{"id":"https://openalex.org/W2105803339","doi":"https://doi.org/10.1145/1367497.1367558","title":"iRobot","display_name":"iRobot","publication_year":2008,"publication_date":"2008-04-21","ids":{"openalex":"https://openalex.org/W2105803339","doi":"https://doi.org/10.1145/1367497.1367558","mag":"2105803339"},"language":"en","primary_location":{"id":"doi:10.1145/1367497.1367558","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1367497.1367558","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 17th international conference on World Wide Web","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/A5069272117","display_name":"Rui Cai","orcid":"https://orcid.org/0000-0002-6499-2091"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rui Cai","raw_affiliation_strings":["Microsoft Research, Asia, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research, Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002360117","display_name":"Jiang-Ming Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiang-Ming Yang","raw_affiliation_strings":["Microsoft Research, Asia, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research, Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012372031","display_name":"Wei Lai","orcid":"https://orcid.org/0000-0002-9385-4421"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Lai","raw_affiliation_strings":["Microsoft Research, Asia, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research, Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101638214","display_name":"Yida Wang","orcid":"https://orcid.org/0000-0001-8165-840X"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yida Wang","raw_affiliation_strings":["Microsoft Research, Asia, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research, Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100433855","display_name":"Lei Zhang","orcid":"https://orcid.org/0000-0001-9343-3654"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lei Zhang","raw_affiliation_strings":["Microsoft Research, Asia, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research, Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210113369"],"apc_list":null,"apc_paid":null,"fwci":17.5225,"has_fulltext":false,"cited_by_count":84,"citation_normalized_percentile":{"value":0.98939038,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"447","last_page":"456"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9958000183105469,"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/T11644","display_name":"Spam and Phishing Detection","score":0.989799976348877,"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":0.6740938425064087}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6740938425064087}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1367497.1367558","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1367497.1367558","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 17th international conference on World Wide Web","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W1489992655","https://openalex.org/W1513248649","https://openalex.org/W1660390307","https://openalex.org/W1775663022","https://openalex.org/W1803802947","https://openalex.org/W1973625941","https://openalex.org/W2023094000","https://openalex.org/W2034607275","https://openalex.org/W2049365470","https://openalex.org/W2066636486","https://openalex.org/W2085922539","https://openalex.org/W2105533042","https://openalex.org/W2112104357","https://openalex.org/W2113184419","https://openalex.org/W2116216325","https://openalex.org/W2129595335","https://openalex.org/W2132613313","https://openalex.org/W2140077965","https://openalex.org/W2145349611","https://openalex.org/W2151932833","https://openalex.org/W2152565070","https://openalex.org/W2159872134","https://openalex.org/W2162006472","https://openalex.org/W2168358004","https://openalex.org/W2170188121","https://openalex.org/W3145128584","https://openalex.org/W4241558715","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W2382290278","https://openalex.org/W2478288626","https://openalex.org/W4391913857","https://openalex.org/W2350741829","https://openalex.org/W2530322880"],"abstract_inverted_index":{"We":[0],"study":[1],"in":[2,16,198],"this":[3,90],"paper":[4],"the":[5,42,68,72,109,112,143,149,154,163,193,199,213,232],"Web":[6,18,25,34,43,58],"forum":[7,35,59,101,116,145,250],"crawling":[8,60,172],"problem,":[9],"which":[10,104,174,271],"is":[11,61,272],"a":[12,29,63,96,115,139,207,222,227,249,268],"very":[13],"fundamental":[14],"step":[15],"many":[17,81],"applications,":[19],"such":[20],"as":[21,78,80,153,242,267],"search":[22],"engine":[23],"and":[24,94,111,118,147,161,179,182,215,240,252,265,279],"data":[26,280],"mining.":[27,281],"As":[28],"typical":[30],"user-created":[31],"content":[32,110,151],"(UCC),":[33],"has":[36,105],"become":[37],"an":[38,99,170],"important":[39],"resource":[40],"on":[41,189],"due":[44,66],"to":[45,67,107,122,156,206],"its":[46],"rich":[47],"information":[48],"contributed":[49],"by":[50,85],"millions":[51],"of":[52,75,98,114,129,195,225,273],"Internet":[53],"users":[54],"every":[55],"day.":[56],"However,":[57],"not":[62],"trivial":[64],"problem":[65],"in-depth":[69],"link":[70],"structures,":[71],"large":[73],"amount":[74],"duplicate":[76,183,214],"pages,":[77],"well":[79],"invalid":[82,181,216],"pages":[83,141,160,178,229,247,261],"caused":[84],"login":[86],"failure":[87],"issues.":[88],"In":[89],"paper,":[91],"we":[92,134,168],"propose":[93],"build":[95],"prototype":[97],"intelligent":[100],"crawler,":[102,209],"iRobot,":[103],"intelligence":[106],"understand":[108],"structure":[113],"site,":[117,146],"then":[119],"decide":[120],"how":[121],"choose":[123],"traversal":[124],"paths":[125],"among":[126],"different":[127],"kinds":[128],"pages.":[130],"To":[131],"do":[132],"this,":[133],"first":[135],"randomly":[136],"sample":[137],"(download)":[138],"few":[140,228],"from":[142,248],"target":[144],"introduce":[148],"page":[150],"layout":[152],"characteristics":[155],"group":[157],"those":[158],"pre-sampled":[159],"re-construct":[162],"forum's":[164],"sitemap.":[165],"After":[166],"that,":[167],"select":[169],"optimal":[171],"path":[173],"only":[175,244],"traverses":[176],"informative":[177,246],"skips":[180],"ones.":[184],"The":[185],"extensive":[186],"experimental":[187],"results":[188],"several":[190],"forums":[191],"show":[192],"performance":[194],"our":[196],"system":[197],"following":[200],"aspects:":[201],"1)":[202],"Effectiveness":[203],"-":[204,220],"Compared":[205],"generic":[208],"iRobot":[210,235],"significantly":[211],"decreases":[212],"pages;":[217],"2)":[218],"Efficiency":[219],"With":[221],"small":[223],"cost":[224],"pre-sampling":[226],"for":[230,276],"learning":[231],"necessary":[233],"knowledge,":[234],"saves":[236],"substantial":[237],"network":[238],"bandwidth":[239],"storage":[241],"it":[243],"fetches":[245],"site;":[251],"3)":[253],"Long":[254],"threads":[255],"that":[256],"are":[257],"divided":[258],"into":[259],"multiple":[260],"can":[262],"be":[263],"re-concatenated":[264],"archived":[266],"whole":[269],"thread,":[270],"great":[274],"help":[275],"further":[277],"indexing":[278]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":7},{"year":2018,"cited_by_count":5},{"year":2017,"cited_by_count":5},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":7},{"year":2014,"cited_by_count":11},{"year":2013,"cited_by_count":9},{"year":2012,"cited_by_count":7}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2016-06-24T00:00:00"}