{"id":"https://openalex.org/W2487547204","doi":"https://doi.org/10.1145/2928294.2928301","title":"An unsupervised classification process for large datasets using web reasoning","display_name":"An unsupervised classification process for large datasets using web reasoning","publication_year":2016,"publication_date":"2016-06-02","ids":{"openalex":"https://openalex.org/W2487547204","doi":"https://doi.org/10.1145/2928294.2928301","mag":"2487547204"},"language":"en","primary_location":{"id":"doi:10.1145/2928294.2928301","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2928294.2928301","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the International Workshop on Semantic Big Data","raw_type":"proceedings-article"},"type":"preprint","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/A5023657251","display_name":"Rafael Peixoto","orcid":null},"institutions":[{"id":"https://openalex.org/I83863532","display_name":"Polytechnic Institute of Porto","ror":"https://ror.org/04988re48","country_code":"PT","type":"education","lineage":["https://openalex.org/I83863532"]}],"countries":["PT"],"is_corresponding":true,"raw_author_name":"Rafael Peixoto","raw_affiliation_strings":["Univ. Bourgogne Franche-Comt\u00e9, Dijon, France and GECAD - ISEP, Polytechnic of Porto, Porto, Portugal"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Univ. Bourgogne Franche-Comt\u00e9, Dijon, France and GECAD - ISEP, Polytechnic of Porto, Porto, Portugal","institution_ids":["https://openalex.org/I83863532"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074474915","display_name":"Thomas Hassan","orcid":"https://orcid.org/0000-0003-2912-1984"},"institutions":[{"id":"https://openalex.org/I4210118524","display_name":"Universit\u00e9 Bourgogne Franche-Comt\u00e9","ror":"https://ror.org/02dn7x778","country_code":"FR","type":"education","lineage":["https://openalex.org/I4210118524"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Thomas Hassan","raw_affiliation_strings":["Univ. Bourgogne Franche-Comt\u00e9, Dijon, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Univ. Bourgogne Franche-Comt\u00e9, Dijon, France","institution_ids":["https://openalex.org/I4210118524"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031830209","display_name":"Christophe Cruz","orcid":"https://orcid.org/0000-0002-5611-9479"},"institutions":[{"id":"https://openalex.org/I4210118524","display_name":"Universit\u00e9 Bourgogne Franche-Comt\u00e9","ror":"https://ror.org/02dn7x778","country_code":"FR","type":"education","lineage":["https://openalex.org/I4210118524"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Christophe Cruz","raw_affiliation_strings":["Univ. Bourgogne Franche-Comt\u00e9, Dijon, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Univ. Bourgogne Franche-Comt\u00e9, Dijon, France","institution_ids":["https://openalex.org/I4210118524"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088285849","display_name":"Aur\u00e9lie Bertaux","orcid":null},"institutions":[{"id":"https://openalex.org/I4210118524","display_name":"Universit\u00e9 Bourgogne Franche-Comt\u00e9","ror":"https://ror.org/02dn7x778","country_code":"FR","type":"education","lineage":["https://openalex.org/I4210118524"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Aur\u00e9lie Bertaux","raw_affiliation_strings":["Univ. Bourgogne Franche-Comt\u00e9, Dijon, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Univ. Bourgogne Franche-Comt\u00e9, Dijon, France","institution_ids":["https://openalex.org/I4210118524"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016303203","display_name":"Nuno Silva","orcid":"https://orcid.org/0000-0002-0556-0707"},"institutions":[{"id":"https://openalex.org/I83863532","display_name":"Polytechnic Institute of Porto","ror":"https://ror.org/04988re48","country_code":"PT","type":"education","lineage":["https://openalex.org/I83863532"]}],"countries":["PT"],"is_corresponding":false,"raw_author_name":"Nuno Silva","raw_affiliation_strings":["GECAD - ISEP, Polytechnic of Porto, Porto, Portugal","Polytechnic Institute of Porto (R. Dr. Roberto Frias, 4200-465 Porto - Portugal)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"GECAD - ISEP, Polytechnic of Porto, Porto, Portugal","institution_ids":["https://openalex.org/I83863532"]},{"raw_affiliation_string":"Polytechnic Institute of Porto (R. Dr. Roberto Frias, 4200-465 Porto - Portugal)","institution_ids":["https://openalex.org/I83863532"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5023657251"],"corresponding_institution_ids":["https://openalex.org/I83863532"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.09101518,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.998199999332428,"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"}},"topics":[{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.998199999332428,"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"}},{"id":"https://openalex.org/T10215","display_name":"Semantic Web and Ontologies","score":0.9976999759674072,"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/T11106","display_name":"Data Management and Algorithms","score":0.995199978351593,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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":0.8376203775405884},{"id":"https://openalex.org/keywords/vectorization","display_name":"Vectorization (mathematics)","score":0.6141445636749268},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.610578179359436},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5990449786186218},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.568772554397583},{"id":"https://openalex.org/keywords/hierarchy","display_name":"Hierarchy","score":0.5473079085350037},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5286555886268616},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.49474284052848816},{"id":"https://openalex.org/keywords/semantic-web","display_name":"Semantic Web","score":0.47055864334106445},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.4633733630180359},{"id":"https://openalex.org/keywords/realization","display_name":"Realization (probability)","score":0.4627001881599426},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4415163993835449},{"id":"https://openalex.org/keywords/unstructured-data","display_name":"Unstructured data","score":0.41056889295578003},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.34962207078933716},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.34030234813690186},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.23425713181495667},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.10973891615867615}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8376203775405884},{"id":"https://openalex.org/C41681595","wikidata":"https://www.wikidata.org/wiki/Q7917855","display_name":"Vectorization (mathematics)","level":2,"score":0.6141445636749268},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.610578179359436},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5990449786186218},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.568772554397583},{"id":"https://openalex.org/C31170391","wikidata":"https://www.wikidata.org/wiki/Q188619","display_name":"Hierarchy","level":2,"score":0.5473079085350037},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5286555886268616},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.49474284052848816},{"id":"https://openalex.org/C2129575","wikidata":"https://www.wikidata.org/wiki/Q54837","display_name":"Semantic Web","level":2,"score":0.47055864334106445},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.4633733630180359},{"id":"https://openalex.org/C2781089630","wikidata":"https://www.wikidata.org/wiki/Q21856745","display_name":"Realization (probability)","level":2,"score":0.4627001881599426},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4415163993835449},{"id":"https://openalex.org/C2781252014","wikidata":"https://www.wikidata.org/wiki/Q1141900","display_name":"Unstructured data","level":3,"score":0.41056889295578003},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.34962207078933716},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.34030234813690186},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.23425713181495667},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.10973891615867615},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"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/C34447519","wikidata":"https://www.wikidata.org/wiki/Q179522","display_name":"Market economy","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}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/2928294.2928301","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2928294.2928301","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the International Workshop on Semantic Big Data","raw_type":"proceedings-article"},{"id":"pmh:oai:HAL:hal-01418148v1","is_oa":false,"landing_page_url":"https://hal.science/hal-01418148","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://www.ifis.uni-luebeck.de/~groppe/sbd/2016","raw_type":"Conference papers"},{"id":"pmh:oai:HAL:hal-01452220v1","is_oa":false,"landing_page_url":"https://hal.archives-ouvertes.fr/hal-01452220","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"The International Workshop on Semantic Big Data (SBD 2016)","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321663","display_name":"Association Nationale de la Recherche et de la Technologie","ror":"https://ror.org/00ht2ab73"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W130692220","https://openalex.org/W1482585805","https://openalex.org/W1528916787","https://openalex.org/W1548616358","https://openalex.org/W1624661769","https://openalex.org/W1663034667","https://openalex.org/W1771420424","https://openalex.org/W1832267212","https://openalex.org/W1977523979","https://openalex.org/W1983077505","https://openalex.org/W2009762859","https://openalex.org/W2013427069","https://openalex.org/W2018113587","https://openalex.org/W2046114481","https://openalex.org/W2078975546","https://openalex.org/W2100515808","https://openalex.org/W2113553966","https://openalex.org/W2118992936","https://openalex.org/W2127723919","https://openalex.org/W2136600545","https://openalex.org/W2154829072","https://openalex.org/W2156774188","https://openalex.org/W2159128662","https://openalex.org/W2173213060","https://openalex.org/W2188459837","https://openalex.org/W2248619253","https://openalex.org/W2334307703","https://openalex.org/W2516991950","https://openalex.org/W2902140193","https://openalex.org/W2915041696","https://openalex.org/W3101974058","https://openalex.org/W4241366218"],"related_works":["https://openalex.org/W2762467749","https://openalex.org/W3157828377","https://openalex.org/W4377992839","https://openalex.org/W2937168573","https://openalex.org/W2261525379","https://openalex.org/W2162769527","https://openalex.org/W2805468299","https://openalex.org/W4231652189","https://openalex.org/W4400467792","https://openalex.org/W2608358066"],"abstract_inverted_index":{"Determining":[0],"valuable":[1],"data":[2,7,47,72],"among":[3],"large":[4,46],"volumes":[5],"of":[6,10,107],"is":[8,118],"one":[9],"the":[11,52,68,83,90],"main":[12],"challenges":[13],"in":[14,89,120],"Big":[15,128],"Data.":[16],"We":[17],"aim":[18],"to":[19,82,101,126],"extract":[20],"knowledge":[21],"from":[22,44,71,104],"these":[23],"sources":[24],"using":[25,111],"a":[26,38,96,121],"Hierarchical":[27],"Multi-Label":[28],"Classification":[29],"process":[30,35,100,117,127],"called":[31],"Semantic":[32,53],"HMC.":[33],"This":[34,86],"automatically":[36,67],"learns":[37],"label":[39,69,84],"hierarchy":[40,70],"and":[41,60,94,113,123,130],"classifies":[42],"items":[43,80,103],"very":[45],"sources.":[48,73],"Five":[49],"steps":[50,65,77,93],"compose":[51],"HMC":[54],"process:":[55],"Indexation,":[56],"Vectorization,":[57],"Hierarchization,":[58],"Resolution":[59],"Realization.":[61],"The":[62,74,116],"first":[63],"three":[64],"construct":[66],"last":[75,91],"two":[76,92],"classify":[78,102],"new":[79,97],"according":[81],"hierarchy.":[85],"paper":[87],"focuses":[88],"presents":[95],"highly":[98],"scalable":[99,122],"huge":[105],"sets":[106],"unstructured":[108],"text":[109],"by":[110],"ontologies":[112],"rule-based":[114],"reasoning.":[115],"implemented":[119],"distributed":[124],"platform":[125],"Data":[129],"some":[131],"results":[132],"are":[133],"discussed.":[134]},"counts_by_year":[],"updated_date":"2026-05-04T08:30:34.212998","created_date":"2025-10-10T00:00:00"}