{"id":"https://openalex.org/W2110780226","doi":"https://doi.org/10.1145/1031453.1031458","title":"Probabilistic models for focused web crawling","display_name":"Probabilistic models for focused web crawling","publication_year":2004,"publication_date":"2004-11-12","ids":{"openalex":"https://openalex.org/W2110780226","doi":"https://doi.org/10.1145/1031453.1031458","mag":"2110780226"},"language":"en","primary_location":{"id":"doi:10.1145/1031453.1031458","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1031453.1031458","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 6th annual ACM international workshop on Web information and data management","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://nrc-publications.canada.ca/eng/view/accepted/?id=de588722-d68b-46b3-9151-3bc91c28bc8f","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100773328","display_name":"Hongyu Liu","orcid":"https://orcid.org/0000-0002-4628-6388"},"institutions":[{"id":"https://openalex.org/I129902397","display_name":"Dalhousie University","ror":"https://ror.org/01e6qks80","country_code":"CA","type":"education","lineage":["https://openalex.org/I129902397"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Hongyu Liu","raw_affiliation_strings":["Dalhousie University","Dalhousie University#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dalhousie University","institution_ids":["https://openalex.org/I129902397"]},{"raw_affiliation_string":"Dalhousie University#TAB#","institution_ids":["https://openalex.org/I129902397"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013989913","display_name":"Evangelos Milios","orcid":"https://orcid.org/0000-0001-5549-4675"},"institutions":[{"id":"https://openalex.org/I129902397","display_name":"Dalhousie University","ror":"https://ror.org/01e6qks80","country_code":"CA","type":"education","lineage":["https://openalex.org/I129902397"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Evangelos Milios","raw_affiliation_strings":["Dalhousie University","Dalhousie University#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dalhousie University","institution_ids":["https://openalex.org/I129902397"]},{"raw_affiliation_string":"Dalhousie University#TAB#","institution_ids":["https://openalex.org/I129902397"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5067447908","display_name":"Jeannette Janssen","orcid":"https://orcid.org/0000-0002-0322-7855"},"institutions":[{"id":"https://openalex.org/I129902397","display_name":"Dalhousie University","ror":"https://ror.org/01e6qks80","country_code":"CA","type":"education","lineage":["https://openalex.org/I129902397"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Jeannette Janssen","raw_affiliation_strings":["Dalhousie University","Dalhousie University#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dalhousie University","institution_ids":["https://openalex.org/I129902397"]},{"raw_affiliation_string":"Dalhousie University#TAB#","institution_ids":["https://openalex.org/I129902397"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":5.6537,"has_fulltext":true,"cited_by_count":36,"citation_normalized_percentile":{"value":0.95651236,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"16","last_page":"22"},"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/T10260","display_name":"Software Engineering Research","score":0.9921000003814697,"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/T10028","display_name":"Topic Modeling","score":0.9708999991416931,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/crfs","display_name":"CRFS","score":0.9526596069335938},{"id":"https://openalex.org/keywords/crawling","display_name":"Crawling","score":0.9111104011535645},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8029888868331909},{"id":"https://openalex.org/keywords/conditional-random-field","display_name":"Conditional random field","score":0.7979741096496582},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.7653560638427734},{"id":"https://openalex.org/keywords/web-crawler","display_name":"Web crawler","score":0.7545038461685181},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.5714576244354248},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5702638030052185},{"id":"https://openalex.org/keywords/relevance","display_name":"Relevance (law)","score":0.5314468741416931},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43897566199302673},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.42648348212242126},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.39730799198150635},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3758935034275055},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.36266472935676575},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.29852890968322754}],"concepts":[{"id":"https://openalex.org/C2775953691","wikidata":"https://www.wikidata.org/wiki/Q5013874","display_name":"CRFS","level":3,"score":0.9526596069335938},{"id":"https://openalex.org/C100368936","wikidata":"https://www.wikidata.org/wiki/Q1411725","display_name":"Crawling","level":2,"score":0.9111104011535645},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8029888868331909},{"id":"https://openalex.org/C152565575","wikidata":"https://www.wikidata.org/wiki/Q1124538","display_name":"Conditional random field","level":2,"score":0.7979741096496582},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.7653560638427734},{"id":"https://openalex.org/C13743948","wikidata":"https://www.wikidata.org/wiki/Q45842","display_name":"Web crawler","level":2,"score":0.7545038461685181},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.5714576244354248},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5702638030052185},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.5314468741416931},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43897566199302673},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.42648348212242126},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.39730799198150635},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3758935034275055},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.36266472935676575},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.29852890968322754},{"id":"https://openalex.org/C105702510","wikidata":"https://www.wikidata.org/wiki/Q514","display_name":"Anatomy","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","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/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/1031453.1031458","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1031453.1031458","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 6th annual ACM international workshop on Web information and data management","raw_type":"proceedings-article"},{"id":"pmh:oai:cisti-icist.nrc-cnrc.ca:cistinparc:16352297","is_oa":true,"landing_page_url":"https://nrc-publications.canada.ca/eng/view/object/?id=de588722-d68b-46b3-9151-3bc91c28bc8f","pdf_url":"https://nrc-publications.canada.ca/eng/view/accepted/?id=de588722-d68b-46b3-9151-3bc91c28bc8f","source":{"id":"https://openalex.org/S7407055245","display_name":"NPARC","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:cisti-icist.nrc-cnrc.ca:cistinparc:16352297","is_oa":true,"landing_page_url":"https://nrc-publications.canada.ca/eng/view/object/?id=de588722-d68b-46b3-9151-3bc91c28bc8f","pdf_url":"https://nrc-publications.canada.ca/eng/view/accepted/?id=de588722-d68b-46b3-9151-3bc91c28bc8f","source":{"id":"https://openalex.org/S7407055245","display_name":"NPARC","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320322675","display_name":"Mitacs","ror":"https://ror.org/00cjrc276"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2110780226.pdf","grobid_xml":"https://content.openalex.org/works/W2110780226.grobid-xml"},"referenced_works_count":52,"referenced_works":["https://openalex.org/W140650756","https://openalex.org/W189514790","https://openalex.org/W1481372933","https://openalex.org/W1485536830","https://openalex.org/W1489992655","https://openalex.org/W1534730506","https://openalex.org/W1539978309","https://openalex.org/W1542491098","https://openalex.org/W1592796124","https://openalex.org/W1597069795","https://openalex.org/W1631403443","https://openalex.org/W1674850363","https://openalex.org/W1679844312","https://openalex.org/W1934019294","https://openalex.org/W1981802602","https://openalex.org/W1987777228","https://openalex.org/W2001832505","https://openalex.org/W2005579877","https://openalex.org/W2007687650","https://openalex.org/W2012516036","https://openalex.org/W2014134732","https://openalex.org/W2017224880","https://openalex.org/W2017726337","https://openalex.org/W2034797903","https://openalex.org/W2045998703","https://openalex.org/W2100815879","https://openalex.org/W2102667697","https://openalex.org/W2102942431","https://openalex.org/W2116224704","https://openalex.org/W2121294789","https://openalex.org/W2124168655","https://openalex.org/W2124673015","https://openalex.org/W2125838338","https://openalex.org/W2139193890","https://openalex.org/W2141825421","https://openalex.org/W2145102654","https://openalex.org/W2147152072","https://openalex.org/W2147880316","https://openalex.org/W2151007976","https://openalex.org/W2151910393","https://openalex.org/W2156515921","https://openalex.org/W2156963321","https://openalex.org/W2157171712","https://openalex.org/W2158188757","https://openalex.org/W2160842254","https://openalex.org/W2162502927","https://openalex.org/W2769133055","https://openalex.org/W3140968660","https://openalex.org/W6653708959","https://openalex.org/W6678406706","https://openalex.org/W6678701036","https://openalex.org/W7048060829"],"related_works":["https://openalex.org/W50079190","https://openalex.org/W2356597680","https://openalex.org/W182104056","https://openalex.org/W2111726165","https://openalex.org/W2011251309","https://openalex.org/W3108423214","https://openalex.org/W2796133761","https://openalex.org/W3088215229","https://openalex.org/W2511246383","https://openalex.org/W4385695127"],"abstract_inverted_index":{"A":[0],"Focused":[1],"crawler":[2],"must":[3],"use":[4,60,90],"information":[5],"gleaned":[6],"from":[7],"previously":[8],"crawled":[9],"page":[10],"sequences":[11],"to":[12,81],"estimate":[13],"the":[14,33,59,76,83,89],"relevance":[15],"of":[16,28,61,78,91,102],"a":[17,100,103],"newly":[18],"seen":[19],"URL.":[20],"Therefore,":[21],"good":[22],"performance":[23],"depends":[24],"on":[25],"powerful":[26],"modelling":[27],"context":[29],"as":[30,32,39],"well":[31],"current":[34],"observations.":[35],"Probabilistic":[36],"models,":[37],"such":[38],"Hidden":[40],"Markov":[41],"Models(HMMs)":[42],"and":[43,52,67,87,94],"Conditional":[44],"Random":[45],"Fields(CRFs),":[46],"can":[47],"potentially":[48],"capture":[49],"both":[50],"formatting":[51],"context.":[53],"In":[54],"this":[55],"paper,":[56],"we":[57,74,98],"present":[58],"HMM":[62],"for":[63,107],"focused":[64,108],"web":[65,109],"crawling,":[66,110],"compare":[68],"it":[69],"with":[70,85],"Best-First":[71],"strategy.":[72],"Furthermore,":[73],"discuss":[75],"concept":[77],"using":[79],"CRFs":[80,106],"overcome":[82],"difficulties":[84],"HMMs":[86],"support":[88],"many,":[92],"arbitrary":[93],"overlapping":[95],"features.":[96],"Finally,":[97],"describe":[99],"design":[101],"system":[104],"applying":[105],"that":[111],"is":[112],"currently":[113],"being":[114],"implemented.":[115]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":7}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
