{"id":"https://openalex.org/W2167075392","doi":"https://doi.org/10.1109/saint.2001.905165","title":"Improving category specific Web search by learning query modifications","display_name":"Improving category specific Web search by learning query modifications","publication_year":2002,"publication_date":"2002-11-13","ids":{"openalex":"https://openalex.org/W2167075392","doi":"https://doi.org/10.1109/saint.2001.905165","mag":"2167075392"},"language":"en","primary_location":{"id":"doi:10.1109/saint.2001.905165","is_oa":false,"landing_page_url":"https://doi.org/10.1109/saint.2001.905165","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings 2001 Symposium on Applications and the Internet","raw_type":"proceedings-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/A5111923887","display_name":"Eric J. Glover","orcid":null},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan\u2013Ann Arbor","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]},{"id":"https://openalex.org/I20089843","display_name":"Princeton University","ror":"https://ror.org/00hx57361","country_code":"US","type":"education","lineage":["https://openalex.org/I20089843"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"E.J. Glover","raw_affiliation_strings":["EECS Department, University of Michigan, Ann Arbor, MI, USA","NEC Research Institute, Inc., Princeton, NJ, USA"],"affiliations":[{"raw_affiliation_string":"EECS Department, University of Michigan, Ann Arbor, MI, USA","institution_ids":["https://openalex.org/I27837315"]},{"raw_affiliation_string":"NEC Research Institute, Inc., Princeton, NJ, USA","institution_ids":["https://openalex.org/I20089843"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033919482","display_name":"Gary William Flake","orcid":null},"institutions":[{"id":"https://openalex.org/I20089843","display_name":"Princeton University","ror":"https://ror.org/00hx57361","country_code":"US","type":"education","lineage":["https://openalex.org/I20089843"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"G.W. Flake","raw_affiliation_strings":["NEC Research Institute, Inc., Princeton, NJ, USA"],"affiliations":[{"raw_affiliation_string":"NEC Research Institute, Inc., Princeton, NJ, USA","institution_ids":["https://openalex.org/I20089843"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043733219","display_name":"Sandra Lawrence","orcid":"https://orcid.org/0000-0003-4429-869X"},"institutions":[{"id":"https://openalex.org/I20089843","display_name":"Princeton University","ror":"https://ror.org/00hx57361","country_code":"US","type":"education","lineage":["https://openalex.org/I20089843"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"S. Lawrence","raw_affiliation_strings":["NEC Research Institute, Inc., Princeton, NJ, USA"],"affiliations":[{"raw_affiliation_string":"NEC Research Institute, Inc., Princeton, NJ, USA","institution_ids":["https://openalex.org/I20089843"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013309904","display_name":"William P. Birmingham","orcid":null},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan\u2013Ann Arbor","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"W.P. Birmingham","raw_affiliation_strings":["EECS Department, University of Michigan, Ann Arbor, MI, USA"],"affiliations":[{"raw_affiliation_string":"EECS Department, University of Michigan, Ann Arbor, MI, USA","institution_ids":["https://openalex.org/I27837315"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018095501","display_name":"Andries Kruger","orcid":"https://orcid.org/0000-0002-9815-570X"},"institutions":[{"id":"https://openalex.org/I20089843","display_name":"Princeton University","ror":"https://ror.org/00hx57361","country_code":"US","type":"education","lineage":["https://openalex.org/I20089843"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"A. Kruger","raw_affiliation_strings":["NEC Research Institute, Inc., Princeton, NJ, USA"],"affiliations":[{"raw_affiliation_string":"NEC Research Institute, Inc., Princeton, NJ, USA","institution_ids":["https://openalex.org/I20089843"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001294898","display_name":"C. Lee Giles","orcid":"https://orcid.org/0000-0002-1931-585X"},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]},{"id":"https://openalex.org/I20089843","display_name":"Princeton University","ror":"https://ror.org/00hx57361","country_code":"US","type":"education","lineage":["https://openalex.org/I20089843"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"C.L. Giles","raw_affiliation_strings":["Information Sciences and Technology, Pennsylvania State University, University Park, PA, USA","NEC Research Institute, Inc., Princeton, NJ, USA"],"affiliations":[{"raw_affiliation_string":"Information Sciences and Technology, Pennsylvania State University, University Park, PA, USA","institution_ids":["https://openalex.org/I130769515"]},{"raw_affiliation_string":"NEC Research Institute, Inc., Princeton, NJ, USA","institution_ids":["https://openalex.org/I20089843"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5110750330","display_name":"D.M. Pennock","orcid":null},"institutions":[{"id":"https://openalex.org/I20089843","display_name":"Princeton University","ror":"https://ror.org/00hx57361","country_code":"US","type":"education","lineage":["https://openalex.org/I20089843"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"D.M. Pennock","raw_affiliation_strings":["NEC Research Institute, Inc., Princeton, NJ, USA"],"affiliations":[{"raw_affiliation_string":"NEC Research Institute, Inc., Princeton, NJ, USA","institution_ids":["https://openalex.org/I20089843"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5111923887"],"corresponding_institution_ids":["https://openalex.org/I20089843","https://openalex.org/I27837315"],"apc_list":null,"apc_paid":null,"fwci":33.3667,"has_fulltext":false,"cited_by_count":115,"citation_normalized_percentile":{"value":0.99698243,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"23","last_page":"32"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9997000098228455,"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":0.9997000098228455,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9958999752998352,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9902999997138977,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.8248825073242188},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.8002074360847473},{"id":"https://openalex.org/keywords/search-engine","display_name":"Search engine","score":0.7565439939498901},{"id":"https://openalex.org/keywords/web-search-query","display_name":"Web search query","score":0.6992208957672119},{"id":"https://openalex.org/keywords/web-query-classification","display_name":"Web query classification","score":0.6288533210754395},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.5239829421043396},{"id":"https://openalex.org/keywords/search-analytics","display_name":"Search analytics","score":0.5024585723876953},{"id":"https://openalex.org/keywords/web-search-engine","display_name":"Web search engine","score":0.5006256103515625},{"id":"https://openalex.org/keywords/spamdexing","display_name":"Spamdexing","score":0.500516414642334},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.4786192774772644},{"id":"https://openalex.org/keywords/query-expansion","display_name":"Query expansion","score":0.4486784338951111},{"id":"https://openalex.org/keywords/web-crawler","display_name":"Web crawler","score":0.42093291878700256}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8248825073242188},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.8002074360847473},{"id":"https://openalex.org/C97854310","wikidata":"https://www.wikidata.org/wiki/Q19541","display_name":"Search engine","level":2,"score":0.7565439939498901},{"id":"https://openalex.org/C164120249","wikidata":"https://www.wikidata.org/wiki/Q995982","display_name":"Web search query","level":3,"score":0.6992208957672119},{"id":"https://openalex.org/C118689300","wikidata":"https://www.wikidata.org/wiki/Q7978614","display_name":"Web query classification","level":4,"score":0.6288533210754395},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.5239829421043396},{"id":"https://openalex.org/C14838553","wikidata":"https://www.wikidata.org/wiki/Q7441639","display_name":"Search analytics","level":4,"score":0.5024585723876953},{"id":"https://openalex.org/C521815418","wikidata":"https://www.wikidata.org/wiki/Q4182287","display_name":"Web search engine","level":4,"score":0.5006256103515625},{"id":"https://openalex.org/C13565553","wikidata":"https://www.wikidata.org/wiki/Q804206","display_name":"Spamdexing","level":5,"score":0.500516414642334},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.4786192774772644},{"id":"https://openalex.org/C99016210","wikidata":"https://www.wikidata.org/wiki/Q5488129","display_name":"Query expansion","level":2,"score":0.4486784338951111},{"id":"https://openalex.org/C13743948","wikidata":"https://www.wikidata.org/wiki/Q45842","display_name":"Web crawler","level":2,"score":0.42093291878700256}],"mesh":[],"locations_count":6,"locations":[{"id":"doi:10.1109/saint.2001.905165","is_oa":false,"landing_page_url":"https://doi.org/10.1109/saint.2001.905165","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings 2001 Symposium on Applications and the Internet","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.11.8325","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.11.8325","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://ranger.uta.edu/~alp/ix/readings/WebPageCategorization.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.147.3405","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.147.3405","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://clgiles.ist.psu.edu/papers/SAINT-2001-learning-queries.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.29.1520","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.29.1520","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.neci.nec.com/homepages/dpennock/papers/glover-2001-saint.ps","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.31.7811","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.31.7811","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.sun.ac.za/projects/tech_reports/US-CS-TR-00-10.ps.gz","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.38.6436","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.38.6436","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.neci.nec.com/~lawrence/papers/search-saint01/search-saint01.ps.gz","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7200000286102295,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W158805393","https://openalex.org/W1489992655","https://openalex.org/W1508511232","https://openalex.org/W1512098439","https://openalex.org/W1534714852","https://openalex.org/W1577933906","https://openalex.org/W1610765524","https://openalex.org/W1659541576","https://openalex.org/W1976959760","https://openalex.org/W1984374364","https://openalex.org/W1997948332","https://openalex.org/W1999817920","https://openalex.org/W2043200638","https://openalex.org/W2076008912","https://openalex.org/W2124673015","https://openalex.org/W2124918383","https://openalex.org/W2149684865","https://openalex.org/W2156909104","https://openalex.org/W4214568865","https://openalex.org/W4292003196","https://openalex.org/W6630409361","https://openalex.org/W6634529573","https://openalex.org/W6636659669","https://openalex.org/W6678308840","https://openalex.org/W6678701036","https://openalex.org/W6682304300"],"related_works":["https://openalex.org/W2980544443","https://openalex.org/W2419328283","https://openalex.org/W1770021664","https://openalex.org/W2389041382","https://openalex.org/W2964491004","https://openalex.org/W2070988406","https://openalex.org/W2223855511","https://openalex.org/W188090516","https://openalex.org/W2296228743","https://openalex.org/W2561589622"],"abstract_inverted_index":{"Users":[0],"looking":[1],"for":[2,25,34,77,83],"documents":[3,14],"within":[4,37],"specific":[5,56,92],"categories":[6,39],"may":[7],"have":[8],"a":[9,47,55],"difficult":[10],"time":[11],"locating":[12,35,78],"valuable":[13],"using":[15,40,61],"general":[16],"purpose":[17],"search":[18,42,93,98],"engines.":[19,43],"We":[20,44],"present":[21,46],"an":[22],"automated":[23],"method":[24],"learning":[26],"query":[27],"modifications":[28],"that":[29,50,71],"can":[30,51],"dramatically":[31],"improve":[32,90],"precision":[33],"pages":[36,53],"specified":[38],"Web":[41],"also":[45],"classification":[48],"procedure":[49],"recognize":[52],"in":[54,94],"category":[57,91],"with":[58],"high":[59],"precision,":[60],"textual":[62],"content,":[63],"text":[64],"location":[65],"and":[66,81],"HTML":[67],"structure.":[68],"Evaluation":[69],"shows":[70],"the":[72,95],"approach":[73],"is":[74],"highly":[75],"effective":[76],"personal":[79],"homepages":[80],"calls":[82],"papers.":[84],"These":[85],"algorithms":[86],"are":[87],"used":[88],"to":[89],"Inquirus":[96],"2":[97],"engine.":[99]},"counts_by_year":[{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":5},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":9}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}
