{"id":"https://openalex.org/W4224308657","doi":"https://doi.org/10.1080/17517575.2022.2062683","title":"Efficient computation of comprehensive statistical information of large OWL datasets: a scalable approach","display_name":"Efficient computation of comprehensive statistical information of large OWL datasets: a scalable approach","publication_year":2022,"publication_date":"2022-04-24","ids":{"openalex":"https://openalex.org/W4224308657","doi":"https://doi.org/10.1080/17517575.2022.2062683"},"language":"en","primary_location":{"id":"doi:10.1080/17517575.2022.2062683","is_oa":false,"landing_page_url":"https://doi.org/10.1080/17517575.2022.2062683","pdf_url":null,"source":{"id":"https://openalex.org/S24861202","display_name":"Enterprise Information Systems","issn_l":"1751-7575","issn":["1751-7575","1751-7583"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320547","host_organization_name":"Taylor & Francis","host_organization_lineage":["https://openalex.org/P4310320547"],"host_organization_lineage_names":["Taylor & Francis"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Enterprise Information Systems","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/A5008234964","display_name":"Heba Mohamed","orcid":"https://orcid.org/0000-0003-3146-1937"},"institutions":[{"id":"https://openalex.org/I135140700","display_name":"University of Bonn","ror":"https://ror.org/041nas322","country_code":"DE","type":"education","lineage":["https://openalex.org/I135140700"]},{"id":"https://openalex.org/I84524832","display_name":"Alexandria University","ror":"https://ror.org/00mzz1w90","country_code":"EG","type":"education","lineage":["https://openalex.org/I84524832"]}],"countries":["DE","EG"],"is_corresponding":false,"raw_author_name":"Heba Mohamed","raw_affiliation_strings":["Faculty of Science, University of Alexandria, Egypt","Smart Data Analytics (SDA), University of Bonn, Bonn, Germany"],"raw_orcid":"https://orcid.org/0000-0003-3146-1937","affiliations":[{"raw_affiliation_string":"Faculty of Science, University of Alexandria, Egypt","institution_ids":["https://openalex.org/I84524832"]},{"raw_affiliation_string":"Smart Data Analytics (SDA), University of Bonn, Bonn, Germany","institution_ids":["https://openalex.org/I135140700"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020690863","display_name":"Said Fathalla","orcid":"https://orcid.org/0000-0002-2818-5890"},"institutions":[{"id":"https://openalex.org/I135140700","display_name":"University of Bonn","ror":"https://ror.org/041nas322","country_code":"DE","type":"education","lineage":["https://openalex.org/I135140700"]},{"id":"https://openalex.org/I84524832","display_name":"Alexandria University","ror":"https://ror.org/00mzz1w90","country_code":"EG","type":"education","lineage":["https://openalex.org/I84524832"]}],"countries":["DE","EG"],"is_corresponding":true,"raw_author_name":"Said Fathalla","raw_affiliation_strings":["Faculty of Science, University of Alexandria, Egypt","Smart Data Analytics (SDA), University of Bonn, Bonn, Germany"],"raw_orcid":"https://orcid.org/0000-0002-2818-5890","affiliations":[{"raw_affiliation_string":"Faculty of Science, University of Alexandria, Egypt","institution_ids":["https://openalex.org/I84524832"]},{"raw_affiliation_string":"Smart Data Analytics (SDA), University of Bonn, Bonn, Germany","institution_ids":["https://openalex.org/I135140700"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067133778","display_name":"Jens Lehmann","orcid":"https://orcid.org/0000-0001-9108-4278"},"institutions":[{"id":"https://openalex.org/I135140700","display_name":"University of Bonn","ror":"https://ror.org/041nas322","country_code":"DE","type":"education","lineage":["https://openalex.org/I135140700"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Jens Lehmann","raw_affiliation_strings":["NetMedia Department, Fraunhofer IAIS, Dresden Lab, Germany","Smart Data Analytics (SDA), University of Bonn, Bonn, Germany"],"raw_orcid":"https://orcid.org/0000-0001-9108-4278","affiliations":[{"raw_affiliation_string":"NetMedia Department, Fraunhofer IAIS, Dresden Lab, Germany","institution_ids":[]},{"raw_affiliation_string":"Smart Data Analytics (SDA), University of Bonn, Bonn, Germany","institution_ids":["https://openalex.org/I135140700"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034642813","display_name":"Hajira Jabeen","orcid":"https://orcid.org/0000-0003-1476-2121"},"institutions":[{"id":"https://openalex.org/I4210101898","display_name":"GESIS - Leibniz-Institute for the Social Sciences","ror":"https://ror.org/018afyw53","country_code":"DE","type":"facility","lineage":["https://openalex.org/I315704651","https://openalex.org/I4210101898"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Hajira Jabeen","raw_affiliation_strings":["GESIS-Leibniz Institute for the Social Sciences, Cologne, Germany"],"raw_orcid":"https://orcid.org/0000-0003-1476-2121","affiliations":[{"raw_affiliation_string":"GESIS-Leibniz Institute for the Social Sciences, Cologne, Germany","institution_ids":["https://openalex.org/I4210101898"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5020690863"],"corresponding_institution_ids":["https://openalex.org/I135140700","https://openalex.org/I84524832"],"apc_list":null,"apc_paid":null,"fwci":0.1695,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.50668939,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"17","issue":"7","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9994999766349792,"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":0.9994999766349792,"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":0.9983999729156494,"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/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9955999851226807,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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":0.8302898406982422},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.8163455724716187},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.6646287441253662},{"id":"https://openalex.org/keywords/spark","display_name":"SPARK (programming language)","score":0.5935317277908325},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5345081090927124},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5226816534996033},{"id":"https://openalex.org/keywords/analytics","display_name":"Analytics","score":0.5102753639221191},{"id":"https://openalex.org/keywords/reuse","display_name":"Reuse","score":0.48580169677734375},{"id":"https://openalex.org/keywords/node","display_name":"Node (physics)","score":0.4732834994792938},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.4210333228111267},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.4106540381908417},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.3730323612689972},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.2823324203491211},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.08961948752403259}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8302898406982422},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.8163455724716187},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.6646287441253662},{"id":"https://openalex.org/C2781215313","wikidata":"https://www.wikidata.org/wiki/Q3493345","display_name":"SPARK (programming language)","level":2,"score":0.5935317277908325},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5345081090927124},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5226816534996033},{"id":"https://openalex.org/C79158427","wikidata":"https://www.wikidata.org/wiki/Q485396","display_name":"Analytics","level":2,"score":0.5102753639221191},{"id":"https://openalex.org/C206588197","wikidata":"https://www.wikidata.org/wiki/Q846574","display_name":"Reuse","level":2,"score":0.48580169677734375},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.4732834994792938},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.4210333228111267},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.4106540381908417},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3730323612689972},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.2823324203491211},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.08961948752403259},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"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},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1080/17517575.2022.2062683","is_oa":false,"landing_page_url":"https://doi.org/10.1080/17517575.2022.2062683","pdf_url":null,"source":{"id":"https://openalex.org/S24861202","display_name":"Enterprise Information Systems","issn_l":"1751-7575","issn":["1751-7575","1751-7583"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320547","host_organization_name":"Taylor & Francis","host_organization_lineage":["https://openalex.org/P4310320547"],"host_organization_lineage_names":["Taylor & Francis"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Enterprise Information Systems","raw_type":"journal-article"},{"id":"pmh:oai:publica.fraunhofer.de:publica/428333","is_oa":false,"landing_page_url":"https://publica.fraunhofer.de/handle/publica/428333","pdf_url":null,"source":{"id":"https://openalex.org/S4306400318","display_name":"Fraunhofer-Publica (Fraunhofer-Gesellschaft)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4923324","host_organization_name":"Fraunhofer-Gesellschaft","host_organization_lineage":["https://openalex.org/I4923324"],"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":"journal article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G8966371783","display_name":null,"funder_award_id":"809965, 872592","funder_id":"https://openalex.org/F4320337669","funder_display_name":"H2020 European Institute of Innovation and Technology"}],"funders":[{"id":"https://openalex.org/F4320337669","display_name":"H2020 European Institute of Innovation and Technology","ror":"https://ror.org/036dxts37"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W205325246","https://openalex.org/W1528140876","https://openalex.org/W1585772925","https://openalex.org/W1605803989","https://openalex.org/W1805882648","https://openalex.org/W1978799369","https://openalex.org/W1989009626","https://openalex.org/W2017323594","https://openalex.org/W2020251180","https://openalex.org/W2075351444","https://openalex.org/W2119738171","https://openalex.org/W2125442437","https://openalex.org/W2171153120","https://openalex.org/W2326340814","https://openalex.org/W2471601082","https://openalex.org/W2604561489","https://openalex.org/W2617512245","https://openalex.org/W2764318100","https://openalex.org/W2766271179","https://openalex.org/W2885767189","https://openalex.org/W2891796645","https://openalex.org/W2922782871","https://openalex.org/W2936724388","https://openalex.org/W2946065541","https://openalex.org/W2980478337","https://openalex.org/W2981845811","https://openalex.org/W3014718825","https://openalex.org/W3129680968","https://openalex.org/W4211171039","https://openalex.org/W4244178506","https://openalex.org/W4248472119"],"related_works":["https://openalex.org/W4390608645","https://openalex.org/W4405901645","https://openalex.org/W4394895745","https://openalex.org/W2960264696","https://openalex.org/W3090563135","https://openalex.org/W2766461310","https://openalex.org/W4247566972","https://openalex.org/W3202731209","https://openalex.org/W3211874991","https://openalex.org/W3191926225"],"abstract_inverted_index":{"Computing":[0],"dataset":[1],"statistics":[2,53],"is":[3,59,89],"crucial":[4],"for":[5,13,50,64,69],"exploring":[6],"their":[7],"structure,":[8],"however,":[9],"it":[10],"becomes":[11],"challenging":[12],"large-scale":[14,55],"datasets.":[15,57],"This":[16],"has":[17],"several":[18],"key":[19],"benefits,":[20],"such":[21],"as":[22],"link":[23],"target":[24],"identification,":[25],"vocabulary":[26],"reuse,":[27],"quality":[28],"analysis,":[29],"big":[30],"data":[31,98],"analytics,":[32],"and":[33,97],"coverage":[34],"analysis.":[35],"In":[36],"this":[37],"paper,":[38],"we":[39],"present":[40],"the":[41,81],"first":[42],"attempt":[43],"of":[44,94],"developing":[45],"a":[46,60],"distributed":[47,61],"approach":[48,63],"(OWLStats)":[49],"collecting":[51],"comprehensive":[52],"over":[54],"OWL":[56,70],"OWLStats":[58,79,88],"in-memory":[62],"computing":[65],"50":[66],"statistical":[67],"criteria":[68],"datasets":[71],"utilizing":[72],"Apache":[73],"Spark.":[74],"We":[75],"have":[76],"successfully":[77],"integrated":[78],"into":[80],"SANSA":[82],"framework.":[83],"Experiments":[84],"results":[85],"prove":[86],"that":[87],"linearly":[90],"scalable":[91],"in":[92],"terms":[93],"both":[95],"node":[96],"scalability.":[99]},"counts_by_year":[{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}