{"id":"https://openalex.org/W2052047294","doi":"https://doi.org/10.4018/ijswis.2014040103","title":"Improving Curated Web-Data Quality with Structured Harvesting and Assessment","display_name":"Improving Curated Web-Data Quality with Structured Harvesting and Assessment","publication_year":2014,"publication_date":"2014-04-01","ids":{"openalex":"https://openalex.org/W2052047294","doi":"https://doi.org/10.4018/ijswis.2014040103","mag":"2052047294"},"language":"en","primary_location":{"id":"doi:10.4018/ijswis.2014040103","is_oa":false,"landing_page_url":"https://doi.org/10.4018/ijswis.2014040103","pdf_url":null,"source":{"id":"https://openalex.org/S181240966","display_name":"International Journal on Semantic Web and Information Systems","issn_l":"1552-6283","issn":["1552-6283","1552-6291"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320424","host_organization_name":"IGI Global","host_organization_lineage":["https://openalex.org/P4310320424"],"host_organization_lineage_names":["IGI Global"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal on Semantic Web and Information Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://hdl.handle.net/2262/76237","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5029916696","display_name":"Kevin Feeney","orcid":"https://orcid.org/0009-0008-1289-8774"},"institutions":[{"id":"https://openalex.org/I205274468","display_name":"Trinity College Dublin","ror":"https://ror.org/02tyrky19","country_code":"IE","type":"education","lineage":["https://openalex.org/I205274468"]}],"countries":["IE"],"is_corresponding":false,"raw_author_name":"Kevin Chekov Feeney","raw_affiliation_strings":["Trinity College Dublin, Dublin, Ireland","Trinity college Dublin, Dublin, Ireland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Trinity College Dublin, Dublin, Ireland","institution_ids":["https://openalex.org/I205274468"]},{"raw_affiliation_string":"Trinity college Dublin, Dublin, Ireland","institution_ids":["https://openalex.org/I205274468"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020871962","display_name":"Declan O\u2019Sullivan","orcid":"https://orcid.org/0000-0003-1090-3548"},"institutions":[{"id":"https://openalex.org/I205274468","display_name":"Trinity College Dublin","ror":"https://ror.org/02tyrky19","country_code":"IE","type":"education","lineage":["https://openalex.org/I205274468"]}],"countries":["IE"],"is_corresponding":false,"raw_author_name":"Declan O'Sullivan","raw_affiliation_strings":["Trinity College Dublin, Dublin, Ireland","Trinity college Dublin, Dublin, Ireland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Trinity College Dublin, Dublin, Ireland","institution_ids":["https://openalex.org/I205274468"]},{"raw_affiliation_string":"Trinity college Dublin, Dublin, Ireland","institution_ids":["https://openalex.org/I205274468"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102190090","display_name":"Wei Tai","orcid":null},"institutions":[{"id":"https://openalex.org/I205274468","display_name":"Trinity College Dublin","ror":"https://ror.org/02tyrky19","country_code":"IE","type":"education","lineage":["https://openalex.org/I205274468"]}],"countries":["IE"],"is_corresponding":false,"raw_author_name":"Wei Tai","raw_affiliation_strings":["Trinity College Dublin, Dublin, Ireland","Trinity college Dublin, Dublin, Ireland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Trinity College Dublin, Dublin, Ireland","institution_ids":["https://openalex.org/I205274468"]},{"raw_affiliation_string":"Trinity college Dublin, Dublin, Ireland","institution_ids":["https://openalex.org/I205274468"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5087699589","display_name":"Rob Brennan","orcid":"https://orcid.org/0000-0001-8236-362X"},"institutions":[{"id":"https://openalex.org/I205274468","display_name":"Trinity College Dublin","ror":"https://ror.org/02tyrky19","country_code":"IE","type":"education","lineage":["https://openalex.org/I205274468"]}],"countries":["IE"],"is_corresponding":false,"raw_author_name":"Rob Brennan","raw_affiliation_strings":["Trinity College Dublin, Dublin, Ireland","Trinity college Dublin, Dublin, Ireland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Trinity College Dublin, Dublin, Ireland","institution_ids":["https://openalex.org/I205274468"]},{"raw_affiliation_string":"Trinity college Dublin, Dublin, Ireland","institution_ids":["https://openalex.org/I205274468"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I205274468"],"apc_list":null,"apc_paid":null,"fwci":5.7572,"has_fulltext":false,"cited_by_count":27,"citation_normalized_percentile":{"value":0.95883332,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"10","issue":"2","first_page":"35","last_page":"62"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9997000098228455,"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":0.9997000098228455,"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/T10215","display_name":"Semantic Web and Ontologies","score":0.9993000030517578,"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.9909999966621399,"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":0.8349292278289795},{"id":"https://openalex.org/keywords/workflow","display_name":"Workflow","score":0.8270962238311768},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.6496875286102295},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.6454658508300781},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.6142218112945557},{"id":"https://openalex.org/keywords/data-quality","display_name":"Data quality","score":0.5346210598945618},{"id":"https://openalex.org/keywords/data-curation","display_name":"Data curation","score":0.5065983533859253},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4279711842536926},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.4139684736728668},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.33083802461624146},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.3244876563549042},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.2808570861816406},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.1084057092666626}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8349292278289795},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.8270962238311768},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.6496875286102295},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.6454658508300781},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.6142218112945557},{"id":"https://openalex.org/C24756922","wikidata":"https://www.wikidata.org/wiki/Q1757694","display_name":"Data quality","level":3,"score":0.5346210598945618},{"id":"https://openalex.org/C91632574","wikidata":"https://www.wikidata.org/wiki/Q15088675","display_name":"Data curation","level":2,"score":0.5065983533859253},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4279711842536926},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.4139684736728668},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.33083802461624146},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.3244876563549042},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.2808570861816406},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.1084057092666626},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","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/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.4018/ijswis.2014040103","is_oa":false,"landing_page_url":"https://doi.org/10.4018/ijswis.2014040103","pdf_url":null,"source":{"id":"https://openalex.org/S181240966","display_name":"International Journal on Semantic Web and Information Systems","issn_l":"1552-6283","issn":["1552-6283","1552-6291"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320424","host_organization_name":"IGI Global","host_organization_lineage":["https://openalex.org/P4310320424"],"host_organization_lineage_names":["IGI Global"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal on Semantic Web and Information Systems","raw_type":"journal-article"},{"id":"pmh:http://www.rian.ie/127759/","is_oa":true,"landing_page_url":"http://hdl.handle.net/2262/76237","pdf_url":null,"source":{"id":"https://openalex.org/S4306400033","display_name":"Arrow@dit (Dublin Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I115570527","host_organization_name":"Dublin Institute of Technology","host_organization_lineage":["https://openalex.org/I115570527"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Kevin Feeney, Declan O'Sullivan, Wei Tai, Rob Brennan, Improving curated web-data quality with structured harvesting and assessment, International Journal On Semantic Web and Information Systems (IJSWIS), 10, 2, 2014, 33 - 60","raw_type":"Journal article"},{"id":"pmh:oai:RePEc:igg:jswis0:v:10:y:2014:i:2:p:35-62","is_oa":false,"landing_page_url":"https://services.igi-global.com/resolvedoi/resolve.aspx?doi=10.4018/ijswis.2014040103","pdf_url":null,"source":{"id":"https://openalex.org/S4306401271","display_name":"RePEc: Research Papers in Economics","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I77793887","host_organization_name":"Federal Reserve Bank of St. Louis","host_organization_lineage":["https://openalex.org/I77793887"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:http://www.rian.ie/127759/","is_oa":true,"landing_page_url":"http://hdl.handle.net/2262/76237","pdf_url":null,"source":{"id":"https://openalex.org/S4306400033","display_name":"Arrow@dit (Dublin Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I115570527","host_organization_name":"Dublin Institute of Technology","host_organization_lineage":["https://openalex.org/I115570527"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Kevin Feeney, Declan O'Sullivan, Wei Tai, Rob Brennan, Improving curated web-data quality with structured harvesting and assessment, International Journal On Semantic Web and Information Systems (IJSWIS), 10, 2, 2014, 33 - 60","raw_type":"Journal article"},"sustainable_development_goals":[{"score":0.5299999713897705,"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W19399978","https://openalex.org/W67122473","https://openalex.org/W105147515","https://openalex.org/W109245773","https://openalex.org/W115858098","https://openalex.org/W1496949948","https://openalex.org/W1643321461","https://openalex.org/W1726650756","https://openalex.org/W1773380474","https://openalex.org/W1913451680","https://openalex.org/W1936754342","https://openalex.org/W1973653891","https://openalex.org/W1977609394","https://openalex.org/W2015191210","https://openalex.org/W2019600686","https://openalex.org/W2024112226","https://openalex.org/W2032191478","https://openalex.org/W2042418169","https://openalex.org/W2059506441","https://openalex.org/W2124627092","https://openalex.org/W2133781513","https://openalex.org/W2133959199","https://openalex.org/W2138186643","https://openalex.org/W2167764583","https://openalex.org/W2397148648","https://openalex.org/W2557515033","https://openalex.org/W3140829898","https://openalex.org/W4240092169","https://openalex.org/W4285719527","https://openalex.org/W6604452468"],"related_works":["https://openalex.org/W1981780420","https://openalex.org/W2182707996","https://openalex.org/W2701062589","https://openalex.org/W45233828","https://openalex.org/W2964988449","https://openalex.org/W4308914582","https://openalex.org/W2135768893","https://openalex.org/W2151834574","https://openalex.org/W176219849","https://openalex.org/W3021414116"],"abstract_inverted_index":{"This":[0],"paper":[1],"describes":[2],"a":[3,49,79,116],"semi-automated":[4],"process,":[5,51],"framework":[6,47,108,141],"and":[7,13,35,53,61,76,133,142,147],"tools":[8,32,134],"for":[9],"harvesting,":[10],"assessing,":[11],"improving":[12],"maintaining":[14],"high-quality":[15],"linked-data.":[16],"The":[17,46,86],"framework,":[18],"known":[19],"as":[20],"DaCura1,":[21],"provides":[22],"dataset":[23,81],"curators,":[24],"who":[25],"may":[26],"not":[27],"be":[28],"knowledge":[29],"engineers,":[30],"with":[31],"to":[33,64,73,99],"collect":[34],"curate":[36],"evolving":[37],"linked":[38],"data":[39,92,121,136,149],"datasets":[40],"that":[41,95,113],"maintain":[42],"quality":[43,93,122,137,150],"over":[44],"time.":[45],"encompasses":[48],"novel":[50],"workflow":[52],"architecture.":[54],"A":[55],"working":[56],"implementation":[57],"has":[58],"been":[59,97],"produced":[60],"applied":[62],"firstly":[63],"the":[65,74,107,127,130],"publication":[66],"of":[67,78,106,119,129],"an":[68,83,139],"existing":[69,101],"social-sciences":[70],"dataset,":[71],"then":[72],"harvesting":[75],"curation":[77],"related":[80],"from":[82],"unstructured":[84],"data-source.":[85],"framework's":[87],"performance":[88],"is":[89],"evaluated":[90],"using":[91],"measures":[94],"have":[96],"developed":[98],"measure":[100],"published":[102],"datasets.":[103],"An":[104],"analysis":[105],"against":[109],"these":[110],"dimensions":[111],"demonstrates":[112],"it":[114],"addresses":[115],"broad":[117],"range":[118],"real-world":[120],"concerns.":[123],"Experimental":[124],"results":[125],"quantify":[126],"impact":[128],"DaCura":[131],"process":[132],"on":[135],"through":[138],"assessment":[140],"methodology":[143],"which":[144],"combines":[145],"automated":[146],"human":[148],"controls.":[151]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":5},{"year":2016,"cited_by_count":5},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":1}],"updated_date":"2026-06-11T06:19:23.411458","created_date":"2025-10-10T00:00:00"}
