{"id":"https://openalex.org/W2126631147","doi":"https://doi.org/10.1007/s007780050061","title":"Scalable feature selection, classification and signature generation for organizing large text databases into hierarchical topic taxonomies","display_name":"Scalable feature selection, classification and signature generation for organizing large text databases into hierarchical topic taxonomies","publication_year":1998,"publication_date":"1998-08-01","ids":{"openalex":"https://openalex.org/W2126631147","doi":"https://doi.org/10.1007/s007780050061","mag":"2126631147"},"language":"en","primary_location":{"id":"doi:10.1007/s007780050061","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s007780050061","pdf_url":null,"source":{"id":"https://openalex.org/S78926909","display_name":"The VLDB Journal","issn_l":"0949-877X","issn":["0949-877X","1066-8888"],"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":"The VLDB Journal The International Journal on Very Large Data Bases","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/A5101457009","display_name":"Soumen Chakrabarti","orcid":"https://orcid.org/0000-0002-9419-7486"},"institutions":[{"id":"https://openalex.org/I4210085935","display_name":"IBM Research - Almaden","ror":"https://ror.org/005w8dd04","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210085935","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Soumen Chakrabarti","raw_affiliation_strings":["IBM Almaden Research Center, 650 Harry Road, San Jose, CA 95120, USA; e-mail: soumen,dom,ragrawal,pragh@almaden.ibm.com\n, , , , , , US","IBM Almaden Research center, 650 Harry Road, San Jose, CA, 95120, USA"],"affiliations":[{"raw_affiliation_string":"IBM Almaden Research Center, 650 Harry Road, San Jose, CA 95120, USA; e-mail: soumen,dom,ragrawal,pragh@almaden.ibm.com\n, , , , , , US","institution_ids":["https://openalex.org/I4210085935"]},{"raw_affiliation_string":"IBM Almaden Research center, 650 Harry Road, San Jose, CA, 95120, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031458509","display_name":"Byron Dom","orcid":null},"institutions":[{"id":"https://openalex.org/I4210085935","display_name":"IBM Research - Almaden","ror":"https://ror.org/005w8dd04","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210085935","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Byron Dom","raw_affiliation_strings":["IBM Almaden Research Center, 650 Harry Road, San Jose, CA 95120, USA; e-mail: soumen,dom,ragrawal,pragh@almaden.ibm.com\n, , , , , , US","e-mail: soumen,dom,ragrawal,pragh@almaden.ibm.com"],"affiliations":[{"raw_affiliation_string":"IBM Almaden Research Center, 650 Harry Road, San Jose, CA 95120, USA; e-mail: soumen,dom,ragrawal,pragh@almaden.ibm.com\n, , , , , , US","institution_ids":["https://openalex.org/I4210085935"]},{"raw_affiliation_string":"e-mail: soumen,dom,ragrawal,pragh@almaden.ibm.com","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108315225","display_name":"Rakesh Agrawal","orcid":null},"institutions":[{"id":"https://openalex.org/I4210085935","display_name":"IBM Research - Almaden","ror":"https://ror.org/005w8dd04","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210085935","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rakesh Agrawal","raw_affiliation_strings":["IBM Almaden Research Center, 650 Harry Road, San Jose, CA 95120, USA; e-mail: soumen,dom,ragrawal,pragh@almaden.ibm.com\n, , , , , , US","IBM Almaden Research center, 650 Harry Road, San Jose, CA, 95120, USA"],"affiliations":[{"raw_affiliation_string":"IBM Almaden Research Center, 650 Harry Road, San Jose, CA 95120, USA; e-mail: soumen,dom,ragrawal,pragh@almaden.ibm.com\n, , , , , , US","institution_ids":["https://openalex.org/I4210085935"]},{"raw_affiliation_string":"IBM Almaden Research center, 650 Harry Road, San Jose, CA, 95120, USA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5078491738","display_name":"Prabhakar Raghavan","orcid":"https://orcid.org/0000-0001-9853-7604"},"institutions":[{"id":"https://openalex.org/I4210085935","display_name":"IBM Research - Almaden","ror":"https://ror.org/005w8dd04","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210085935","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Prabhakar Raghavan","raw_affiliation_strings":["IBM Almaden Research Center, 650 Harry Road, San Jose, CA 95120, USA; e-mail: soumen,dom,ragrawal,pragh@almaden.ibm.com\n, , , , , , US","e-mail: soumen,dom,ragrawal,pragh@almaden.ibm.com"],"affiliations":[{"raw_affiliation_string":"IBM Almaden Research Center, 650 Harry Road, San Jose, CA 95120, USA; e-mail: soumen,dom,ragrawal,pragh@almaden.ibm.com\n, , , , , , US","institution_ids":["https://openalex.org/I4210085935"]},{"raw_affiliation_string":"e-mail: soumen,dom,ragrawal,pragh@almaden.ibm.com","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5101457009"],"corresponding_institution_ids":["https://openalex.org/I4210085935"],"apc_list":{"value":2290,"currency":"EUR","value_usd":2890},"apc_paid":null,"fwci":10.4359,"has_fulltext":false,"cited_by_count":230,"citation_normalized_percentile":{"value":0.98341499,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":"7","issue":"3","first_page":"163","last_page":"178"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9979000091552734,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9979000091552734,"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":0.9976000189781189,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9976000189781189,"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":0.8632379770278931},{"id":"https://openalex.org/keywords/joins","display_name":"Joins","score":0.7744914293289185},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.6299633979797363},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.581445574760437},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5395045280456543},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.5163010954856873},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4665068984031677},{"id":"https://openalex.org/keywords/feature-selection","display_name":"Feature selection","score":0.46620261669158936},{"id":"https://openalex.org/keywords/document-classification","display_name":"Document classification","score":0.42855286598205566},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.33896273374557495},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.33608779311180115},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.21382266283035278}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8632379770278931},{"id":"https://openalex.org/C2778692605","wikidata":"https://www.wikidata.org/wiki/Q4041866","display_name":"Joins","level":2,"score":0.7744914293289185},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.6299633979797363},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.581445574760437},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5395045280456543},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.5163010954856873},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4665068984031677},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.46620261669158936},{"id":"https://openalex.org/C2780479914","wikidata":"https://www.wikidata.org/wiki/Q302088","display_name":"Document classification","level":2,"score":0.42855286598205566},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.33896273374557495},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.33608779311180115},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.21382266283035278},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1007/s007780050061","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s007780050061","pdf_url":null,"source":{"id":"https://openalex.org/S78926909","display_name":"The VLDB Journal","issn_l":"0949-877X","issn":["0949-877X","1066-8888"],"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":"The VLDB Journal The International Journal on Very Large Data Bases","raw_type":"journal-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.30.4612","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.30.4612","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://link.springer-ny.com/link/service/journals/00778/tocs/../papers/8007003/80070163.ps.gz","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.33.2822","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.33.2822","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.berkeley.edu/~soumen/VLDB54_3.PDF","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":47,"referenced_works":["https://openalex.org/W1518603657","https://openalex.org/W1527532036","https://openalex.org/W1530657611","https://openalex.org/W1536628706","https://openalex.org/W1555244713","https://openalex.org/W1557657228","https://openalex.org/W1592212241","https://openalex.org/W1594031697","https://openalex.org/W1620204465","https://openalex.org/W1770825568","https://openalex.org/W1840338487","https://openalex.org/W1868287705","https://openalex.org/W1956559956","https://openalex.org/W1966553486","https://openalex.org/W1978394996","https://openalex.org/W1988520084","https://openalex.org/W1997841190","https://openalex.org/W2002016471","https://openalex.org/W2004075725","https://openalex.org/W2008375984","https://openalex.org/W2014415866","https://openalex.org/W2028962062","https://openalex.org/W2034795026","https://openalex.org/W2043403353","https://openalex.org/W2046495522","https://openalex.org/W2058982198","https://openalex.org/W2063392856","https://openalex.org/W2064379477","https://openalex.org/W2076008912","https://openalex.org/W2078376347","https://openalex.org/W2079656678","https://openalex.org/W2085129404","https://openalex.org/W2094934653","https://openalex.org/W2099111195","https://openalex.org/W2124591829","https://openalex.org/W2125055259","https://openalex.org/W2140354722","https://openalex.org/W2147152072","https://openalex.org/W2215091624","https://openalex.org/W2321470647","https://openalex.org/W2435251607","https://openalex.org/W2440833291","https://openalex.org/W2607893089","https://openalex.org/W2911779492","https://openalex.org/W2919963289","https://openalex.org/W2974222084","https://openalex.org/W3017143921"],"related_works":["https://openalex.org/W17155033","https://openalex.org/W2088925915","https://openalex.org/W2382891957","https://openalex.org/W2393491644","https://openalex.org/W3207760230","https://openalex.org/W1496222301","https://openalex.org/W2067184662","https://openalex.org/W1590307681","https://openalex.org/W2536018345","https://openalex.org/W2900292107"],"abstract_inverted_index":null,"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":3},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":15},{"year":2013,"cited_by_count":8},{"year":2012,"cited_by_count":9}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}
