{"id":"https://openalex.org/W2082269221","doi":"https://doi.org/10.1007/s00354-009-0087-7","title":"Organizing the Web's Information Explosion to Discover Unknown Unknowns","display_name":"Organizing the Web's Information Explosion to Discover Unknown Unknowns","publication_year":2010,"publication_date":"2010-07-01","ids":{"openalex":"https://openalex.org/W2082269221","doi":"https://doi.org/10.1007/s00354-009-0087-7","mag":"2082269221"},"language":"en","primary_location":{"id":"doi:10.1007/s00354-009-0087-7","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s00354-009-0087-7","pdf_url":null,"source":{"id":"https://openalex.org/S165364243","display_name":"New Generation Computing","issn_l":"0288-3635","issn":["0288-3635","1882-7055"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"New Generation Computing","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/A5055783764","display_name":"Kentaro Torisawa","orcid":null},"institutions":[{"id":"https://openalex.org/I90023481","display_name":"National Institute of Information and Communications Technology","ror":"https://ror.org/016bgq349","country_code":"JP","type":"facility","lineage":["https://openalex.org/I90023481"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Kentaro Torisawa","raw_affiliation_strings":["Language Infrastructure Group, MASTAR Project, National Institute of Information and Communications Technology (NICT), 4-2-1, Hikaridai, Seikacho, Kyoto, 619-0288, Japan","Language Infrastructure Group, MASTAR Project, National Institute of Information and Communications Technology (NICT)"],"affiliations":[{"raw_affiliation_string":"Language Infrastructure Group, MASTAR Project, National Institute of Information and Communications Technology (NICT), 4-2-1, Hikaridai, Seikacho, Kyoto, 619-0288, Japan","institution_ids":["https://openalex.org/I90023481"]},{"raw_affiliation_string":"Language Infrastructure Group, MASTAR Project, National Institute of Information and Communications Technology (NICT)","institution_ids":["https://openalex.org/I90023481"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109098548","display_name":"Stijn De Saeger","orcid":null},"institutions":[{"id":"https://openalex.org/I90023481","display_name":"National Institute of Information and Communications Technology","ror":"https://ror.org/016bgq349","country_code":"JP","type":"facility","lineage":["https://openalex.org/I90023481"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Stijn De Saeger","raw_affiliation_strings":["Language Infrastructure Group, MASTAR Project, National Institute of Information and Communications Technology (NICT), 4-2-1, Hikaridai, Seikacho, Kyoto, 619-0288, Japan","Language Infrastructure Group, MASTAR Project, National Institute of Information and Communications Technology (NICT)"],"affiliations":[{"raw_affiliation_string":"Language Infrastructure Group, MASTAR Project, National Institute of Information and Communications Technology (NICT), 4-2-1, Hikaridai, Seikacho, Kyoto, 619-0288, Japan","institution_ids":["https://openalex.org/I90023481"]},{"raw_affiliation_string":"Language Infrastructure Group, MASTAR Project, National Institute of Information and Communications Technology (NICT)","institution_ids":["https://openalex.org/I90023481"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073653623","display_name":"Jun\u2019ichi Kazama","orcid":null},"institutions":[{"id":"https://openalex.org/I90023481","display_name":"National Institute of Information and Communications Technology","ror":"https://ror.org/016bgq349","country_code":"JP","type":"facility","lineage":["https://openalex.org/I90023481"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Jun\u2019ichi Kazama","raw_affiliation_strings":["Language Infrastructure Group, MASTAR Project, National Institute of Information and Communications Technology (NICT), 4-2-1, Hikaridai, Seikacho, Kyoto, 619-0288, Japan","Language Infrastructure Group, MASTAR Project, National Institute of Information and Communications Technology (NICT)"],"affiliations":[{"raw_affiliation_string":"Language Infrastructure Group, MASTAR Project, National Institute of Information and Communications Technology (NICT), 4-2-1, Hikaridai, Seikacho, Kyoto, 619-0288, Japan","institution_ids":["https://openalex.org/I90023481"]},{"raw_affiliation_string":"Language Infrastructure Group, MASTAR Project, National Institute of Information and Communications Technology (NICT)","institution_ids":["https://openalex.org/I90023481"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082126688","display_name":"Asuka Sumida","orcid":null},"institutions":[{"id":"https://openalex.org/I177738480","display_name":"Japan Advanced Institute of Science and Technology","ror":"https://ror.org/03frj4r98","country_code":"JP","type":"education","lineage":["https://openalex.org/I177738480"]},{"id":"https://openalex.org/I90023481","display_name":"National Institute of Information and Communications Technology","ror":"https://ror.org/016bgq349","country_code":"JP","type":"facility","lineage":["https://openalex.org/I90023481"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Asuka Sumida","raw_affiliation_strings":["Japan Advanced Institute of Science and Technology, 1-1 Asahidai, Nomi-shi, Ishikawa, 923-1211, Japan","Language Infrastructure Group, MASTAR Project, National Institute of Information and Communications Technology (NICT), 4-2-1, Hikaridai, Seikacho, Kyoto, 619-0288, Japan","Japan Advanced Institute of Science and Technology","Language Infrastructure Group, MASTAR Project, National Institute of Information and Communications Technology (NICT)"],"affiliations":[{"raw_affiliation_string":"Japan Advanced Institute of Science and Technology, 1-1 Asahidai, Nomi-shi, Ishikawa, 923-1211, Japan","institution_ids":["https://openalex.org/I177738480"]},{"raw_affiliation_string":"Language Infrastructure Group, MASTAR Project, National Institute of Information and Communications Technology (NICT), 4-2-1, Hikaridai, Seikacho, Kyoto, 619-0288, Japan","institution_ids":["https://openalex.org/I90023481"]},{"raw_affiliation_string":"Japan Advanced Institute of Science and Technology","institution_ids":["https://openalex.org/I177738480"]},{"raw_affiliation_string":"Language Infrastructure Group, MASTAR Project, National Institute of Information and Communications Technology (NICT)","institution_ids":["https://openalex.org/I90023481"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078710811","display_name":"Daisuke Noguchi","orcid":null},"institutions":[{"id":"https://openalex.org/I90023481","display_name":"National Institute of Information and Communications Technology","ror":"https://ror.org/016bgq349","country_code":"JP","type":"facility","lineage":["https://openalex.org/I90023481"]},{"id":"https://openalex.org/I118347220","display_name":"NEC (Japan)","ror":"https://ror.org/04jndar25","country_code":"JP","type":"company","lineage":["https://openalex.org/I118347220"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Daisuke Noguchi","raw_affiliation_strings":["Language Infrastructure Group, MASTAR Project, National Institute of Information and Communications Technology (NICT), 4-2-1, Hikaridai, Seikacho, Kyoto, 619-0288, Japan","NEC BIGLOBE Ltd., 11-1, Ohsaki 1-chome, Shinagawa-ku, Tokyo, 141-0032, Japan","Language Infrastructure Group, MASTAR Project, National Institute of Information and Communications Technology (NICT)"],"affiliations":[{"raw_affiliation_string":"Language Infrastructure Group, MASTAR Project, National Institute of Information and Communications Technology (NICT), 4-2-1, Hikaridai, Seikacho, Kyoto, 619-0288, Japan","institution_ids":["https://openalex.org/I90023481"]},{"raw_affiliation_string":"NEC BIGLOBE Ltd., 11-1, Ohsaki 1-chome, Shinagawa-ku, Tokyo, 141-0032, Japan","institution_ids":["https://openalex.org/I118347220"]},{"raw_affiliation_string":"Language Infrastructure Group, MASTAR Project, National Institute of Information and Communications Technology (NICT)","institution_ids":["https://openalex.org/I90023481"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001930281","display_name":"Yasunori Kakizawa","orcid":null},"institutions":[{"id":"https://openalex.org/I90023481","display_name":"National Institute of Information and Communications Technology","ror":"https://ror.org/016bgq349","country_code":"JP","type":"facility","lineage":["https://openalex.org/I90023481"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yasunori Kakizawa","raw_affiliation_strings":["Language Infrastructure Group, MASTAR Project, National Institute of Information and Communications Technology (NICT), 4-2-1, Hikaridai, Seikacho, Kyoto, 619-0288, Japan","Language Infrastructure Group, MASTAR Project, National Institute of Information and Communications Technology (NICT)"],"affiliations":[{"raw_affiliation_string":"Language Infrastructure Group, MASTAR Project, National Institute of Information and Communications Technology (NICT), 4-2-1, Hikaridai, Seikacho, Kyoto, 619-0288, Japan","institution_ids":["https://openalex.org/I90023481"]},{"raw_affiliation_string":"Language Infrastructure Group, MASTAR Project, National Institute of Information and Communications Technology (NICT)","institution_ids":["https://openalex.org/I90023481"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103042688","display_name":"Masaki Murata","orcid":"https://orcid.org/0009-0004-6965-9687"},"institutions":[{"id":"https://openalex.org/I90023481","display_name":"National Institute of Information and Communications Technology","ror":"https://ror.org/016bgq349","country_code":"JP","type":"facility","lineage":["https://openalex.org/I90023481"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Masaki Murata","raw_affiliation_strings":["Language Infrastructure Group, MASTAR Project, National Institute of Information and Communications Technology (NICT), 4-2-1, Hikaridai, Seikacho, Kyoto, 619-0288, Japan","Language Infrastructure Group, MASTAR Project, National Institute of Information and Communications Technology (NICT)"],"affiliations":[{"raw_affiliation_string":"Language Infrastructure Group, MASTAR Project, National Institute of Information and Communications Technology (NICT), 4-2-1, Hikaridai, Seikacho, Kyoto, 619-0288, Japan","institution_ids":["https://openalex.org/I90023481"]},{"raw_affiliation_string":"Language Infrastructure Group, MASTAR Project, National Institute of Information and Communications Technology (NICT)","institution_ids":["https://openalex.org/I90023481"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103582701","display_name":"Kow Kuroda","orcid":null},"institutions":[{"id":"https://openalex.org/I90023481","display_name":"National Institute of Information and Communications Technology","ror":"https://ror.org/016bgq349","country_code":"JP","type":"facility","lineage":["https://openalex.org/I90023481"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kow Kuroda","raw_affiliation_strings":["Language Infrastructure Group, MASTAR Project, National Institute of Information and Communications Technology (NICT), 4-2-1, Hikaridai, Seikacho, Kyoto, 619-0288, Japan","Language Infrastructure Group, MASTAR Project, National Institute of Information and Communications Technology (NICT)"],"affiliations":[{"raw_affiliation_string":"Language Infrastructure Group, MASTAR Project, National Institute of Information and Communications Technology (NICT), 4-2-1, Hikaridai, Seikacho, Kyoto, 619-0288, Japan","institution_ids":["https://openalex.org/I90023481"]},{"raw_affiliation_string":"Language Infrastructure Group, MASTAR Project, National Institute of Information and Communications Technology (NICT)","institution_ids":["https://openalex.org/I90023481"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5050316548","display_name":"Ichiro Yamada","orcid":"https://orcid.org/0000-0001-5214-6309"},"institutions":[{"id":"https://openalex.org/I90023481","display_name":"National Institute of Information and Communications Technology","ror":"https://ror.org/016bgq349","country_code":"JP","type":"facility","lineage":["https://openalex.org/I90023481"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Ichiro Yamada","raw_affiliation_strings":["Language Infrastructure Group, MASTAR Project, National Institute of Information and Communications Technology (NICT), 4-2-1, Hikaridai, Seikacho, Kyoto, 619-0288, Japan","Language Infrastructure Group, MASTAR Project, National Institute of Information and Communications Technology (NICT)"],"affiliations":[{"raw_affiliation_string":"Language Infrastructure Group, MASTAR Project, National Institute of Information and Communications Technology (NICT), 4-2-1, Hikaridai, Seikacho, Kyoto, 619-0288, Japan","institution_ids":["https://openalex.org/I90023481"]},{"raw_affiliation_string":"Language Infrastructure Group, MASTAR Project, National Institute of Information and Communications Technology (NICT)","institution_ids":["https://openalex.org/I90023481"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5055783764"],"corresponding_institution_ids":["https://openalex.org/I90023481"],"apc_list":{"value":2490,"currency":"EUR","value_usd":3090},"apc_paid":null,"fwci":3.2842,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.92471607,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"28","issue":"3","first_page":"217","last_page":"236"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9995999932289124,"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"}},"topics":[{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9995999932289124,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9977999925613403,"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.9970999956130981,"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":0.8555564880371094},{"id":"https://openalex.org/keywords/directory","display_name":"Directory","score":0.8173478841781616},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.6286683678627014},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.607148289680481},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.48784923553466797},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4706152081489563},{"id":"https://openalex.org/keywords/semantic-web","display_name":"Semantic Web","score":0.4493190050125122},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.4404488205909729},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.09216439723968506},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.07585427165031433}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8555564880371094},{"id":"https://openalex.org/C2777683733","wikidata":"https://www.wikidata.org/wiki/Q201456","display_name":"Directory","level":2,"score":0.8173478841781616},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.6286683678627014},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.607148289680481},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.48784923553466797},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4706152081489563},{"id":"https://openalex.org/C2129575","wikidata":"https://www.wikidata.org/wiki/Q54837","display_name":"Semantic Web","level":2,"score":0.4493190050125122},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.4404488205909729},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.09216439723968506},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.07585427165031433},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s00354-009-0087-7","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s00354-009-0087-7","pdf_url":null,"source":{"id":"https://openalex.org/S165364243","display_name":"New Generation Computing","issn_l":"0288-3635","issn":["0288-3635","1882-7055"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"New Generation Computing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W69597389","https://openalex.org/W72624665","https://openalex.org/W89857650","https://openalex.org/W97622340","https://openalex.org/W171181878","https://openalex.org/W197270748","https://openalex.org/W340397307","https://openalex.org/W1502473750","https://openalex.org/W1564094940","https://openalex.org/W1574901103","https://openalex.org/W1593239840","https://openalex.org/W1974383174","https://openalex.org/W2013109830","https://openalex.org/W2022166150","https://openalex.org/W2026247308","https://openalex.org/W2048679005","https://openalex.org/W2049633694","https://openalex.org/W2067044483","https://openalex.org/W2068737686","https://openalex.org/W2100377551","https://openalex.org/W2112508660","https://openalex.org/W2115900915","https://openalex.org/W2127462357","https://openalex.org/W2137023796","https://openalex.org/W2144108169","https://openalex.org/W2144882256","https://openalex.org/W2145328028","https://openalex.org/W2148540243","https://openalex.org/W2148603752","https://openalex.org/W2170205828","https://openalex.org/W2405628206","https://openalex.org/W2882319491","https://openalex.org/W3042139692","https://openalex.org/W6602823196","https://openalex.org/W6603592053","https://openalex.org/W6603979058"],"related_works":["https://openalex.org/W3115906952","https://openalex.org/W3134811395","https://openalex.org/W3155196058","https://openalex.org/W1529821365","https://openalex.org/W2135486207","https://openalex.org/W1499611046","https://openalex.org/W3024420453","https://openalex.org/W2388608119","https://openalex.org/W2915494741","https://openalex.org/W9569021"],"abstract_inverted_index":null,"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}