{"id":"https://openalex.org/W2944134933","doi":"https://doi.org/10.1109/tbdata.2019.2907588","title":"Incorporating Data Context to Cost-Effectively Automate End-to-End Data Wrangling","display_name":"Incorporating Data Context to Cost-Effectively Automate End-to-End Data Wrangling","publication_year":2019,"publication_date":"2019-05-08","ids":{"openalex":"https://openalex.org/W2944134933","doi":"https://doi.org/10.1109/tbdata.2019.2907588","mag":"2944134933"},"language":"en","primary_location":{"id":"doi:10.1109/tbdata.2019.2907588","is_oa":true,"landing_page_url":"https://doi.org/10.1109/tbdata.2019.2907588","pdf_url":"https://ieeexplore.ieee.org/ielx7/6687317/9366322/08691825.pdf","source":{"id":"https://openalex.org/S2491400915","display_name":"IEEE Transactions on Big Data","issn_l":"2332-7790","issn":["2332-7790","2372-2096"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Big Data","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://ieeexplore.ieee.org/ielx7/6687317/9366322/08691825.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5032869679","display_name":"Martin Koehler","orcid":"https://orcid.org/0000-0003-0377-9008"},"institutions":[{"id":"https://openalex.org/I28407311","display_name":"University of Manchester","ror":"https://ror.org/027m9bs27","country_code":"GB","type":"education","lineage":["https://openalex.org/I28407311"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Martin Koehler","raw_affiliation_strings":["Information Management Group, School of Computer Science, University of Manchester, Manchester, United Kingdom"],"raw_orcid":"https://orcid.org/0000-0003-0377-9008","affiliations":[{"raw_affiliation_string":"Information Management Group, School of Computer Science, University of Manchester, Manchester, United Kingdom","institution_ids":["https://openalex.org/I28407311"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070591199","display_name":"E. W. Abel","orcid":"https://orcid.org/0000-0002-3694-5116"},"institutions":[{"id":"https://openalex.org/I28407311","display_name":"University of Manchester","ror":"https://ror.org/027m9bs27","country_code":"GB","type":"education","lineage":["https://openalex.org/I28407311"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Edward Abel","raw_affiliation_strings":["Information Management Group, School of Computer Science, University of Manchester, Manchester, United Kingdom"],"raw_orcid":"https://orcid.org/0000-0002-3694-5116","affiliations":[{"raw_affiliation_string":"Information Management Group, School of Computer Science, University of Manchester, Manchester, United Kingdom","institution_ids":["https://openalex.org/I28407311"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020308111","display_name":"Alex Bogatu","orcid":"https://orcid.org/0000-0003-1604-5097"},"institutions":[{"id":"https://openalex.org/I28407311","display_name":"University of Manchester","ror":"https://ror.org/027m9bs27","country_code":"GB","type":"education","lineage":["https://openalex.org/I28407311"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Alex Bogatu","raw_affiliation_strings":["Information Management Group, School of Computer Science, University of Manchester, Manchester, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Information Management Group, School of Computer Science, University of Manchester, Manchester, United Kingdom","institution_ids":["https://openalex.org/I28407311"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020613765","display_name":"Cristina Civili","orcid":"https://orcid.org/0000-0002-4357-3509"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Cristina Civili","raw_affiliation_strings":["School of Informatics, University of Edinburgh, Edinburgh, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Informatics, University of Edinburgh, Edinburgh, United Kingdom","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062787907","display_name":"Lacramioara Mazilu","orcid":"https://orcid.org/0000-0003-2415-6336"},"institutions":[{"id":"https://openalex.org/I28407311","display_name":"University of Manchester","ror":"https://ror.org/027m9bs27","country_code":"GB","type":"education","lineage":["https://openalex.org/I28407311"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Lacramioara Mazilu","raw_affiliation_strings":["Information Management Group, School of Computer Science, University of Manchester, Manchester, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Information Management Group, School of Computer Science, University of Manchester, Manchester, United Kingdom","institution_ids":["https://openalex.org/I28407311"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010193726","display_name":"\u039d\u03b9\u03ba\u03cc\u03bb\u03b1\u03bf\u03c2 \u039a\u03c9\u03bd\u03c3\u03c4\u03b1\u03bd\u03c4\u03af\u03bd\u03bf\u03c5","orcid":"https://orcid.org/0000-0003-3742-9276"},"institutions":[{"id":"https://openalex.org/I28407311","display_name":"University of Manchester","ror":"https://ror.org/027m9bs27","country_code":"GB","type":"education","lineage":["https://openalex.org/I28407311"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Nikolaos Konstantinou","raw_affiliation_strings":["Information Management Group, School of Computer Science, University of Manchester, Manchester, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Information Management Group, School of Computer Science, University of Manchester, Manchester, United Kingdom","institution_ids":["https://openalex.org/I28407311"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057541402","display_name":"Alvaro A. A. Fernandes","orcid":"https://orcid.org/0000-0002-6100-7199"},"institutions":[{"id":"https://openalex.org/I28407311","display_name":"University of Manchester","ror":"https://ror.org/027m9bs27","country_code":"GB","type":"education","lineage":["https://openalex.org/I28407311"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Alvaro A.A. Fernandes","raw_affiliation_strings":["Information Management Group, School of Computer Science, University of Manchester, Manchester, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Information Management Group, School of Computer Science, University of Manchester, Manchester, United Kingdom","institution_ids":["https://openalex.org/I28407311"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5105350782","display_name":"John Keane","orcid":"https://orcid.org/0000-0001-9022-4339"},"institutions":[{"id":"https://openalex.org/I28407311","display_name":"University of Manchester","ror":"https://ror.org/027m9bs27","country_code":"GB","type":"education","lineage":["https://openalex.org/I28407311"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"John Keane","raw_affiliation_strings":["Software Systems Group, School of Computer Science, University of Manchester, Manchester, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Software Systems Group, School of Computer Science, University of Manchester, Manchester, United Kingdom","institution_ids":["https://openalex.org/I28407311"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069883356","display_name":"Leonid Libkin","orcid":"https://orcid.org/0000-0002-6698-2735"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Leonid Libkin","raw_affiliation_strings":["School of Informatics, University of Edinburgh, Edinburgh, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Informatics, University of Edinburgh, Edinburgh, United Kingdom","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066619159","display_name":"Norman W. Paton","orcid":"https://orcid.org/0000-0003-2008-6617"},"institutions":[{"id":"https://openalex.org/I28407311","display_name":"University of Manchester","ror":"https://ror.org/027m9bs27","country_code":"GB","type":"education","lineage":["https://openalex.org/I28407311"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Norman W. Paton","raw_affiliation_strings":["Information Management Group, School of Computer Science, University of Manchester, Manchester, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Information Management Group, School of Computer Science, University of Manchester, Manchester, United Kingdom","institution_ids":["https://openalex.org/I28407311"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.9747,"has_fulltext":true,"cited_by_count":20,"citation_normalized_percentile":{"value":0.86845392,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":"7","issue":"1","first_page":"169","last_page":"186"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9988999962806702,"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":0.9988999962806702,"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.996399998664856,"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/T11891","display_name":"Big Data and Business Intelligence","score":0.9908000230789185,"subfield":{"id":"https://openalex.org/subfields/1404","display_name":"Management Information Systems"},"field":{"id":"https://openalex.org/fields/14","display_name":"Business, Management and Accounting"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8465538024902344},{"id":"https://openalex.org/keywords/schema-matching","display_name":"Schema matching","score":0.6673390865325928},{"id":"https://openalex.org/keywords/data-extraction","display_name":"Data extraction","score":0.6637928485870361},{"id":"https://openalex.org/keywords/automation","display_name":"Automation","score":0.582252562046051},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5635320544242859},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5453365445137024},{"id":"https://openalex.org/keywords/data-warehouse","display_name":"Data warehouse","score":0.5173696875572205},{"id":"https://openalex.org/keywords/schema","display_name":"Schema (genetic algorithms)","score":0.4958976209163666},{"id":"https://openalex.org/keywords/data-integration","display_name":"Data integration","score":0.4660414755344391},{"id":"https://openalex.org/keywords/profiling","display_name":"Profiling (computer programming)","score":0.4538099765777588},{"id":"https://openalex.org/keywords/data-validation","display_name":"Data validation","score":0.44527772068977356},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.44176238775253296},{"id":"https://openalex.org/keywords/data-redundancy","display_name":"Data redundancy","score":0.43446269631385803},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.4232906401157379},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4175940752029419},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.3355630338191986},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.24909833073616028}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8465538024902344},{"id":"https://openalex.org/C2777327318","wikidata":"https://www.wikidata.org/wiki/Q1408390","display_name":"Schema matching","level":3,"score":0.6673390865325928},{"id":"https://openalex.org/C2777466982","wikidata":"https://www.wikidata.org/wiki/Q5227287","display_name":"Data extraction","level":3,"score":0.6637928485870361},{"id":"https://openalex.org/C115901376","wikidata":"https://www.wikidata.org/wiki/Q184199","display_name":"Automation","level":2,"score":0.582252562046051},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5635320544242859},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5453365445137024},{"id":"https://openalex.org/C135572916","wikidata":"https://www.wikidata.org/wiki/Q193351","display_name":"Data warehouse","level":2,"score":0.5173696875572205},{"id":"https://openalex.org/C52146309","wikidata":"https://www.wikidata.org/wiki/Q7431116","display_name":"Schema (genetic algorithms)","level":2,"score":0.4958976209163666},{"id":"https://openalex.org/C72634772","wikidata":"https://www.wikidata.org/wiki/Q386824","display_name":"Data integration","level":2,"score":0.4660414755344391},{"id":"https://openalex.org/C187191949","wikidata":"https://www.wikidata.org/wiki/Q1138496","display_name":"Profiling (computer programming)","level":2,"score":0.4538099765777588},{"id":"https://openalex.org/C92446256","wikidata":"https://www.wikidata.org/wiki/Q3306762","display_name":"Data validation","level":2,"score":0.44527772068977356},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.44176238775253296},{"id":"https://openalex.org/C7545210","wikidata":"https://www.wikidata.org/wiki/Q838123","display_name":"Data redundancy","level":2,"score":0.43446269631385803},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.4232906401157379},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4175940752029419},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.3355630338191986},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.24909833073616028},{"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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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/C2779473830","wikidata":"https://www.wikidata.org/wiki/Q1540899","display_name":"MEDLINE","level":2,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","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},{"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/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/tbdata.2019.2907588","is_oa":true,"landing_page_url":"https://doi.org/10.1109/tbdata.2019.2907588","pdf_url":"https://ieeexplore.ieee.org/ielx7/6687317/9366322/08691825.pdf","source":{"id":"https://openalex.org/S2491400915","display_name":"IEEE Transactions on Big Data","issn_l":"2332-7790","issn":["2332-7790","2372-2096"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Big Data","raw_type":"journal-article"},{"id":"pmh:oai:pure.atira.dk:openaire/159691d2-e145-491a-b371-6ea23950474f","is_oa":true,"landing_page_url":"https://research.manchester.ac.uk/en/publications/159691d2-e145-491a-b371-6ea23950474f","pdf_url":null,"source":{"id":"https://openalex.org/S4306400662","display_name":"Research Explorer (The University of Manchester)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I28407311","host_organization_name":"University of Manchester","host_organization_lineage":["https://openalex.org/I28407311"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Koehler, M, Abel, E, Bogatu, A, Civili, C, Mazilu, L, Konstantinou, N, Fernandes, A, Keane, J, Libkin, L & Paton, N 2019, 'Incorporating Data Context to Cost-Effectively Automate End-to-End Data Wrangling', IEEE Transactions on Big Data, vol. 0, no. 0, pp. 1-1. https://doi.org/10.1109/TBDATA.2019.2907588","raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:oai:pure.ed.ac.uk:openaire/fde010ce-d128-4162-a1cb-859c25a3a381","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/fde010ce-d128-4162-a1cb-859c25a3a381","pdf_url":null,"source":{"id":"https://openalex.org/S4306400321","display_name":"Edinburgh Research Explorer (University of Edinburgh)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98677209","host_organization_name":"University of Edinburgh","host_organization_lineage":["https://openalex.org/I98677209"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Koehler, M, Abel, E, Bogatu, A, Civili, C, Mazilu, L, Konstantinou, N, Fernandes, A A A, Keane, J, Libkin, L & Paton, N W 2021, 'Incorporating Data Context to Cost-Effectively Automate End-to-End Data Wrangling', IEEE Transactions on Big Data, vol. 7, no. 1, pp. 169-186. https://doi.org/10.1109/TBDATA.2019.2907588","raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"pmh:oai:pure.ed.ac.uk:publications/fde010ce-d128-4162-a1cb-859c25a3a381","is_oa":true,"landing_page_url":"https://hdl.handle.net/20.500.11820/fde010ce-d128-4162-a1cb-859c25a3a381","pdf_url":null,"source":{"id":"https://openalex.org/S4406922455","display_name":"Edinburgh Research Explorer","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":""}],"best_oa_location":{"id":"doi:10.1109/tbdata.2019.2907588","is_oa":true,"landing_page_url":"https://doi.org/10.1109/tbdata.2019.2907588","pdf_url":"https://ieeexplore.ieee.org/ielx7/6687317/9366322/08691825.pdf","source":{"id":"https://openalex.org/S2491400915","display_name":"IEEE Transactions on Big Data","issn_l":"2332-7790","issn":["2332-7790","2372-2096"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Big Data","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G53695486","display_name":null,"funder_award_id":"EP/N023056/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G5458651130","display_name":null,"funder_award_id":"M025268","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G8298339663","display_name":"VADA: Value Added Data Systems -- Principles and Architecture","funder_award_id":"EP/M025268/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G8400180575","display_name":null,"funder_award_id":"EP/M025268/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G8891597062","display_name":null,"funder_award_id":"EP/M025268/","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2944134933.pdf","grobid_xml":"https://content.openalex.org/works/W2944134933.grobid-xml"},"referenced_works_count":60,"referenced_works":["https://openalex.org/W246024570","https://openalex.org/W1521736627","https://openalex.org/W1965492961","https://openalex.org/W1998982581","https://openalex.org/W2007324466","https://openalex.org/W2009332124","https://openalex.org/W2063705591","https://openalex.org/W2064766209","https://openalex.org/W2073287065","https://openalex.org/W2097874932","https://openalex.org/W2113607096","https://openalex.org/W2126848435","https://openalex.org/W2132525863","https://openalex.org/W2137775416","https://openalex.org/W2140523882","https://openalex.org/W2161163216","https://openalex.org/W2186090720","https://openalex.org/W2296164608","https://openalex.org/W2341832822","https://openalex.org/W2419277694","https://openalex.org/W2427822648","https://openalex.org/W2439326083","https://openalex.org/W2493970676","https://openalex.org/W2544486974","https://openalex.org/W2566506518","https://openalex.org/W2576723740","https://openalex.org/W2584580687","https://openalex.org/W2585438896","https://openalex.org/W2602948783","https://openalex.org/W2605173345","https://openalex.org/W2610818984","https://openalex.org/W2612069656","https://openalex.org/W2612924628","https://openalex.org/W2613536717","https://openalex.org/W2620780799","https://openalex.org/W2626926457","https://openalex.org/W2639544096","https://openalex.org/W2725469321","https://openalex.org/W2744739752","https://openalex.org/W2747119418","https://openalex.org/W2752618741","https://openalex.org/W2769360714","https://openalex.org/W2782832832","https://openalex.org/W2796948984","https://openalex.org/W2798299346","https://openalex.org/W2807198416","https://openalex.org/W2950734068","https://openalex.org/W2963174348","https://openalex.org/W2963435533","https://openalex.org/W4237014379","https://openalex.org/W4237412827","https://openalex.org/W4243303575","https://openalex.org/W6680599078","https://openalex.org/W6680607918","https://openalex.org/W6686415897","https://openalex.org/W6723501177","https://openalex.org/W6731864191","https://openalex.org/W6732710093","https://openalex.org/W6733170484","https://openalex.org/W6763967731"],"related_works":["https://openalex.org/W2165918986","https://openalex.org/W1128683088","https://openalex.org/W3138074544","https://openalex.org/W2372910313","https://openalex.org/W4310041472","https://openalex.org/W2938811602","https://openalex.org/W2036644834","https://openalex.org/W2016611314","https://openalex.org/W2408969024","https://openalex.org/W2080890385"],"abstract_inverted_index":{"The":[0],"process":[1,30,115],"of":[2,47,85,91,98,154,176],"preparing":[3],"potentially":[4],"large":[5],"and":[6,67,142,145,152,157,167],"complex":[7],"data":[8,19,52,86,97,113,118,123,140,166],"sets":[9],"for":[10],"further":[11],"analysis":[12],"or":[13,44],"manual":[14,39],"examination":[15],"is":[16,125],"often":[17],"called":[18],"wrangling.":[20,178],"In":[21,49],"classical":[22],"warehousing":[23],"environments,":[24],"the":[25,78,149,155,161,174],"steps":[26,132],"in":[27,41,77,130,173],"such":[28],"a":[29,83,92,106],"are":[31,101],"carried":[32],"out":[33],"using":[34],"Extract-Transform-Load":[35],"platforms,":[36],"with":[37,95,163],"significant":[38],"involvement":[40],"specifying,":[42],"configuring":[43],"tuning":[45],"many":[46],"them.":[48],"typical":[50],"big":[51],"applications,":[53],"we":[54,159],"need":[55],"to":[56,109,127,147],"ensure":[57],"that":[58,100],"all":[59],"wrangling":[60,114],"steps,":[61],"including":[62],"web":[63],"extraction,":[64],"selection,":[65],"integration":[66],"cleaning,":[68],"benefit":[69],"from":[70],"automation":[71,129],"wherever":[72],"possible.":[73],"Towards":[74],"this":[75],"goal,":[76],"paper":[79],"we:":[80],"(i)":[81],"introduce":[82],"notion":[84],"context,":[87],"which":[88],"associates":[89],"portions":[90],"target":[93],"schema":[94],"extensional":[96],"types":[99],"commonly":[102],"available;":[103],"(ii)":[104],"define":[105],"scalable":[107],"methodology":[108],"bootstrap":[110],"an":[111],"end-to-end":[112],"based":[116],"on":[117],"profiling;":[119],"(iii)":[120],"describe":[121],"how":[122],"context":[124],"used":[126],"inform":[128],"several":[131],"within":[133],"wrangling,":[134],"specifically,":[135],"matching,":[136],"value":[137],"format":[138],"transformation,":[139],"repair,":[141],"mapping":[143],"generation":[144],"selection":[146],"optimise":[148],"accuracy,":[150],"consistency":[151],"relevance":[153],"result;":[156],"(iv)":[158],"evaluate":[160],"approach":[162],"real":[164],"estate":[165],"financial":[168],"data,":[169],"showing":[170],"substantial":[171],"improvements":[172],"results":[175],"automated":[177]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":2}],"updated_date":"2026-07-02T09:51:11.867554","created_date":"2025-10-10T00:00:00"}
