{"id":"https://openalex.org/W3133805811","doi":"https://doi.org/10.1177/0165551521998636","title":"Improvements for research data repositories: The case of text spam","display_name":"Improvements for research data repositories: The case of text spam","publication_year":2021,"publication_date":"2021-03-02","ids":{"openalex":"https://openalex.org/W3133805811","doi":"https://doi.org/10.1177/0165551521998636","mag":"3133805811"},"language":"en","primary_location":{"id":"doi:10.1177/0165551521998636","is_oa":false,"landing_page_url":"https://doi.org/10.1177/0165551521998636","pdf_url":null,"source":{"id":"https://openalex.org/S68913162","display_name":"Journal of Information Science","issn_l":"0165-5515","issn":["0165-5515","1741-6485"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320017","host_organization_name":"SAGE Publishing","host_organization_lineage":["https://openalex.org/P4310320017"],"host_organization_lineage_names":["SAGE Publishing"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Information Science","raw_type":"journal-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/A5016931382","display_name":"I. Landesa Vazquez","orcid":null},"institutions":[{"id":"https://openalex.org/I6289922","display_name":"Universidade de Vigo","ror":"https://ror.org/05rdf8595","country_code":"ES","type":"education","lineage":["https://openalex.org/I6289922"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Ismael V\u00e1zquez","raw_affiliation_strings":["Department of Computer Science, University of Vigo, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Vigo, Spain","institution_ids":["https://openalex.org/I6289922"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050515222","display_name":"Mar\u00eda Novo-Lour\u00e9s","orcid":null},"institutions":[{"id":"https://openalex.org/I4210091478","display_name":"Galicia Sur Biomedical Foundation","ror":"https://ror.org/00jdfsf63","country_code":"ES","type":"other","lineage":["https://openalex.org/I4210091478"]},{"id":"https://openalex.org/I4210158352","display_name":"Servicio Gallego de Salud","ror":"https://ror.org/0591s4t67","country_code":"ES","type":"healthcare","lineage":["https://openalex.org/I4210158352"]},{"id":"https://openalex.org/I6289922","display_name":"Universidade de Vigo","ror":"https://ror.org/05rdf8595","country_code":"ES","type":"education","lineage":["https://openalex.org/I6289922"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Mar\u00eda Novo-Lour\u00e9s","raw_affiliation_strings":["Department of Computer Science, University of Vigo, Spain; SING Research Group, Galicia Sur Health Research Institute (IIS Galicia Sur), SERGAS-UVIGO, Spain","Department of Computer Science, University of Vigo, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Vigo, Spain; SING Research Group, Galicia Sur Health Research Institute (IIS Galicia Sur), SERGAS-UVIGO, Spain","institution_ids":["https://openalex.org/I4210091478","https://openalex.org/I6289922","https://openalex.org/I4210158352"]},{"raw_affiliation_string":"Department of Computer Science, University of Vigo, Spain","institution_ids":["https://openalex.org/I6289922"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065363539","display_name":"Reyes Pav\u00f3n","orcid":"https://orcid.org/0000-0002-4247-973X"},"institutions":[{"id":"https://openalex.org/I4210091478","display_name":"Galicia Sur Biomedical Foundation","ror":"https://ror.org/00jdfsf63","country_code":"ES","type":"other","lineage":["https://openalex.org/I4210091478"]},{"id":"https://openalex.org/I4210158352","display_name":"Servicio Gallego de Salud","ror":"https://ror.org/0591s4t67","country_code":"ES","type":"healthcare","lineage":["https://openalex.org/I4210158352"]},{"id":"https://openalex.org/I6289922","display_name":"Universidade de Vigo","ror":"https://ror.org/05rdf8595","country_code":"ES","type":"education","lineage":["https://openalex.org/I6289922"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Reyes Pav\u00f3n","raw_affiliation_strings":["Department of Computer Science, University of Vigo, Spain; SING Research Group, Galicia Sur Health Research Institute (IIS Galicia Sur), SERGAS-UVIGO, Spain","Department of Computer Science, University of Vigo, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Vigo, Spain; SING Research Group, Galicia Sur Health Research Institute (IIS Galicia Sur), SERGAS-UVIGO, Spain","institution_ids":["https://openalex.org/I4210091478","https://openalex.org/I6289922","https://openalex.org/I4210158352"]},{"raw_affiliation_string":"Department of Computer Science, University of Vigo, Spain","institution_ids":["https://openalex.org/I6289922"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052333506","display_name":"Rosal\u00eda Laza","orcid":"https://orcid.org/0000-0002-1889-1337"},"institutions":[{"id":"https://openalex.org/I4210091478","display_name":"Galicia Sur Biomedical Foundation","ror":"https://ror.org/00jdfsf63","country_code":"ES","type":"other","lineage":["https://openalex.org/I4210091478"]},{"id":"https://openalex.org/I4210158352","display_name":"Servicio Gallego de Salud","ror":"https://ror.org/0591s4t67","country_code":"ES","type":"healthcare","lineage":["https://openalex.org/I4210158352"]},{"id":"https://openalex.org/I6289922","display_name":"Universidade de Vigo","ror":"https://ror.org/05rdf8595","country_code":"ES","type":"education","lineage":["https://openalex.org/I6289922"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Rosal\u00eda Laza","raw_affiliation_strings":["Department of Computer Science, University of Vigo, Spain; SING Research Group, Galicia Sur Health Research Institute (IIS Galicia Sur), SERGAS-UVIGO, Spain","Department of Computer Science, University of Vigo, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Vigo, Spain; SING Research Group, Galicia Sur Health Research Institute (IIS Galicia Sur), SERGAS-UVIGO, Spain","institution_ids":["https://openalex.org/I4210091478","https://openalex.org/I6289922","https://openalex.org/I4210158352"]},{"raw_affiliation_string":"Department of Computer Science, University of Vigo, Spain","institution_ids":["https://openalex.org/I6289922"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031898530","display_name":"Jos\u00e9 R. M\u00e9ndez","orcid":"https://orcid.org/0000-0002-1935-4760"},"institutions":[{"id":"https://openalex.org/I4210091478","display_name":"Galicia Sur Biomedical Foundation","ror":"https://ror.org/00jdfsf63","country_code":"ES","type":"other","lineage":["https://openalex.org/I4210091478"]},{"id":"https://openalex.org/I4210158352","display_name":"Servicio Gallego de Salud","ror":"https://ror.org/0591s4t67","country_code":"ES","type":"healthcare","lineage":["https://openalex.org/I4210158352"]},{"id":"https://openalex.org/I6289922","display_name":"Universidade de Vigo","ror":"https://ror.org/05rdf8595","country_code":"ES","type":"education","lineage":["https://openalex.org/I6289922"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Jos\u00e9 Ram\u00f3n M\u00e9ndez","raw_affiliation_strings":["Department of Computer Science, University of Vigo, Spain; SING Research Group, Galicia Sur Health Research Institute (IIS Galicia Sur), SERGAS-UVIGO, Spain","Department of Computer Science, University of Vigo, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Vigo, Spain; SING Research Group, Galicia Sur Health Research Institute (IIS Galicia Sur), SERGAS-UVIGO, Spain","institution_ids":["https://openalex.org/I4210091478","https://openalex.org/I6289922","https://openalex.org/I4210158352"]},{"raw_affiliation_string":"Department of Computer Science, University of Vigo, Spain","institution_ids":["https://openalex.org/I6289922"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5089801683","display_name":"David Ruano-Ord\u00e1s","orcid":"https://orcid.org/0000-0002-6050-373X"},"institutions":[{"id":"https://openalex.org/I4210091478","display_name":"Galicia Sur Biomedical Foundation","ror":"https://ror.org/00jdfsf63","country_code":"ES","type":"other","lineage":["https://openalex.org/I4210091478"]},{"id":"https://openalex.org/I4210158352","display_name":"Servicio Gallego de Salud","ror":"https://ror.org/0591s4t67","country_code":"ES","type":"healthcare","lineage":["https://openalex.org/I4210158352"]},{"id":"https://openalex.org/I6289922","display_name":"Universidade de Vigo","ror":"https://ror.org/05rdf8595","country_code":"ES","type":"education","lineage":["https://openalex.org/I6289922"]}],"countries":["ES"],"is_corresponding":true,"raw_author_name":"David Ruano-Ord\u00e1s","raw_affiliation_strings":["Department of Computer Science, University of Vigo, Spain; SING Research Group, Galicia Sur Health Research Institute (IIS Galicia Sur), SERGAS-UVIGO, Spain","Department of Computer Science, University of Vigo, Spain"],"raw_orcid":"https://orcid.org/0000-0002-6050-373X","affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Vigo, Spain; SING Research Group, Galicia Sur Health Research Institute (IIS Galicia Sur), SERGAS-UVIGO, Spain","institution_ids":["https://openalex.org/I4210091478","https://openalex.org/I6289922","https://openalex.org/I4210158352"]},{"raw_affiliation_string":"Department of Computer Science, University of Vigo, Spain","institution_ids":["https://openalex.org/I6289922"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5089801683"],"corresponding_institution_ids":["https://openalex.org/I4210091478","https://openalex.org/I4210158352","https://openalex.org/I6289922"],"apc_list":null,"apc_paid":null,"fwci":2.5269,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.92643411,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"49","issue":"2","first_page":"285","last_page":"301"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.9958999752998352,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"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/T11986","display_name":"Scientific Computing and Data Management","score":0.9958999752998352,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"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/T11719","display_name":"Data Quality and Management","score":0.9914000034332275,"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/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.9865000247955322,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8224890828132629},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.6340422630310059},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6122428774833679},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.5034186244010925},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.47496888041496277},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.41375288367271423},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4040428102016449}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8224890828132629},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.6340422630310059},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6122428774833679},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.5034186244010925},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.47496888041496277},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.41375288367271423},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4040428102016449},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","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},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1177/0165551521998636","is_oa":false,"landing_page_url":"https://doi.org/10.1177/0165551521998636","pdf_url":null,"source":{"id":"https://openalex.org/S68913162","display_name":"Journal of Information Science","issn_l":"0165-5515","issn":["0165-5515","1741-6485"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320017","host_organization_name":"SAGE Publishing","host_organization_lineage":["https://openalex.org/P4310320017"],"host_organization_lineage_names":["SAGE Publishing"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Information Science","raw_type":"journal-article"},{"id":"pmh:oai:www.investigo.biblioteca.uvigo.es:11093/7491","is_oa":false,"landing_page_url":"http://hdl.handle.net/11093/7491","pdf_url":null,"source":{"id":"https://openalex.org/S4377196408","display_name":"Investigo Institutional repository of UVigo (Universidade de Vigo)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I6289922","host_organization_name":"Universidade de Vigo","host_organization_lineage":["https://openalex.org/I6289922"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1445387246","display_name":null,"funder_award_id":"TIN2017-84658-C2-1-R","funder_id":"https://openalex.org/F4320326262","funder_display_name":"Ministerio de Asuntos Econ\u00f3micos y Transformaci\u00f3n Digital, Gobierno de Espa\u00f1a"},{"id":"https://openalex.org/G1924902539","display_name":null,"funder_award_id":"ED481B 2017/018","funder_id":"https://openalex.org/F4320325108","funder_display_name":"Conseller\u00eda de Cultura, Educaci\u00f3n e Ordenaci\u00f3n Universitaria, Xunta de Galicia"},{"id":"https://openalex.org/G8208689475","display_name":null,"funder_award_id":"TIN2017-84658-C2-1-R","funder_id":"https://openalex.org/F4320335598","funder_display_name":"Agencia Estatal de Investigaci\u00f3n"},{"id":"https://openalex.org/G8708971385","display_name":null,"funder_award_id":"TIN2017-84658-C2-1-R","funder_id":"https://openalex.org/F4320335322","funder_display_name":"European Regional Development Fund"}],"funders":[{"id":"https://openalex.org/F4320325108","display_name":"Conseller\u00eda de Cultura, Educaci\u00f3n e Ordenaci\u00f3n Universitaria, Xunta de Galicia","ror":"https://ror.org/03gq5rs15"},{"id":"https://openalex.org/F4320326262","display_name":"Ministerio de Asuntos Econ\u00f3micos y Transformaci\u00f3n Digital, Gobierno de Espa\u00f1a","ror":"https://ror.org/03sv46s19"},{"id":"https://openalex.org/F4320335322","display_name":"European Regional Development Fund","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320335598","display_name":"Agencia Estatal de Investigaci\u00f3n","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W1489138569","https://openalex.org/W2110783067","https://openalex.org/W2132862423","https://openalex.org/W2141407461","https://openalex.org/W2146012091","https://openalex.org/W2150264441","https://openalex.org/W2278629362","https://openalex.org/W2302501749","https://openalex.org/W2388245502","https://openalex.org/W2598013184","https://openalex.org/W2604213177","https://openalex.org/W2773787581","https://openalex.org/W2791979951","https://openalex.org/W2807800730","https://openalex.org/W2809503112","https://openalex.org/W2903976715","https://openalex.org/W2973058741","https://openalex.org/W3024722698","https://openalex.org/W3045464143","https://openalex.org/W3046408935","https://openalex.org/W3098427023","https://openalex.org/W3106918560","https://openalex.org/W3194766113","https://openalex.org/W4239025696","https://openalex.org/W4248358572","https://openalex.org/W6893590294"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W2384888906","https://openalex.org/W2376314740","https://openalex.org/W2366644548","https://openalex.org/W2357241418","https://openalex.org/W2119214692","https://openalex.org/W2119135658","https://openalex.org/W2115485936","https://openalex.org/W2153015554","https://openalex.org/W2146184373"],"abstract_inverted_index":{"Current":[0],"research":[1,84,116],"has":[2,70],"evolved":[3],"in":[4,190],"such":[5],"a":[6,72],"way":[7],"scientists":[8],"must":[9],"not":[10],"only":[11],"adequately":[12],"describe":[13],"the":[14,19,27,31,55,60,103,120,131,138,143,159,176,191],"algorithms":[15],"they":[16],"introduce":[17],"and":[18,33,65,87,90,101,146,154],"results":[20,32],"of":[21,29,54,62,75,122,133,178,188,197],"their":[22,96],"application,":[23],"but":[24],"also":[25],"ensure":[26],"possibility":[28],"reproducing":[30],"comparing":[34],"them":[35],"with":[36],"those":[37],"obtained":[38],"through":[39,50],"other":[40],"approximations.":[41],"In":[42,182],"this":[43,198],"context,":[44],"public":[45],"data":[46,85,88,112],"sets":[47,89,113],"(sometimes":[48],"shared":[49],"repositories)":[51],"are":[52],"one":[53],"most":[56],"important":[57],"elements":[58],"for":[59,107,114,151],"development":[61],"experimental":[63],"protocols":[64],"test":[66],"benches.":[67],"This":[68],"study":[69],"analysed":[71],"significant":[73],"number":[74],"CS/ML":[76],"(":[77],"Computer":[78],"Science":[79],"/":[80],"Machine":[81],"Learning":[82],")":[83],"repositories":[86],"detected":[91],"some":[92],"limitations":[93],"that":[94],"hamper":[95],"utility.":[97],"Particularly,":[98],"we":[99,162,184],"identify":[100],"discuss":[102],"following":[104],"demanding":[105],"functionalities":[106,145],"repositories:":[108],"(1)":[109],"building":[110],"customised":[111],"specific":[115],"tasks,":[117],"(2)":[118],"facilitating":[119],"comparison":[121],"different":[123],"techniques":[124],"using":[125,142],"dissimilar":[126],"pre-processing":[127,139],"methods,":[128],"(3)":[129],"ensuring":[130],"availability":[132],"software":[134],"applications":[135],"to":[136,175,194],"reproduce":[137],"steps":[140],"without":[141],"repository":[144],"(4)":[147],"providing":[148],"protection":[149],"mechanisms":[150],"licencing":[152],"issues":[153],"user":[155],"rights.":[156],"To":[157],"show":[158],"introduced":[160],"functionality,":[161],"created":[163],"STRep":[164,189],"(Spam":[165],"Text":[166],"Repository)":[167],"web":[168],"application":[169],"which":[170],"implements":[171],"our":[172],"recommendations":[173],"adapted":[174],"field":[177],"spam":[179],"text":[180],"repositories.":[181],"addition,":[183],"launched":[185],"an":[186],"instance":[187],"URL":[192],"https://rdata.4spam.group":[193],"facilitate":[195],"understanding":[196],"study.":[199]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":4},{"year":2021,"cited_by_count":1}],"updated_date":"2026-05-05T06:06:40.768181","created_date":"2025-10-10T00:00:00"}