{"id":"https://openalex.org/W2048282669","doi":"https://doi.org/10.1145/2509908.2509909","title":"Automatic web spreadsheet data extraction","display_name":"Automatic web spreadsheet data extraction","publication_year":2013,"publication_date":"2013-08-30","ids":{"openalex":"https://openalex.org/W2048282669","doi":"https://doi.org/10.1145/2509908.2509909","mag":"2048282669"},"language":"en","primary_location":{"id":"doi:10.1145/2509908.2509909","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2509908.2509909","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 3rd International Workshop on Semantic Search Over the Web","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/A5100457637","display_name":"Zhe Chen","orcid":"https://orcid.org/0000-0001-5004-8975"},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan\u2013Ann Arbor","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Zhe Chen","raw_affiliation_strings":["University of Michigan, Ann Arbor, MI"],"affiliations":[{"raw_affiliation_string":"University of Michigan, Ann Arbor, MI","institution_ids":["https://openalex.org/I27837315"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5039133265","display_name":"Michael Cafarella","orcid":"https://orcid.org/0000-0001-6122-0590"},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan\u2013Ann Arbor","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael Cafarella","raw_affiliation_strings":["University of Michigan, Ann Arbor, MI"],"affiliations":[{"raw_affiliation_string":"University of Michigan, Ann Arbor, MI","institution_ids":["https://openalex.org/I27837315"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5100457637"],"corresponding_institution_ids":["https://openalex.org/I27837315"],"apc_list":null,"apc_paid":null,"fwci":9.0674,"has_fulltext":false,"cited_by_count":102,"citation_normalized_percentile":{"value":0.98043527,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10317","display_name":"Advanced Database Systems and Queries","score":0.9991000294685364,"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"}},"topics":[{"id":"https://openalex.org/T10317","display_name":"Advanced Database Systems and Queries","score":0.9991000294685364,"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/T13197","display_name":"Spreadsheets and End-User Computing","score":0.9983999729156494,"subfield":{"id":"https://openalex.org/subfields/1712","display_name":"Software"},"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":0.9937999844551086,"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":0.8480932712554932},{"id":"https://openalex.org/keywords/data-extraction","display_name":"Data extraction","score":0.6856223344802856},{"id":"https://openalex.org/keywords/data-integration","display_name":"Data integration","score":0.616397500038147},{"id":"https://openalex.org/keywords/relational-database","display_name":"Relational database","score":0.6134032011032104},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4602223336696625},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4429776966571808},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.42699742317199707},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.38123375177383423}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8480932712554932},{"id":"https://openalex.org/C2777466982","wikidata":"https://www.wikidata.org/wiki/Q5227287","display_name":"Data extraction","level":3,"score":0.6856223344802856},{"id":"https://openalex.org/C72634772","wikidata":"https://www.wikidata.org/wiki/Q386824","display_name":"Data integration","level":2,"score":0.616397500038147},{"id":"https://openalex.org/C5655090","wikidata":"https://www.wikidata.org/wiki/Q192588","display_name":"Relational database","level":2,"score":0.6134032011032104},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4602223336696625},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4429776966571808},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.42699742317199707},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.38123375177383423},{"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},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/2509908.2509909","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2509908.2509909","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 3rd International Workshop on Semantic Search Over the Web","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.388.852","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.388.852","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://web.eecs.umich.edu/~michjc/papers/spreadsheets_ssw2013.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/8","display_name":"Decent work and economic growth","score":0.7699999809265137}],"awards":[{"id":"https://openalex.org/G1323612667","display_name":null,"funder_award_id":"IIS-1054913, IIS-1064606","funder_id":"https://openalex.org/F4320337389","funder_display_name":"Division of Information and Intelligent Systems"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320307783","display_name":"Dow Chemical Company","ror":"https://ror.org/032hx4q18"},{"id":"https://openalex.org/F4320309327","display_name":"Google","ror":"https://ror.org/00njsd438"},{"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":25,"referenced_works":["https://openalex.org/W176528069","https://openalex.org/W1551291454","https://openalex.org/W1974480600","https://openalex.org/W1978492080","https://openalex.org/W2006426998","https://openalex.org/W2010598806","https://openalex.org/W2022141025","https://openalex.org/W2034797903","https://openalex.org/W2039649893","https://openalex.org/W2050427657","https://openalex.org/W2091107180","https://openalex.org/W2097864578","https://openalex.org/W2098516643","https://openalex.org/W2101498152","https://openalex.org/W2102951036","https://openalex.org/W2106895292","https://openalex.org/W2122088005","https://openalex.org/W2133990480","https://openalex.org/W2138187595","https://openalex.org/W2147880316","https://openalex.org/W2153635508","https://openalex.org/W2172240163","https://openalex.org/W6607266271","https://openalex.org/W6633158399","https://openalex.org/W6675485567"],"related_works":["https://openalex.org/W2126133844","https://openalex.org/W2977818562","https://openalex.org/W2155603949","https://openalex.org/W2527777278","https://openalex.org/W2544610230","https://openalex.org/W1971084186","https://openalex.org/W2073277777","https://openalex.org/W3095784589","https://openalex.org/W4205595170","https://openalex.org/W2113336906"],"abstract_inverted_index":{"Spreadsheets":[0],"contain":[1],"a":[2,12],"huge":[3],"amount":[4],"of":[5,25,68],"high-value":[6],"data":[7,14,26,44],"but":[8,30],"do":[9],"not":[10],"observe":[11],"standard":[13],"model":[15],"and":[16],"thus":[17],"are":[18,47],"difficult":[19],"to":[20,51],"integrate.":[21],"A":[22],"large":[23],"number":[24],"integration":[27,54],"tools":[28],"exist,":[29],"they":[31],"generally":[32],"can":[33],"only":[34,63],"work":[35],"on":[36],"relational":[37,43],"data.":[38],"Existing":[39],"systems":[40],"for":[41],"extracting":[42],"from":[45],"spreadsheets":[46],"too":[48],"labor":[49],"intensive":[50],"support":[52],"ad-hoc":[53],"tasks,":[55],"in":[56],"which":[57],"the":[58,66],"correct":[59],"extraction":[60],"target":[61],"is":[62],"learned":[64],"during":[65],"course":[67],"user":[69],"interaction.":[70]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":10},{"year":2021,"cited_by_count":12},{"year":2020,"cited_by_count":11},{"year":2019,"cited_by_count":12},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":11},{"year":2016,"cited_by_count":11},{"year":2015,"cited_by_count":9},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}
