{"id":"https://openalex.org/W2151007976","doi":"https://doi.org/10.1145/1031114.1031117","title":"Topical web crawlers","display_name":"Topical web crawlers","publication_year":2004,"publication_date":"2004-11-01","ids":{"openalex":"https://openalex.org/W2151007976","doi":"https://doi.org/10.1145/1031114.1031117","mag":"2151007976"},"language":"en","primary_location":{"id":"doi:10.1145/1031114.1031117","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1031114.1031117","pdf_url":null,"source":{"id":"https://openalex.org/S97833917","display_name":"ACM Transactions on Internet Technology","issn_l":"1533-5399","issn":["1533-5399","1557-6051"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Internet Technology","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/A5021346979","display_name":"Filippo Menczer","orcid":"https://orcid.org/0000-0003-4384-2876"},"institutions":[{"id":"https://openalex.org/I4210119109","display_name":"Indiana University Bloomington","ror":"https://ror.org/02k40bc56","country_code":"US","type":"education","lineage":["https://openalex.org/I4210119109","https://openalex.org/I592451"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Filippo Menczer","raw_affiliation_strings":["Indiana University, Bloomington, IN"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indiana University, Bloomington, IN","institution_ids":["https://openalex.org/I4210119109"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038050803","display_name":"Gautam Pant","orcid":"https://orcid.org/0000-0001-7414-2325"},"institutions":[{"id":"https://openalex.org/I223532165","display_name":"University of Utah","ror":"https://ror.org/03r0ha626","country_code":"US","type":"education","lineage":["https://openalex.org/I223532165"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gautam Pant","raw_affiliation_strings":["University of Utah, Salt Lake City, UT"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Utah, Salt Lake City, UT","institution_ids":["https://openalex.org/I223532165"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016839456","display_name":"Padmini Srinivasan","orcid":"https://orcid.org/0000-0001-8791-403X"},"institutions":[{"id":"https://openalex.org/I126307644","display_name":"University of Iowa","ror":"https://ror.org/036jqmy94","country_code":"US","type":"education","lineage":["https://openalex.org/I126307644"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Padmini Srinivasan","raw_affiliation_strings":["University of Iowa, Iowa City, IA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Iowa, Iowa City, IA","institution_ids":["https://openalex.org/I126307644"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":36.2147,"has_fulltext":false,"cited_by_count":270,"citation_normalized_percentile":{"value":0.99646214,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":"4","issue":"4","first_page":"378","last_page":"419"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9995999932289124,"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":0.9995999932289124,"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/T11478","display_name":"Caching and Content Delivery","score":0.98580002784729,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T10742","display_name":"Peer-to-Peer Network Technologies","score":0.9783999919891357,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/web-crawler","display_name":"Web crawler","score":0.9170355796813965},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.9028353691101074},{"id":"https://openalex.org/keywords/crawling","display_name":"Crawling","score":0.8842247724533081},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.778183102607727},{"id":"https://openalex.org/keywords/focused-crawler","display_name":"Focused crawler","score":0.7340986728668213},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5177389979362488},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.47655871510505676},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.37174850702285767},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3377852439880371},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.18893206119537354},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.17468881607055664},{"id":"https://openalex.org/keywords/web-navigation","display_name":"Web navigation","score":0.14001420140266418}],"concepts":[{"id":"https://openalex.org/C13743948","wikidata":"https://www.wikidata.org/wiki/Q45842","display_name":"Web crawler","level":2,"score":0.9170355796813965},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.9028353691101074},{"id":"https://openalex.org/C100368936","wikidata":"https://www.wikidata.org/wiki/Q1411725","display_name":"Crawling","level":2,"score":0.8842247724533081},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.778183102607727},{"id":"https://openalex.org/C73340581","wikidata":"https://www.wikidata.org/wiki/Q5463958","display_name":"Focused crawler","level":5,"score":0.7340986728668213},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5177389979362488},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.47655871510505676},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.37174850702285767},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3377852439880371},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.18893206119537354},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.17468881607055664},{"id":"https://openalex.org/C61096286","wikidata":"https://www.wikidata.org/wiki/Q7978592","display_name":"Web navigation","level":3,"score":0.14001420140266418},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C105702510","wikidata":"https://www.wikidata.org/wiki/Q514","display_name":"Anatomy","level":1,"score":0.0},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0},{"id":"https://openalex.org/C173576120","wikidata":"https://www.wikidata.org/wiki/Q2641220","display_name":"Static web page","level":4,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1031114.1031117","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1031114.1031117","pdf_url":null,"source":{"id":"https://openalex.org/S97833917","display_name":"ACM Transactions on Internet Technology","issn_l":"1533-5399","issn":["1533-5399","1557-6051"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Internet Technology","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","score":0.46000000834465027,"display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":47,"referenced_works":["https://openalex.org/W110443600","https://openalex.org/W125867323","https://openalex.org/W160262995","https://openalex.org/W1485536830","https://openalex.org/W1489992655","https://openalex.org/W1504010199","https://openalex.org/W1555999627","https://openalex.org/W1562405179","https://openalex.org/W1566984846","https://openalex.org/W1608864735","https://openalex.org/W1659541576","https://openalex.org/W1674850363","https://openalex.org/W1679844312","https://openalex.org/W1963805119","https://openalex.org/W1965942030","https://openalex.org/W1966496085","https://openalex.org/W2001832505","https://openalex.org/W2001834587","https://openalex.org/W2005579877","https://openalex.org/W2007687650","https://openalex.org/W2020423193","https://openalex.org/W2029341294","https://openalex.org/W2042330455","https://openalex.org/W2044743392","https://openalex.org/W2045998703","https://openalex.org/W2059713800","https://openalex.org/W2066636486","https://openalex.org/W2067338315","https://openalex.org/W2098162425","https://openalex.org/W2102931907","https://openalex.org/W2115579680","https://openalex.org/W2117850397","https://openalex.org/W2120870126","https://openalex.org/W2124673015","https://openalex.org/W2138621811","https://openalex.org/W2141825421","https://openalex.org/W2147164982","https://openalex.org/W2149257407","https://openalex.org/W2151626491","https://openalex.org/W2162502927","https://openalex.org/W2166007234","https://openalex.org/W2766736793","https://openalex.org/W2902404196","https://openalex.org/W2997385171","https://openalex.org/W4285719527","https://openalex.org/W6633534558","https://openalex.org/W7026841064"],"related_works":["https://openalex.org/W4385695127","https://openalex.org/W2375180657","https://openalex.org/W2042034567","https://openalex.org/W2026132847","https://openalex.org/W2137810919","https://openalex.org/W2358310581","https://openalex.org/W2274831913","https://openalex.org/W2352686120","https://openalex.org/W2019080882","https://openalex.org/W1506122440"],"abstract_inverted_index":{"Topical":[0],"crawlers":[1,34,115,169,181],"are":[2],"increasingly":[3],"seen":[4],"as":[5],"a":[6,53,62,68,110,134],"way":[7],"to":[8,32,55,73,109,121],"address":[9],"the":[10,19,37,42,86,99,106,128,149,152,163,167,189,196],"scalability":[11,186],"limitations":[12],"of":[13,39,44,64,105,137,151,166],"universal":[14],"search":[15],"engines,":[16],"by":[17,133,187],"distributing":[18,188],"crawling":[20,59],"process":[21],"across":[22,191],"users,":[23],"queries,":[24],"or":[25],"even":[26],"client":[27],"computers.":[28],"The":[29],"context":[30],"available":[31,108,178],"such":[33],"can":[35],"guide":[36,122],"navigation":[38],"links":[40],"with":[41,177],"goal":[43],"efficiently":[45],"locating":[46],"highly":[47,80],"relevant":[48],"target":[49],"pages.":[50],"We":[51,125,160],"developed":[52],"framework":[54,69],"fairly":[56],"evaluate":[57,74],"topical":[58],"algorithms":[60,76],"under":[61],"number":[63],"performance":[65,130,150,173],"metrics.":[66],"Such":[67],"is":[70,131],"employed":[71],"here":[72],"different":[75],"that":[77,116,127,147],"have":[78],"proven":[79],"competitive":[81],"among":[82],"those":[83],"proposed":[84],"in":[85,89,195],"literature":[87],"and":[88,103,112,139,142,170,174,185],"our":[90],"own":[91],"previous":[92],"research.":[93],"In":[94],"particular":[95],"we":[96],"focus":[97],"on":[98,113],"tradeoff":[100],"between":[101],"exploration":[102],"exploitation":[104],"cues":[107],"crawler,":[111],"adaptive":[114],"use":[117],"machine":[118],"learning":[119],"techniques":[120],"their":[123],"search.":[124],"find":[126],"best":[129,153,197],"achieved":[132],"novel":[135],"combination":[136],"explorative":[138],"exploitative":[140],"bias,":[141],"introduce":[143],"an":[144],"evolutionary":[145],"crawler":[146,155],"surpasses":[148],"nonadaptive":[154],"after":[156],"sufficiently":[157],"long":[158],"crawls.":[159],"also":[161],"analyze":[162],"computational":[164],"complexity":[165,175],"various":[168],"discuss":[171],"how":[172],"scale":[176],"resources.":[179],"Evolutionary":[180],"achieve":[182],"high":[183],"efficiency":[184],"work":[190],"concurrent":[192],"agents,":[193],"resulting":[194],"performance/cost":[198],"ratio.":[199]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":8},{"year":2021,"cited_by_count":8},{"year":2020,"cited_by_count":6},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":6},{"year":2017,"cited_by_count":11},{"year":2016,"cited_by_count":8},{"year":2015,"cited_by_count":11},{"year":2014,"cited_by_count":18},{"year":2013,"cited_by_count":30},{"year":2012,"cited_by_count":20}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}
