/01mng8331"},{"id":"https://openalex.org/F4320337389","display_name":"Division of Information and Intelligent Systems","ror":"https://ror.org/053a2cp42"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W1501251778","https://openalex.org/W1519606823","https://openalex.org/W1523566045","https://openalex.org/W1565645856","https://openalex.org/W1627640994","https://openalex.org/W1632114991","https://openalex.org/W1715730942","https://openalex.org/W1967510258","https://openalex.org/W1971527337","https://openalex.org/W1973749534","https://openalex.org/W1982801501","https://openalex.org/W1990811607","https://openalex.org/W1992079127","https://openalex.org/W2000586878","https://openalex.org/W2001793573","https://openalex.org/W2003869148","https://openalex.org/W2013970953","https://openalex.org/W2022679230","https://openalex.org/W2044904950","https://openalex.org/W2046441607","https://openalex.org/W2082490674","https://openalex.org/W2092364718","https://openalex.org/W2093189534","https://openalex.org/W2102381086","https://openalex.org/W2108223890","https://openalex.org/W2122683221","https://openalex.org/W2125055259","https://openalex.org/W2129826770","https://openalex.org/W2132731949","https://openalex.org/W2133990480","https://openalex.org/W2140004302","https://openalex.org/W2157093342","https://openalex.org/W2188661153","https://openalex.org/W2275216626","https://openalex.org/W2296120208","https://openalex.org/W2343954916","https://openalex.org/W2490033887","https://openalex.org/W3019943686","https://openalex.org/W4239696231","https://openalex.org/W4285719527","https://openalex.org/W6676610031"],"related_works":["https://openalex.org/W10590203","https://openalex.org/W3125352268","https://openalex.org/W1829360400","https://openalex.org/W2558672055","https://openalex.org/W2776293731","https://openalex.org/W2610919777","https://openalex.org/W2965230088","https://openalex.org/W1534806717","https://openalex.org/W4293389049","https://openalex.org/W4243630814"],"abstract_inverted_index":{"There":[0],"are":[1,10,36],"millions":[2],"of":[3,19,44],"web":[4,105],"tables":[5],"with":[6,68,99],"geographic":[7,50,71,90],"data":[8,14,51],"that":[9,77,84],"pertinent":[11],"for":[12],"big":[13],"integration":[15],"in":[16,38,47,127],"a":[17,63,112],"variety":[18],"domain":[20],"applications,":[21],"such":[22],"as":[23,60],"urban":[24],"sustainability,":[25],"transportation":[26],"networks,":[27],"policy":[28],"studies,":[29],"and":[30,41,70,81,114,130],"public":[31],"health.":[32],"These":[33],"tables,":[34],"however,":[35],"heterogeneous":[37],"structure,":[39],"concepts,":[40],"metadata.":[42],"One":[43],"the":[45,53],"challenges":[46],"semantically":[48],"extracting":[49],"is":[52],"need":[54],"to":[55,61,74,88,124,136],"resolve":[56],"these":[57],"heterogeneities":[58],"so":[59],"uncover":[62],"conceptual":[64],"hierarchy,":[65],"metadata":[66],"associated":[67],"instances,":[69],"information---corresponding":[72],"respectively":[73],"ontologies,":[75],"elements":[76],"we":[78,95],"call":[79],"features,":[80],"cell":[82],"values":[83],"can":[85],"be":[86],"used":[87],"identify":[89,108],"coordinates.":[91],"In":[92],"this":[93],"paper,":[94],"present":[96],"an":[97],"architecture":[98],"methods":[100],"to:":[101],"(1)":[102],"extract":[103],"feature-rich":[104],"tables;":[106],"(2)":[107],"features;":[109],"(3)":[110],"construct":[111],"schema":[113],"instances":[115],"using":[116],"RDF;":[117],"(4)":[118],"perform":[119],"geocoding.":[120],"Preliminary":[121],"experiments":[122],"led":[123],"high":[125],"accuracy":[126],"table":[128],"identification":[129],"feature":[131],"naming":[132],"even":[133],"when":[134],"compared":[135],"manual":[137],"evaluation.":[138]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":3}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}
