{"id":"https://openalex.org/W2115737424","doi":"https://doi.org/10.1007/978-3-319-25639-9_46","title":"Roomba: An Extensible Framework to Validate and Build Dataset Profiles","display_name":"Roomba: An Extensible Framework to Validate and Build Dataset Profiles","publication_year":2015,"publication_date":"2015-01-01","ids":{"openalex":"https://openalex.org/W2115737424","doi":"https://doi.org/10.1007/978-3-319-25639-9_46","mag":"2115737424"},"language":"en","primary_location":{"id":"doi:10.1007/978-3-319-25639-9_46","is_oa":true,"landing_page_url":"https://doi.org/10.1007/978-3-319-25639-9_46","pdf_url":"https://link.springer.com/content/pdf/10.1007/978-3-319-25639-9_46.pdf","source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/978-3-319-25639-9_46.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5050129866","display_name":"Ahmad Assaf","orcid":null},"institutions":[{"id":"https://openalex.org/I1902872","display_name":"EURECOM","ror":"https://ror.org/00sse7z02","country_code":"FR","type":"education","lineage":["https://openalex.org/I1902872","https://openalex.org/I205703379"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Ahmad Assaf","raw_affiliation_strings":["EURECOM, Sophia Antipolis, France","SAP Labs France, Mougins, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"EURECOM, Sophia Antipolis, France","institution_ids":["https://openalex.org/I1902872"]},{"raw_affiliation_string":"SAP Labs France, Mougins, France","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022574838","display_name":"Rapha\u00ebl Troncy","orcid":"https://orcid.org/0000-0003-0457-1436"},"institutions":[{"id":"https://openalex.org/I1902872","display_name":"EURECOM","ror":"https://ror.org/00sse7z02","country_code":"FR","type":"education","lineage":["https://openalex.org/I1902872","https://openalex.org/I205703379"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Rapha\u00ebl Troncy","raw_affiliation_strings":["EURECOM, Sophia Antipolis, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"EURECOM, Sophia Antipolis, France","institution_ids":["https://openalex.org/I1902872"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5027271719","display_name":"Aline Senart","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Aline Senart","raw_affiliation_strings":["SAP Labs France, Mougins, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SAP Labs France, Mougins, France","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":5000,"currency":"EUR","value_usd":5392},"apc_paid":{"value":5000,"currency":"EUR","value_usd":5392},"fwci":null,"has_fulltext":true,"cited_by_count":19,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"325","last_page":"339"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10215","display_name":"Semantic Web and Ontologies","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T10215","display_name":"Semantic Web and Ontologies","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.9993000030517578,"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":0.9966999888420105,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8965394496917725},{"id":"https://openalex.org/keywords/metadata","display_name":"Metadata","score":0.830035924911499},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5475028157234192},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5358554124832153},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5311943888664246},{"id":"https://openalex.org/keywords/reuse","display_name":"Reuse","score":0.5296271443367004},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.43481141328811646},{"id":"https://openalex.org/keywords/metadata-repository","display_name":"Metadata repository","score":0.410664439201355},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.3412756323814392},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.3208416700363159},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.29057711362838745}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8965394496917725},{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.830035924911499},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5475028157234192},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5358554124832153},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5311943888664246},{"id":"https://openalex.org/C206588197","wikidata":"https://www.wikidata.org/wiki/Q846574","display_name":"Reuse","level":2,"score":0.5296271443367004},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.43481141328811646},{"id":"https://openalex.org/C153048206","wikidata":"https://www.wikidata.org/wiki/Q3454922","display_name":"Metadata repository","level":3,"score":0.410664439201355},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.3412756323814392},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3208416700363159},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.29057711362838745},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1007/978-3-319-25639-9_46","is_oa":true,"landing_page_url":"https://doi.org/10.1007/978-3-319-25639-9_46","pdf_url":"https://link.springer.com/content/pdf/10.1007/978-3-319-25639-9_46.pdf","source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},{"id":"pmh:oai:fr.eurecom:4542","is_oa":false,"landing_page_url":"http://www.eurecom.fr/publication/4542","pdf_url":null,"source":{"id":"https://openalex.org/S4377196942","display_name":"Graduate School and Research Center in Digital Science (EURECOM)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1902872","host_organization_name":"EURECOM","host_organization_lineage":["https://openalex.org/I1902872"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"PROFILES 2015, 2nd International Workshop on Dataset Profiling Federated Search for Linked Data,
\\nMain conference ESWC15, 31 May-4 June 2015, Portoroz, Slovenia","raw_type":"Conference"}],"best_oa_location":{"id":"doi:10.1007/978-3-319-25639-9_46","is_oa":true,"landing_page_url":"https://doi.org/10.1007/978-3-319-25639-9_46","pdf_url":"https://link.springer.com/content/pdf/10.1007/978-3-319-25639-9_46.pdf","source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9","score":0.4300000071525574}],"awards":[],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2115737424.pdf","grobid_xml":"https://content.openalex.org/works/W2115737424.grobid-xml"},"referenced_works_count":25,"referenced_works":["https://openalex.org/W5158979","https://openalex.org/W23305702","https://openalex.org/W140982117","https://openalex.org/W154639948","https://openalex.org/W157799491","https://openalex.org/W191140265","https://openalex.org/W812314648","https://openalex.org/W1482811823","https://openalex.org/W1550792544","https://openalex.org/W1582479658","https://openalex.org/W1805882648","https://openalex.org/W1988497694","https://openalex.org/W2015191210","https://openalex.org/W2017323594","https://openalex.org/W2041714924","https://openalex.org/W2047022284","https://openalex.org/W2125442437","https://openalex.org/W2136679991","https://openalex.org/W2137489006","https://openalex.org/W2146008005","https://openalex.org/W2150822694","https://openalex.org/W2394815666","https://openalex.org/W2400515935","https://openalex.org/W2404566507","https://openalex.org/W2899293404"],"related_works":["https://openalex.org/W1552553528","https://openalex.org/W2183628870","https://openalex.org/W2782431616","https://openalex.org/W3023161639","https://openalex.org/W2008531296","https://openalex.org/W2379265733","https://openalex.org/W2394393789","https://openalex.org/W2374379029","https://openalex.org/W1503116306","https://openalex.org/W4299935056"],"abstract_inverted_index":{"Linked":[0],"Open":[1],"Data":[2],"(LOD)":[3],"has":[4],"emerged":[5],"as":[6,54,56],"one":[7,27],"of":[8,12,25,93,126],"the":[9,16,124,127],"largest":[10],"collections":[11],"interlinked":[13],"datasets":[14],"on":[15],"web.":[17],"In":[18],"order":[19,121],"to":[20,29,31,44,74,122,131],"benefit":[21],"from":[22],"this":[23],"mine":[24],"data,":[26],"needs":[28],"access":[30],"descriptive":[32,111,133],"information":[33,40,69,136],"about":[34],"each":[35],"dataset":[36,49,113,140],"(or":[37],"metadata).":[38],"This":[39,115],"can":[41],"be":[42],"used":[43],"delay":[45],"data":[46,58,77,145],"entropy,":[47],"enhance":[48],"discovery,":[50],"exploration":[51],"and":[52,63,89,109,130,134],"reuse":[53],"well":[55],"helping":[57],"portal":[59],"administrators":[60],"in":[61,91,120],"detecting":[62],"eliminating":[64],"spam.":[65],"However,":[66],"such":[67],"metadata":[68,128],"is":[70],"currently":[71],"very":[72],"limited":[73],"a":[75,101,138],"few":[76],"portals":[78],"where":[79],"they":[80],"are":[81],"usually":[82],"provided":[83,129],"manually,":[84],"thus":[85],"being":[86],"often":[87],"incomplete":[88],"inconsistent":[90],"terms":[92],"quality.":[94],"To":[95],"address":[96],"these":[97],"issues,":[98],"we":[99],"propose":[100],"scalable":[102],"automatic":[103],"approach":[104,116],"for":[105,137,142],"extracting,":[106],"validating,":[107],"correcting":[108],"generating":[110],"linked":[112],"profiles.":[114],"applies":[117],"several":[118],"techniques":[119],"check":[123],"validity":[125],"generate":[132],"statistical":[135],"particular":[139],"or":[141],"an":[143],"entire":[144],"portal.":[146]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":6},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":2}],"updated_date":"2026-07-19T07:52:34.831488","created_date":"2025-10-10T00:00:00"}