{"id":"https://openalex.org/W2221553715","doi":"https://doi.org/10.1145/375663.375671","title":"Probe, count, and classify","display_name":"Probe, count, and classify","publication_year":2001,"publication_date":"2001-05-01","ids":{"openalex":"https://openalex.org/W2221553715","doi":"https://doi.org/10.1145/375663.375671","mag":"2221553715"},"language":"en","primary_location":{"is_oa":false,"landing_page_url":"https://doi.org/10.1145/375663.375671","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false},"type":"article","type_crossref":"proceedings-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/A5010731709","display_name":"Panagiotis G. Ipeirotis","orcid":"https://orcid.org/0000-0002-2966-7402"},"institutions":[{"id":"https://openalex.org/I4210156583","display_name":"Laboratoire d'Informatique de Paris-Nord","ror":"https://ror.org/05g1zjw44","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I4210091279","https://openalex.org/I4210156583","https://openalex.org/I4210159245"]},{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["FR","US"],"is_corresponding":false,"raw_author_name":"Panagiotis G. Ipeirotis","raw_affiliation_strings":["Computer Science Dept., Columbia University"],"affiliations":[{"raw_affiliation_string":"Computer Science Dept., Columbia University","institution_ids":["https://openalex.org/I4210156583","https://openalex.org/I78577930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080063580","display_name":"Luis Gravano","orcid":null},"institutions":[{"id":"https://openalex.org/I4210156583","display_name":"Laboratoire d'Informatique de Paris-Nord","ror":"https://ror.org/05g1zjw44","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I4210091279","https://openalex.org/I4210156583","https://openalex.org/I4210159245"]},{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["FR","US"],"is_corresponding":false,"raw_author_name":"Luis Gravano","raw_affiliation_strings":["Computer Science Dept., Columbia University"],"affiliations":[{"raw_affiliation_string":"Computer Science Dept., Columbia University","institution_ids":["https://openalex.org/I4210156583","https://openalex.org/I78577930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5054695014","display_name":"Mehran Sahami","orcid":"https://orcid.org/0000-0001-9549-6974"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mehran Sahami","raw_affiliation_strings":["E.piphany, Inc."],"affiliations":[{"raw_affiliation_string":"E.piphany, Inc.","institution_ids":[]}]}],"institution_assertions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":10.137,"has_fulltext":true,"fulltext_origin":"ngrams","cited_by_count":159,"citation_normalized_percentile":{"value":0.902377,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"67","last_page":"78"},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9685,"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":0.9685,"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":[],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.49832296},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37389928},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.33443362}],"mesh":[],"locations_count":1,"locations":[{"is_oa":false,"landing_page_url":"https://doi.org/10.1145/375663.375671","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false}],"best_oa_location":null,"sustainable_development_goals":[],"grants":[],"datasets":[],"versions":[],"referenced_works_count":34,"referenced_works":["https://openalex.org/W1489384387","https://openalex.org/W1517178556","https://openalex.org/W1539477445","https://openalex.org/W1550206324","https://openalex.org/W1553682320","https://openalex.org/W1620204465","https://openalex.org/W1849729440","https://openalex.org/W1978394996","https://openalex.org/W2005422315","https://openalex.org/W2012426233","https://openalex.org/W2016892599","https://openalex.org/W2018157370","https://openalex.org/W2058374187","https://openalex.org/W2058982198","https://openalex.org/W2060216474","https://openalex.org/W2061973112","https://openalex.org/W2079656678","https://openalex.org/W2091777463","https://openalex.org/W2094934653","https://openalex.org/W2099944991","https://openalex.org/W2116908444","https://openalex.org/W2124918383","https://openalex.org/W2125725207","https://openalex.org/W2137845970","https://openalex.org/W2144533137","https://openalex.org/W2149684865","https://openalex.org/W2164547069","https://openalex.org/W2169044456","https://openalex.org/W2170654002","https://openalex.org/W3143553289","https://openalex.org/W4247346926","https://openalex.org/W4285719527","https://openalex.org/W4292003196","https://openalex.org/W4405107181"],"related_works":["https://openalex.org/W4396701345","https://openalex.org/W4391913857","https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2376932109","https://openalex.org/W2358668433","https://openalex.org/W2042327336","https://openalex.org/W2033914206"],"abstract_inverted_index":{"The":[0],"contents":[1],"of":[2,27,39,83,110,129,134,160],"many":[3],"valuable":[4],"web-accessible":[5,59,141],"databases":[6,60],"are":[7,14],"only":[8,44],"accessible":[9],"through":[10],"search":[11],"interfaces":[12],"and":[13,152],"hence":[15],"invisible":[16],"to":[17,31,56],"traditional":[18],"web":[19,42,52],"\"crawlers.\"":[20],"Recent":[21],"studies":[22],"have":[23,54,123],"estimated":[24,46],"the":[25,37,40,102,108,118],"size":[26,38],"this":[28,67,75],"\"hidden":[29],"web\"":[30],"be":[32],"500":[33],"billion":[34,48],"pages,":[35],"while":[36],"\"crawlable\"":[41],"is":[43],"an":[45,125],"two":[47],"pages.":[49],"Recently,":[50],"commercial":[51],"sites":[53],"started":[55],"manually":[57],"organize":[58],"into":[61],"Yahoo!-like":[62],"hierarchical":[63],"classification":[64,76,155],"schemes.":[65],"In":[66],"paper,":[68],"we":[69],"introduce":[70],"a":[71,80,88,158],"method":[72],"for":[73],"automating":[74],"process":[77],"by":[78],"using":[79],"small":[81],"number":[82,109],"query":[84,114],"probes.":[85],"To":[86],"classify":[87],"database,":[89,103],"our":[90,130,147],"algorithm":[91],"does":[92],"not":[93],"retrieve":[94],"or":[95,99],"inspect":[96],"any":[97],"documents":[98],"pages":[100],"from":[101],"but":[104],"rather":[105],"just":[106],"exploits":[107],"matches":[111],"that":[112,146],"each":[113],"probe":[115],"generates":[116],"at":[117],"database":[119],"in":[120],"question.":[121],"We":[122],"conducted":[124],"extensive":[126],"experimental":[127],"evaluation":[128],"technique":[131],"over":[132,138],"collections":[133],"real":[135],"documents,":[136],"including":[137],"one":[139],"hundred":[140],"databases.":[142,161],"Our":[143],"experiments":[144],"show":[145],"system":[148],"has":[149],"low":[150],"overhead":[151],"achieves":[153],"high":[154],"accuracy":[156],"across":[157],"variety":[159]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W2221553715","counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":5},{"year":2015,"cited_by_count":6},{"year":2014,"cited_by_count":8},{"year":2013,"cited_by_count":6},{"year":2012,"cited_by_count":5}],"updated_date":"2024-12-10T20:03:20.616659","created_date":"2016-06-24"}