{"id":"https://openalex.org/W1999740339","doi":"https://doi.org/10.1145/2187980.2187985","title":"FoCUS","display_name":"FoCUS","publication_year":2012,"publication_date":"2012-04-16","ids":{"openalex":"https://openalex.org/W1999740339","doi":"https://doi.org/10.1145/2187980.2187985","mag":"1999740339"},"language":"en","primary_location":{"id":"doi:10.1145/2187980.2187985","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2187980.2187985","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 21st International Conference on World Wide Web","raw_type":"proceedings-article"},"type":"conference-paper","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/A5040999303","display_name":"Jingtian Jiang","orcid":null},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingtian Jiang","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China",", University of Science and Technology of China, Hefei, China#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":", University of Science and Technology of China, Hefei, China#TAB#","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064573190","display_name":"Nenghai Yu","orcid":"https://orcid.org/0000-0003-4417-9316"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Nenghai Yu","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China",", University of Science and Technology of China, Hefei, China#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":", University of Science and Technology of China, Hefei, China#TAB#","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5090151187","display_name":"Chin-Yew Lin","orcid":"https://orcid.org/0000-0002-0798-6365"},"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":"Chin-Yew Lin","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":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"33","last_page":"42"},"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/T11644","display_name":"Spam and Phishing Detection","score":0.9962999820709229,"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/T12479","display_name":"Web Application Security Vulnerabilities","score":0.9858999848365784,"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":0.8275552988052368},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7701934576034546},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.652259111404419},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.6468733549118042},{"id":"https://openalex.org/keywords/crawling","display_name":"Crawling","score":0.6084252595901489},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.569880485534668},{"id":"https://openalex.org/keywords/thread","display_name":"Thread (computing)","score":0.5301467180252075},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5191187858581543},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5031532645225525},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.4686174988746643},{"id":"https://openalex.org/keywords/test-set","display_name":"Test set","score":0.42507049441337585},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.31377655267715454}],"concepts":[{"id":"https://openalex.org/C13743948","wikidata":"https://www.wikidata.org/wiki/Q45842","display_name":"Web crawler","level":2,"score":0.8275552988052368},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7701934576034546},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.652259111404419},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.6468733549118042},{"id":"https://openalex.org/C100368936","wikidata":"https://www.wikidata.org/wiki/Q1411725","display_name":"Crawling","level":2,"score":0.6084252595901489},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.569880485534668},{"id":"https://openalex.org/C138101251","wikidata":"https://www.wikidata.org/wiki/Q213092","display_name":"Thread (computing)","level":2,"score":0.5301467180252075},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5191187858581543},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5031532645225525},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.4686174988746643},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.42507049441337585},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.31377655267715454},{"id":"https://openalex.org/C105702510","wikidata":"https://www.wikidata.org/wiki/Q514","display_name":"Anatomy","level":1,"score":0.0},{"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","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":1,"locations":[{"id":"doi:10.1145/2187980.2187985","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2187980.2187985","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 21st 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":20,"referenced_works":["https://openalex.org/W1986968077","https://openalex.org/W2066636486","https://openalex.org/W2083563309","https://openalex.org/W2085922539","https://openalex.org/W2100779529","https://openalex.org/W2105803339","https://openalex.org/W2112104357","https://openalex.org/W2116216325","https://openalex.org/W2132613313","https://openalex.org/W2134491992","https://openalex.org/W2140077965","https://openalex.org/W2145349611","https://openalex.org/W2154445423","https://openalex.org/W2156909104","https://openalex.org/W2159869159","https://openalex.org/W2159872134","https://openalex.org/W2168358004","https://openalex.org/W2385656172","https://openalex.org/W3149154678","https://openalex.org/W4241558715"],"related_works":["https://openalex.org/W2161927007","https://openalex.org/W3044444100","https://openalex.org/W3216588747","https://openalex.org/W2186888085","https://openalex.org/W2051135816","https://openalex.org/W2685618609","https://openalex.org/W2548298479","https://openalex.org/W2148812475","https://openalex.org/W4300913644","https://openalex.org/W3215669057"],"abstract_inverted_index":{"In":[0],"this":[1,82],"paper,":[2],"we":[3,84],"present":[4],"FoCUS":[5,18,154],"(Forum":[6],"Crawler":[7],"Under":[8],"Supervision),":[9],"a":[10,92,143,163],"supervised":[11],"web-scale":[12],"forum":[13,24,42,56,88,174],"crawler.":[14],"The":[15],"goal":[16],"of":[17,41,108,146,166],"is":[19,38],"to":[20,71,77,91,100,142],"only":[21],"trawl":[22],"relevant":[23],"content":[25,36],"from":[26,74,112,121,133],"the":[27,39,86],"web":[28,87],"with":[29],"minimal":[30],"overhead.":[31],"Forum":[32],"threads":[33],"contain":[34],"information":[35],"that":[37,153],"target":[40],"crawlers.":[43],"Although":[44],"forums":[45,139,168],"have":[46,61],"different":[47,55,173],"layouts":[48],"or":[49],"styles":[50],"and":[51,97,103,140,159],"are":[52],"powered":[53,169],"by":[54,67,170],"software":[57,175],"packages,":[58],"they":[59],"always":[60],"similar":[62],"implicit":[63,109],"navigation":[64,110],"paths":[65,111],"connected":[66],"specific":[68],"URL":[69,93],"types":[70],"lead":[72],"users":[73],"entry":[75],"pages":[76],"thread":[78],"pages.":[79],"Based":[80],"on":[81,162],"observation,":[83],"reduce":[85],"crawling":[89],"problem":[90,96],"type":[94,124,128],"recognition":[95],"show":[98,152],"how":[99],"learn":[101],"accurate":[102],"effective":[104],"regular":[105],"expression":[106],"patterns":[107],"an":[113],"automatically":[114],"created":[115],"training":[116],"set":[117,145,165],"using":[118],"aggregated":[119],"results":[120,151],"weak":[122],"page":[123,127],"classifiers.":[125],"Robust":[126],"classifiers":[129],"can":[130],"be":[131],"trained":[132],"as":[134,136],"few":[135],"5":[137],"annotated":[138],"applied":[141],"large":[144,164],"unseen":[147],"forums.":[148],"Our":[149],"test":[150,167],"achieved":[155],"over":[156,171],"98%":[157],"effectiveness":[158],"97%":[160],"coverage":[161],"150":[172],"packages.":[176]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":4},{"year":2013,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2016-06-24T00:00:00"}