{"id":"https://openalex.org/W2161023902","doi":"https://doi.org/10.1145/1141753.1141801","title":"Categorizing web search results into meaningful and stable categories using fast-feature techniques","display_name":"Categorizing web search results into meaningful and stable categories using fast-feature techniques","publication_year":2006,"publication_date":"2006-06-11","ids":{"openalex":"https://openalex.org/W2161023902","doi":"https://doi.org/10.1145/1141753.1141801","mag":"2161023902"},"language":"en","primary_location":{"id":"doi:10.1145/1141753.1141801","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1141753.1141801","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 6th ACM/IEEE-CS joint conference on Digital libraries","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/A5074615503","display_name":"Bill Kules","orcid":null},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bill Kules","raw_affiliation_strings":["University of Maryland, College Park, MD"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Maryland, College Park, MD","institution_ids":["https://openalex.org/I66946132"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087603701","display_name":"Jack Kustanowitz","orcid":null},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jack Kustanowitz","raw_affiliation_strings":["University of Maryland, College Park, MD"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Maryland, College Park, MD","institution_ids":["https://openalex.org/I66946132"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5052623072","display_name":"Ben Shneiderman","orcid":"https://orcid.org/0000-0002-8298-1097"},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ben Shneiderman","raw_affiliation_strings":["University of Maryland, College Park, MD"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Maryland, College Park, MD","institution_ids":["https://openalex.org/I66946132"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I66946132"],"apc_list":null,"apc_paid":null,"fwci":13.0529,"has_fulltext":false,"cited_by_count":55,"citation_normalized_percentile":{"value":0.98745007,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"210","last_page":"219"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9991999864578247,"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":0.9991999864578247,"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/T10286","display_name":"Information Retrieval and Search Behavior","score":0.9907000064849854,"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":0.9789999723434448,"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":0.7842661142349243},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6809359788894653},{"id":"https://openalex.org/keywords/categorization","display_name":"Categorization","score":0.6197762489318848},{"id":"https://openalex.org/keywords/directory","display_name":"Directory","score":0.6045379638671875},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.6023341417312622},{"id":"https://openalex.org/keywords/snippet","display_name":"Snippet","score":0.5917688608169556},{"id":"https://openalex.org/keywords/search-engine","display_name":"Search engine","score":0.5459604859352112},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5442363023757935},{"id":"https://openalex.org/keywords/metadata","display_name":"Metadata","score":0.5266458988189697},{"id":"https://openalex.org/keywords/web-search-engine","display_name":"Web search engine","score":0.5183490514755249},{"id":"https://openalex.org/keywords/web-crawler","display_name":"Web crawler","score":0.4889148771762848},{"id":"https://openalex.org/keywords/web-resource","display_name":"Web resource","score":0.45593422651290894},{"id":"https://openalex.org/keywords/hierarchy","display_name":"Hierarchy","score":0.44715356826782227},{"id":"https://openalex.org/keywords/search-analytics","display_name":"Search analytics","score":0.42613059282302856},{"id":"https://openalex.org/keywords/web-search-query","display_name":"Web search query","score":0.39831867814064026},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.13257956504821777}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7842661142349243},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6809359788894653},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.6197762489318848},{"id":"https://openalex.org/C2777683733","wikidata":"https://www.wikidata.org/wiki/Q201456","display_name":"Directory","level":2,"score":0.6045379638671875},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.6023341417312622},{"id":"https://openalex.org/C2777822670","wikidata":"https://www.wikidata.org/wiki/Q1120538","display_name":"Snippet","level":2,"score":0.5917688608169556},{"id":"https://openalex.org/C97854310","wikidata":"https://www.wikidata.org/wiki/Q19541","display_name":"Search engine","level":2,"score":0.5459604859352112},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5442363023757935},{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.5266458988189697},{"id":"https://openalex.org/C521815418","wikidata":"https://www.wikidata.org/wiki/Q4182287","display_name":"Web search engine","level":4,"score":0.5183490514755249},{"id":"https://openalex.org/C13743948","wikidata":"https://www.wikidata.org/wiki/Q45842","display_name":"Web crawler","level":2,"score":0.4889148771762848},{"id":"https://openalex.org/C65603577","wikidata":"https://www.wikidata.org/wiki/Q3427877","display_name":"Web resource","level":2,"score":0.45593422651290894},{"id":"https://openalex.org/C31170391","wikidata":"https://www.wikidata.org/wiki/Q188619","display_name":"Hierarchy","level":2,"score":0.44715356826782227},{"id":"https://openalex.org/C14838553","wikidata":"https://www.wikidata.org/wiki/Q7441639","display_name":"Search analytics","level":4,"score":0.42613059282302856},{"id":"https://openalex.org/C164120249","wikidata":"https://www.wikidata.org/wiki/Q995982","display_name":"Web search query","level":3,"score":0.39831867814064026},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.13257956504821777},{"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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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":3,"locations":[{"id":"doi:10.1145/1141753.1141801","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1141753.1141801","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 6th ACM/IEEE-CS joint conference on Digital libraries","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.359.7855","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.359.7855","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.umd.edu/~ben/papers/Kules2006Categorizing.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.76.9379","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.76.9379","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://hcil.cs.umd.edu/trs/2006-15/2006-15.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6899999976158142,"display_name":"Decent work and economic growth","id":"https://metadata.un.org/sdg/8"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W1543886729","https://openalex.org/W1598285388","https://openalex.org/W2008781077","https://openalex.org/W2023408138","https://openalex.org/W2031548498","https://openalex.org/W2063862666","https://openalex.org/W2067223933","https://openalex.org/W2074449313","https://openalex.org/W2076008912","https://openalex.org/W2076452960","https://openalex.org/W2087031692","https://openalex.org/W2100958137","https://openalex.org/W2101005742","https://openalex.org/W2106180529","https://openalex.org/W2116341550","https://openalex.org/W2116908444","https://openalex.org/W2118020653","https://openalex.org/W2124159267","https://openalex.org/W2127994451","https://openalex.org/W2128868253","https://openalex.org/W2135778849","https://openalex.org/W2147327597","https://openalex.org/W2156037541","https://openalex.org/W2162827959","https://openalex.org/W2169899598","https://openalex.org/W2196501509","https://openalex.org/W2296157284","https://openalex.org/W2501639669","https://openalex.org/W2911381658","https://openalex.org/W3015720892","https://openalex.org/W4251308671","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W2165396088","https://openalex.org/W2379145789","https://openalex.org/W3199173531","https://openalex.org/W2898209107","https://openalex.org/W2423684479","https://openalex.org/W2980544443","https://openalex.org/W4200125296","https://openalex.org/W1770021664","https://openalex.org/W33687805","https://openalex.org/W4389795082"],"abstract_inverted_index":{"When":[0],"search":[1,41,87,110,114,133,160,187],"results":[2,52,95],"against":[3],"digital":[4],"libraries":[5],"and":[6,16,24,48,78,116,135,146,170],"web":[7,76,109,113,175],"resources":[8],"have":[9,154],"limited":[10],"metadata,":[11],"augmenting":[12],"them":[13],"with":[14],"meaningful":[15,54],"stable":[17],"category":[18],"information":[19],"can":[20],"enable":[21],"better":[22],"overviews":[23],"support":[25,183],"user":[26],"exploration.":[27],"This":[28],"paper":[29],"proposes":[30],"six":[31],"fast-feature":[32],"techniques":[33,153],"that":[34],"use":[35,57],"only":[36],"features":[37],"available":[38],"in":[39,157],"the":[40,71,92,117,140,144,149],"result":[42],"list,":[43],"such":[44],"as":[45],"title,":[46],"snippet,":[47],"URL,":[49],"to":[50,82,86,104,131,166,182],"categorize":[51],"into":[53],"categories.":[55],"They":[56],"credible":[58],"knowledge":[59],"resources,":[60],"including":[61],"a":[62,67,132,158],"US":[63],"government":[64,112],"organizational":[65],"hierarchy,":[66],"thematic":[68],"hierarchy":[69],"from":[70],"Open":[72],"Directory":[73],"Project":[74],"(ODP)":[75],"directory,":[77],"personal":[79],"browse":[80],"histories,":[81],"add":[83],"valuable":[84],"metadata":[85],"results.":[88,188],"In":[89],"three":[90],"tests":[91],"percent":[93],"of":[94,119,139,148,186],"categorized":[96,137],"for":[97],"five":[98],"representative":[99],"queries":[100,130],"was":[101],"high":[102],"enough":[103],"suggest":[105],"practical":[106],"benefits:":[107],"general":[108],"(76-90%),":[111],"(39-100%),":[115],"Bureau":[118],"Labor":[120],"Statistics":[121],"website":[122],"(48-94%).":[123],"An":[124],"additional":[125],"test":[126],"submitted":[127],"250":[128],"TREC":[129],"engine":[134],"successfully":[136],"66%":[138],"top":[141,150],"100":[142],"using":[143],"ODP":[145],"61%":[147],"350.":[151],"Fast-feature":[152],"been":[155],"implemented":[156],"prototype":[159],"engine.":[161],"We":[162],"propose":[163],"research":[164],"directions":[165],"improve":[167],"categorization":[168,185],"rates":[169],"make":[171],"suggestions":[172],"about":[173],"how":[174],"site":[176],"designers":[177],"could":[178],"re-organize":[179],"their":[180],"sites":[181],"fast":[184]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":4},{"year":2012,"cited_by_count":5}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}
