{"id":"https://openalex.org/W2100779529","doi":"https://doi.org/10.1145/1390334.1390413","title":"Exploring traversal strategy for web forum crawling","display_name":"Exploring traversal strategy for web forum crawling","publication_year":2008,"publication_date":"2008-07-20","ids":{"openalex":"https://openalex.org/W2100779529","doi":"https://doi.org/10.1145/1390334.1390413","mag":"2100779529"},"language":"en","primary_location":{"id":"doi:10.1145/1390334.1390413","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1390334.1390413","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st annual international ACM SIGIR conference on Research and development in information retrieval","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/A5101638215","display_name":"Yida Wang","orcid":"https://orcid.org/0000-0003-1350-485X"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yida Wang","raw_affiliation_strings":["CSSAR, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CSSAR, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366"]}]},{"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","Microsoft research Asia, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]},{"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","Microsoft research Asia, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]},{"raw_affiliation_string":"Microsoft research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","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","Microsoft research Asia, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]},{"raw_affiliation_string":"Microsoft research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","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","Microsoft research Asia, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]},{"raw_affiliation_string":"Microsoft research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103733614","display_name":"Wei\u2010Ying Ma","orcid":"https://orcid.org/0000-0002-7384-0735"},"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-Ying Ma","raw_affiliation_strings":["Microsoft Research Asia, Beijing, China","Microsoft research Asia, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]},{"raw_affiliation_string":"Microsoft research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":9.6327,"has_fulltext":false,"cited_by_count":38,"citation_normalized_percentile":{"value":0.97641694,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"459","last_page":"466"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":1.0,"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":1.0,"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":0.9940000176429749,"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":0.9848999977111816,"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/web-crawler","display_name":"Web crawler","score":0.906373143196106},{"id":"https://openalex.org/keywords/tree-traversal","display_name":"Tree traversal","score":0.894007682800293},{"id":"https://openalex.org/keywords/crawling","display_name":"Crawling","score":0.8235427141189575},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7819156646728516},{"id":"https://openalex.org/keywords/focused-crawler","display_name":"Focused crawler","score":0.7047901153564453},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.6999214291572571},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.546941876411438},{"id":"https://openalex.org/keywords/graph-traversal","display_name":"Graph traversal","score":0.4736579358577728},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.46678245067596436},{"id":"https://openalex.org/keywords/site-map","display_name":"Site map","score":0.4122757017612457},{"id":"https://openalex.org/keywords/static-web-page","display_name":"Static web page","score":0.27943044900894165},{"id":"https://openalex.org/keywords/web-navigation","display_name":"Web navigation","score":0.22287669777870178}],"concepts":[{"id":"https://openalex.org/C13743948","wikidata":"https://www.wikidata.org/wiki/Q45842","display_name":"Web crawler","level":2,"score":0.906373143196106},{"id":"https://openalex.org/C140745168","wikidata":"https://www.wikidata.org/wiki/Q1210082","display_name":"Tree traversal","level":2,"score":0.894007682800293},{"id":"https://openalex.org/C100368936","wikidata":"https://www.wikidata.org/wiki/Q1411725","display_name":"Crawling","level":2,"score":0.8235427141189575},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7819156646728516},{"id":"https://openalex.org/C73340581","wikidata":"https://www.wikidata.org/wiki/Q5463958","display_name":"Focused crawler","level":5,"score":0.7047901153564453},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.6999214291572571},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.546941876411438},{"id":"https://openalex.org/C96333769","wikidata":"https://www.wikidata.org/wiki/Q907955","display_name":"Graph traversal","level":3,"score":0.4736579358577728},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.46678245067596436},{"id":"https://openalex.org/C67617509","wikidata":"https://www.wikidata.org/wiki/Q1503327","display_name":"Site map","level":5,"score":0.4122757017612457},{"id":"https://openalex.org/C173576120","wikidata":"https://www.wikidata.org/wiki/Q2641220","display_name":"Static web page","level":4,"score":0.27943044900894165},{"id":"https://openalex.org/C61096286","wikidata":"https://www.wikidata.org/wiki/Q7978592","display_name":"Web navigation","level":3,"score":0.22287669777870178},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/1390334.1390413","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1390334.1390413","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st annual international ACM SIGIR conference on Research and development in information retrieval","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.186.7625","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.186.7625","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://research.microsoft.com/pubs/131117/forumcrawl_sigir08.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W1489992655","https://openalex.org/W2066636486","https://openalex.org/W2085922539","https://openalex.org/W2105803339","https://openalex.org/W2113184419","https://openalex.org/W2120136770","https://openalex.org/W2140077965","https://openalex.org/W2145349611","https://openalex.org/W2151932833","https://openalex.org/W2152565070","https://openalex.org/W2158601853","https://openalex.org/W2159872134","https://openalex.org/W2162502927","https://openalex.org/W2170188121"],"related_works":["https://openalex.org/W2375180657","https://openalex.org/W4385695127","https://openalex.org/W2026132847","https://openalex.org/W2137810919","https://openalex.org/W2358310581","https://openalex.org/W2352686120","https://openalex.org/W4248730791","https://openalex.org/W1506122440","https://openalex.org/W2364692302","https://openalex.org/W2371838993"],"abstract_inverted_index":{"In":[0,106],"this":[1,84],"paper,":[2,85],"we":[3,86],"study":[4],"the":[5,48,67,71,99,108,113,116,120,123,130,145,149,183],"problem":[6],"of":[7,20,41,101,112,115,122,179],"Web":[8,11,22,167],"forum":[9,12,25,43,77,188],"crawling.":[10],"has":[13],"now":[14],"become":[15],"an":[16,88,93],"important":[17],"data":[18,78],"source":[19],"many":[21,56],"applications;":[23],"while":[24],"crawling":[26,100],"is":[27,160],"still":[28],"a":[29,51,102,155,202],"challenging":[30],"task":[31],"due":[32],"to":[33,91,97,132,152],"complex":[34],"in-site":[35],"link":[36],"structures":[37],"and":[38,58,63,70,81,119,137,141,144,201],"login":[39],"controls":[40],"most":[42],"sites.":[44],"Without":[45],"carefully":[46],"selecting":[47],"traversal":[49,95,109,185],"path,":[50],"generic":[52,204],"crawler":[53,131,150,189],"usually":[54,161],"downloads":[55],"duplicate":[57,140],"invalid":[59],"pages":[60,136,165,194],"from":[61],"forums,":[62],"thus":[64],"wastes":[65],"both":[66],"precious":[68],"bandwidth":[69],"limited":[72],"storage":[73],"space.":[74],"To":[75],"crawl":[76,134],"more":[79,192],"effectively":[80],"efficiently,":[82],"in":[83,163,166,195],"propose":[87],"automatic":[89],"approach":[90],"exploring":[92],"appropriate":[94],"strategy":[96,110],"direct":[98],"given":[103],"target":[104],"forum.":[105],"detail,":[107],"consists":[111],"identification":[114],"skeleton":[117,127],"links":[118,128,147],"detection":[121],"page-flipping":[124,146],"links.":[125],"The":[126,169],"instruct":[129],"only":[133],"valuable":[135],"meanwhile":[138],"avoid":[139],"uninformative":[142],"ones;":[143],"tell":[148],"how":[151],"completely":[153],"download":[154],"long":[156],"discussion":[157],"thread":[158],"which":[159],"shown":[162],"multiple":[164],"forums.":[168],"extensive":[170],"experimental":[171],"results":[172],"on":[173],"several":[174],"forums":[175],"show":[176],"encouraging":[177],"performance":[178],"our":[180,187],"approach.":[181],"Following":[182],"discovered":[184],"strategy,":[186],"can":[190],"archive":[191],"informative":[193],"comparison":[196],"with":[197],"previous":[198],"related":[199],"work":[200],"commercial":[203],"crawler.":[205]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":1},{"year":2014,"cited_by_count":5},{"year":2013,"cited_by_count":5},{"year":2012,"cited_by_count":6}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
