{"id":"https://openalex.org/W3105270240","doi":"https://doi.org/10.5220/0010056101530160","title":"Ontology-based Methods for Classifying Scientific Datasets into Research Domains: Much Harder than Expected","display_name":"Ontology-based Methods for Classifying Scientific Datasets into Research Domains: Much Harder than Expected","publication_year":2020,"publication_date":"2020-01-01","ids":{"openalex":"https://openalex.org/W3105270240","doi":"https://doi.org/10.5220/0010056101530160","mag":"3105270240"},"language":"en","primary_location":{"id":"doi:10.5220/0010056101530160","is_oa":true,"landing_page_url":"https://doi.org/10.5220/0010056101530160","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 12th International Joint Conference on Knowledge Discovery, Knowledge Engineering and Knowledge Management","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.5220/0010056101530160","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5000048946","display_name":"Xu Wang","orcid":"https://orcid.org/0000-0002-7585-759X"},"institutions":[{"id":"https://openalex.org/I865915315","display_name":"Vrije Universiteit Amsterdam","ror":"https://ror.org/008xxew50","country_code":"NL","type":"education","lineage":["https://openalex.org/I865915315"]}],"countries":["NL"],"is_corresponding":true,"raw_author_name":"Xu Wang","raw_affiliation_strings":["Vrije University Amsterdam, De Boelelaan 1105, 1081 HV Amsterdam, The Netherlands, --- Select a Country ---"],"affiliations":[{"raw_affiliation_string":"Vrije University Amsterdam, De Boelelaan 1105, 1081 HV Amsterdam, The Netherlands, --- Select a Country ---","institution_ids":["https://openalex.org/I865915315"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029130731","display_name":"Frank van Harmelen","orcid":"https://orcid.org/0000-0002-7913-0048"},"institutions":[{"id":"https://openalex.org/I865915315","display_name":"Vrije Universiteit Amsterdam","ror":"https://ror.org/008xxew50","country_code":"NL","type":"education","lineage":["https://openalex.org/I865915315"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Frank Van Harmelen","raw_affiliation_strings":["Vrije University Amsterdam, De Boelelaan 1105, 1081 HV Amsterdam, The Netherlands, --- Select a Country ---"],"affiliations":[{"raw_affiliation_string":"Vrije University Amsterdam, De Boelelaan 1105, 1081 HV Amsterdam, The Netherlands, --- Select a Country ---","institution_ids":["https://openalex.org/I865915315"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101447313","display_name":"Zhisheng Huang","orcid":"https://orcid.org/0000-0003-3794-9829"},"institutions":[{"id":"https://openalex.org/I865915315","display_name":"Vrije Universiteit Amsterdam","ror":"https://ror.org/008xxew50","country_code":"NL","type":"education","lineage":["https://openalex.org/I865915315"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Zhisheng Huang","raw_affiliation_strings":["Vrije University Amsterdam, De Boelelaan 1105, 1081 HV Amsterdam, The Netherlands, --- Select a Country ---"],"affiliations":[{"raw_affiliation_string":"Vrije University Amsterdam, De Boelelaan 1105, 1081 HV Amsterdam, The Netherlands, --- Select a Country ---","institution_ids":["https://openalex.org/I865915315"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5000048946"],"corresponding_institution_ids":["https://openalex.org/I865915315"],"apc_list":null,"apc_paid":null,"fwci":0.1672,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.51358665,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"153","last_page":"160"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9959999918937683,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9959999918937683,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10215","display_name":"Semantic Web and Ontologies","score":0.987500011920929,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9739000201225281,"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":0.8262524008750916},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.7346634864807129},{"id":"https://openalex.org/keywords/ontology","display_name":"Ontology","score":0.7033075094223022},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6295582056045532},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5831405520439148},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4950351119041443},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4520612955093384},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4429052174091339},{"id":"https://openalex.org/keywords/estimator","display_name":"Estimator","score":0.4258181154727936},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.39722394943237305},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3881436586380005}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8262524008750916},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.7346634864807129},{"id":"https://openalex.org/C25810664","wikidata":"https://www.wikidata.org/wiki/Q44325","display_name":"Ontology","level":2,"score":0.7033075094223022},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6295582056045532},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5831405520439148},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4950351119041443},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4520612955093384},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4429052174091339},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.4258181154727936},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39722394943237305},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3881436586380005},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.5220/0010056101530160","is_oa":true,"landing_page_url":"https://doi.org/10.5220/0010056101530160","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 12th International Joint Conference on Knowledge Discovery, Knowledge Engineering and Knowledge Management","raw_type":"proceedings-article"},{"id":"pmh:oai:research.vu.nl:openaire_cris_publications/8cfb26b0-1f29-4092-bf63-0806f62d73ab","is_oa":false,"landing_page_url":"https://research.vu.nl/en/publications/8cfb26b0-1f29-4092-bf63-0806f62d73ab","pdf_url":null,"source":{"id":"https://openalex.org/S4306401107","display_name":"VU Research Portal","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I865915315","host_organization_name":"Vrije Universiteit Amsterdam","host_organization_lineage":["https://openalex.org/I865915315"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Wang, X, Van Harmelen, F & Huang, Z 2020, Ontology-based methods for classifying scientific datasets into research domains : Much harder than expected. in A Fred & J Filipe (eds), Proceedings of the 12th International Joint Conference on Knowledge Discovery, Knowledge Engineering and Knowledge Management - KDIR : Volume 1: KDIR. vol. 1, C3K, Proceedings of the International Joint Conference on Knowledge Discovery, Knowledge Engineering and Knowledge Management, SciTePress, pp. 153-160, 12th International Conference on Knowledge Discovery and Information Retrieval, KDIR 2020 - Part of the 12th International Joint Conference on Knowledge Discovery, Knowledge Engineering and Knowledge Management, IC3K 2020, Virtual, Online, 2/11/20. https://doi.org/10.5220/0010056101530160","raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"pmh:oai:research.vu.nl:openaire/8cfb26b0-1f29-4092-bf63-0806f62d73ab","is_oa":true,"landing_page_url":"https://hdl.handle.net/1871.1/8cfb26b0-1f29-4092-bf63-0806f62d73ab","pdf_url":null,"source":{"id":"https://openalex.org/S4306401107","display_name":"VU Research Portal","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I865915315","host_organization_name":"Vrije Universiteit Amsterdam","host_organization_lineage":["https://openalex.org/I865915315"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Wang, X, Van Harmelen, F & Huang, Z 2020, Ontology-based methods for classifying scientific datasets into research domains : Much harder than expected. in A Fred & J Filipe (eds), Proceedings of the 12th International Joint Conference on Knowledge Discovery, Knowledge Engineering and Knowledge Management - KDIR : Volume 1: KDIR. vol. 1, C3K, Proceedings of the International Joint Conference on Knowledge Discovery, Knowledge Engineering and Knowledge Management, SciTePress, pp. 153-160, 12th International Conference on Knowledge Discovery and Information Retrieval, KDIR 2020 - Part of the 12th International Joint Conference on Knowledge Discovery, Knowledge Engineering and Knowledge Management, IC3K 2020, Virtual, Online, 2/11/20. https://doi.org/10.5220/0010056101530160","raw_type":"info:eu-repo/semantics/publishedVersion"}],"best_oa_location":{"id":"doi:10.5220/0010056101530160","is_oa":true,"landing_page_url":"https://doi.org/10.5220/0010056101530160","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 12th International Joint Conference on Knowledge Discovery, Knowledge Engineering and Knowledge Management","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1426318481","display_name":null,"funder_award_id":"grant","funder_id":"https://openalex.org/F4320322725","funder_display_name":"China Scholarship Council"},{"id":"https://openalex.org/G2300736770","display_name":null,"funder_award_id":"(CSC)","funder_id":"https://openalex.org/F4320322725","funder_display_name":"China Scholarship Council"},{"id":"https://openalex.org/G2363776585","display_name":null,"funder_award_id":"652.001.002","funder_id":"https://openalex.org/F4320321800","funder_display_name":"Nederlandse Organisatie voor Wetenschappelijk Onderzoek"},{"id":"https://openalex.org/G8589651859","display_name":null,"funder_award_id":"China","funder_id":"https://openalex.org/F4320322725","funder_display_name":"China Scholarship Council"}],"funders":[{"id":"https://openalex.org/F4320321800","display_name":"Nederlandse Organisatie voor Wetenschappelijk Onderzoek","ror":"https://ror.org/04jsz6e67"},{"id":"https://openalex.org/F4320322725","display_name":"China Scholarship Council","ror":"https://ror.org/04atp4p48"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W1525595230","https://openalex.org/W1606882635","https://openalex.org/W1647729745","https://openalex.org/W1978394996","https://openalex.org/W2077929656","https://openalex.org/W2135272908","https://openalex.org/W2136480620","https://openalex.org/W2142216989","https://openalex.org/W2157407349","https://openalex.org/W2165897980","https://openalex.org/W2950225692","https://openalex.org/W3098427023","https://openalex.org/W4294170691"],"related_works":["https://openalex.org/W2378211422","https://openalex.org/W2745001401","https://openalex.org/W4321353415","https://openalex.org/W2130974462","https://openalex.org/W972276598","https://openalex.org/W4246352526","https://openalex.org/W2028665553","https://openalex.org/W4230315250","https://openalex.org/W2086519370","https://openalex.org/W2087343574"],"abstract_inverted_index":{"Scientific":[0],"datasets":[1,22],"are":[2,29,132],"increasingly":[3],"stored,":[4],"published,":[5],"and":[6,34,56,71,89,118,158],"re-used":[7],"online.":[8,23],"This":[9],"has":[10],"prompted":[11],"major":[12],"search":[13],"engines":[14],"to":[15,19,25,31,79,167,199],"start":[16],"services":[17,28],"dedicated":[18],"finding":[20],"research":[21,59],"However,":[24],"date":[26],"such":[27],"limited":[30],"keyword":[32],"search,":[33],"provide":[35],"little":[36,170],"or":[37],"no":[38],"semantic":[39],"guidance.":[40],"Determining":[41],"the":[42,84,96,100,114,134,140,162,176],"scientific":[43],"domain":[44,60],"for":[45,95,189,197],"a":[46,50,73,87,90,108,124,143,186],"given":[47],"dataset":[48,54,63,91,101,144],"is":[49,145],"crucial":[51],"part":[52],"in":[53,172],"recommendation":[55],"search:":[57],"\"Which":[58],"does":[61],"this":[62,67,173],"belong":[64],"to?\".":[65],"In":[66],"paper":[68],"we":[69,119,193],"investigate":[70],"compare":[72],"number":[74],"of":[75,138,142,164,169],"novel":[76],"ontology-based":[77,182],"methods":[78],"answer":[80],"that":[81,133,159],"question,":[82],"using":[83],"distance":[85],"between":[86],"domain-ontology":[88],"as":[92],"an":[93],"estimator":[94],"domain(s)":[97,141],"into":[98],"which":[99,192],"should":[102],"be":[103,168],"classified.":[104],"We":[105,184],"also":[106],"define":[107],"simple":[109,136,177],"keyword-based":[110,178],"classifier":[111,179],"based":[112],"on":[113,123],"Normalized":[115],"Google":[116],"Distance,":[117],"evaluate":[120],"all":[121],"classifiers":[122],"hand-constructed":[125],"gold":[126],"standard.":[127],"Our":[128],"two":[129],"main":[130],"findings":[131],"seemingly":[135],"task":[137],"determining":[139],"surprisingly":[146],"much":[147],"harder":[148],"than":[149],"expected":[150],"(even":[151],"when":[152],"performed":[153],"under":[154],"highly":[155],"simplified":[156],"circumstances),":[157],"(again":[160],"surprisingly),":[161],"use":[163],"ontologies":[165],"seems":[166],"help":[171],"task,":[174],"with":[175],"outperforming":[180],"every":[181],"classifier.":[183],"constructed":[185],"gold-standard":[187],"benchmark":[188],"our":[190],"experiments":[191],"make":[194],"available":[195],"online":[196],"others":[198],"use.":[200]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}