{"id":"https://openalex.org/W2102015549","doi":"https://doi.org/10.1109/cmpsac.2003.1245354","title":"A probabilistic model for intelligent Web crawlers","display_name":"A probabilistic model for intelligent Web crawlers","publication_year":2004,"publication_date":"2004-03-01","ids":{"openalex":"https://openalex.org/W2102015549","doi":"https://doi.org/10.1109/cmpsac.2003.1245354","mag":"2102015549"},"language":"en","primary_location":{"id":"doi:10.1109/cmpsac.2003.1245354","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cmpsac.2003.1245354","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings 27th Annual International Computer Software and Applications Conference. COMPAC 2003","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/A5110831232","display_name":"Hu Ke","orcid":"https://orcid.org/0009-0006-7274-6786"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Ke Hu","raw_affiliation_strings":["Department of Information Engineering, Chinese University of Hong Kong, New Territories, Hong Kong, China","[Dept. of Inf. Eng., Chinese Univ. of Hong Kong, Shatin, China]"],"affiliations":[{"raw_affiliation_string":"Department of Information Engineering, Chinese University of Hong Kong, New Territories, Hong Kong, China","institution_ids":["https://openalex.org/I177725633"]},{"raw_affiliation_string":"[Dept. of Inf. Eng., Chinese Univ. of Hong Kong, Shatin, China]","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5039173605","display_name":"Wing Shing Wong","orcid":"https://orcid.org/0000-0001-6357-0981"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wing Shing Wong","raw_affiliation_strings":["Department of Information Engineering, Chinese University of Hong Kong, New Territories, Hong Kong, China","[Dept. of Inf. Eng., Chinese Univ. of Hong Kong, Shatin, China]"],"affiliations":[{"raw_affiliation_string":"Department of Information Engineering, Chinese University of Hong Kong, New Territories, Hong Kong, China","institution_ids":["https://openalex.org/I177725633"]},{"raw_affiliation_string":"[Dept. of Inf. Eng., Chinese Univ. of Hong Kong, Shatin, China]","institution_ids":["https://openalex.org/I177725633"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5110831232"],"corresponding_institution_ids":["https://openalex.org/I177725633"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.13410121,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"278","last_page":"282"},"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":0.9858999848365784,"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":0.979200005531311,"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":0.9720129370689392},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7617547512054443},{"id":"https://openalex.org/keywords/focused-crawler","display_name":"Focused crawler","score":0.6689108610153198},{"id":"https://openalex.org/keywords/crawling","display_name":"Crawling","score":0.6597336530685425},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.6310399770736694},{"id":"https://openalex.org/keywords/web-search-engine","display_name":"Web search engine","score":0.5647903680801392},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5508848428726196},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.5478139519691467},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.4681701064109802},{"id":"https://openalex.org/keywords/web-navigation","display_name":"Web navigation","score":0.2976130545139313},{"id":"https://openalex.org/keywords/static-web-page","display_name":"Static web page","score":0.26048773527145386},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.15025004744529724}],"concepts":[{"id":"https://openalex.org/C13743948","wikidata":"https://www.wikidata.org/wiki/Q45842","display_name":"Web crawler","level":2,"score":0.9720129370689392},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7617547512054443},{"id":"https://openalex.org/C73340581","wikidata":"https://www.wikidata.org/wiki/Q5463958","display_name":"Focused crawler","level":5,"score":0.6689108610153198},{"id":"https://openalex.org/C100368936","wikidata":"https://www.wikidata.org/wiki/Q1411725","display_name":"Crawling","level":2,"score":0.6597336530685425},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.6310399770736694},{"id":"https://openalex.org/C521815418","wikidata":"https://www.wikidata.org/wiki/Q4182287","display_name":"Web search engine","level":4,"score":0.5647903680801392},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5508848428726196},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.5478139519691467},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.4681701064109802},{"id":"https://openalex.org/C61096286","wikidata":"https://www.wikidata.org/wiki/Q7978592","display_name":"Web navigation","level":3,"score":0.2976130545139313},{"id":"https://openalex.org/C173576120","wikidata":"https://www.wikidata.org/wiki/Q2641220","display_name":"Static web page","level":4,"score":0.26048773527145386},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.15025004744529724},{"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":1,"locations":[{"id":"doi:10.1109/cmpsac.2003.1245354","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cmpsac.2003.1245354","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings 27th Annual International Computer Software and Applications Conference. COMPAC 2003","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8199999928474426,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W1489992655","https://openalex.org/W1674850363","https://openalex.org/W1976969221","https://openalex.org/W2005579877","https://openalex.org/W2007687650","https://openalex.org/W2018928332","https://openalex.org/W2066636486","https://openalex.org/W2125473504","https://openalex.org/W2997134027"],"related_works":["https://openalex.org/W2375180657","https://openalex.org/W4248730791","https://openalex.org/W2026132847","https://openalex.org/W1506122440","https://openalex.org/W4385695127","https://openalex.org/W2095543197","https://openalex.org/W2113184419","https://openalex.org/W2371838993","https://openalex.org/W1999548128","https://openalex.org/W4254300012"],"abstract_inverted_index":{"With":[0,116],"the":[1,5,12,41,44,53,67,85,107,117],"enormous":[2],"growth":[3],"of":[4,14,43,106,114],"World":[6],"Wide":[7],"Web":[8,18,27,55,86,108],"in":[9,47],"recent":[10],"years,":[11],"issue":[13],"how":[15],"to":[16,39,51,58,89,100,131],"discover":[17],"pages":[19,56],"efficiently":[20],"has":[21],"become":[22],"an":[23,110,123],"important":[24],"challenge":[25],"for":[26],"crawler":[28,68,121,125],"designers.":[29],"In":[30],"this":[31,64],"paper,":[32],"we":[33],"will":[34],"outline":[35],"a":[36,48,59,82,102,133],"simple":[37],"model":[38,101],"predict":[40],"distribution":[42,92],"search":[45,50],"depth":[46],"breadth-first":[49],"reach":[52],"first":[54],"relevant":[57],"user":[60],"query.":[61],"We":[62],"define":[63],"probability":[65],"as":[66],"confidence.":[69],"Recent":[70],"studies":[71],"by":[72,120],"Y.":[73],"Deshpande":[74],"and":[75],"S.":[76],"Hansen":[77],"(2001)":[78],"indicate":[79],"that":[80],"at":[81],"large":[83],"scale":[84],"structure":[87,105],"subscribes":[88],"power":[90],"law":[91],"on":[93],"several":[94],"aspects.":[95],"However,":[96],"our":[97],"work":[98],"tries":[99],"microscopic":[103],"linkage":[104],"from":[109],"intelligent":[111,124],"crawler's":[112],"point":[113],"view.":[115],"information":[118],"provided":[119],"confidence,":[122],"can":[126],"adjust":[127],"its":[128],"crawling":[129],"behavior":[130],"achieve":[132],"higher":[134],"harvest":[135],"rate.":[136]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}