{"id":"https://openalex.org/W2102121847","doi":"https://doi.org/10.1145/2063576.2063593","title":"User browsing behavior-driven web crawling","display_name":"User browsing behavior-driven web crawling","publication_year":2011,"publication_date":"2011-10-24","ids":{"openalex":"https://openalex.org/W2102121847","doi":"https://doi.org/10.1145/2063576.2063593","mag":"2102121847"},"language":"en","primary_location":{"id":"doi:10.1145/2063576.2063593","doi":"https://doi.org/10.1145/2063576.2063593","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2063576.2063593","pdf_url":null,"source":{"id":"https://openalex.org/S4393918199","display_name":"ACM International Conference on Information and Knowledge Management (CIKM)","issn_l":"2155-0751","issn":["2155-0751"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 20th ACM international conference on Information and knowledge management","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"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/A5064521695","display_name":"Minghai Liu","orcid":"https://orcid.org/0000-0001-9209-745X","observed_orcids":["https://orcid.org/0000-0001-9209-745X"]},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Minghai Liu","raw_affiliation_strings":["School of EECS, Peking University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of EECS, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069272117","display_name":"Rui Cai","orcid":"https://orcid.org/0000-0002-6499-2091","observed_orcids":["https://orcid.org/0000-0002-6499-2091","https://orcid.org/0009-0000-9803-9250"]},"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/A5100642537","display_name":"Ming Zhang","orcid":"https://orcid.org/0000-0002-9809-3430","observed_orcids":["https://orcid.org/0000-0002-9809-3430"]},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ming Zhang","raw_affiliation_strings":["School of EECS, Peking University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of EECS, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100433855","display_name":"Lei Zhang","orcid":"https://orcid.org/0000-0001-9343-3654","observed_orcids":["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":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.6676,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":{"value":0.83625632,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"87","last_page":"92"},"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/T10286","display_name":"Information Retrieval and Search Behavior","score":0.00019999999494757503,"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/T13976","display_name":"Web visibility and informetrics","score":0.0,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/web-crawling","display_name":"web crawling","score":0.9879999756813049},{"id":"https://openalex.org/keywords/user-browsing-behavior","display_name":"user browsing behavior","score":0.843999981880188},{"id":"https://openalex.org/keywords/user-interests","display_name":"user interests","score":0.46700000762939453},{"id":"https://openalex.org/keywords/link-structure","display_name":"link structure","score":0.6449999809265137}],"concepts":[{"id":"https://openalex.org/C100368936","wikidata":"https://www.wikidata.org/wiki/Q1411725","display_name":"Crawling","level":2,"score":0.9311758279800415},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8324536085128784},{"id":"https://openalex.org/C13743948","wikidata":"https://www.wikidata.org/wiki/Q45842","display_name":"Web crawler","level":2,"score":0.7274436950683594},{"id":"https://openalex.org/C2779172887","wikidata":"https://www.wikidata.org/wiki/Q184316","display_name":"PageRank","level":2,"score":0.7141388654708862},{"id":"https://openalex.org/C197046077","wikidata":"https://www.wikidata.org/wiki/Q785337","display_name":"Web mining","level":3,"score":0.5913621187210083},{"id":"https://openalex.org/C177774035","wikidata":"https://www.wikidata.org/wiki/Q1246948","display_name":"Granularity","level":2,"score":0.5741986632347107},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.5688801407814026},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.530865490436554},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5252986550331116},{"id":"https://openalex.org/C1173588","wikidata":"https://www.wikidata.org/wiki/Q6554294","display_name":"Link analysis","level":2,"score":0.44489988684654236},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.40513497591018677},{"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/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/2063576.2063593","doi":"https://doi.org/10.1145/2063576.2063593","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2063576.2063593","pdf_url":null,"source":{"id":"https://openalex.org/S4393918199","display_name":"ACM International Conference on Information and Knowledge Management (CIKM)","issn_l":"2155-0751","issn":["2155-0751"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 20th ACM international conference on Information and knowledge management","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.357.5844","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.357.5844","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/155618/CIKM2011_WebCrawl.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W14315322","https://openalex.org/W110443600","https://openalex.org/W1489992655","https://openalex.org/W1585280831","https://openalex.org/W1854214752","https://openalex.org/W1968908999","https://openalex.org/W2017224880","https://openalex.org/W2029341294","https://openalex.org/W2066636486","https://openalex.org/W2100779529","https://openalex.org/W2103545802","https://openalex.org/W2105803339","https://openalex.org/W2113184419","https://openalex.org/W2128384372","https://openalex.org/W2138621811","https://openalex.org/W2140018945","https://openalex.org/W2140077965","https://openalex.org/W2151007976","https://openalex.org/W2151932833","https://openalex.org/W2158601853","https://openalex.org/W2327714094","https://openalex.org/W2911388033","https://openalex.org/W4253654031"],"related_works":["https://openalex.org/W2029341294","https://openalex.org/W2016345114","https://openalex.org/W2028371599","https://openalex.org/W81688156","https://openalex.org/W2126586599","https://openalex.org/W2026632779","https://openalex.org/W1577496147","https://openalex.org/W1979144454","https://openalex.org/W2120703707","https://openalex.org/W2102252097"],"abstract_inverted_index":{"To":[0],"optimize":[1],"the":[2,38,72,76,82,98,109],"performance":[3],"of":[4,84,100,111],"web":[5,56],"crawlers,":[6],"various":[7],"page":[8,47],"importance":[9,48,99],"measures":[10,23],"have":[11],"been":[12],"studied":[13],"to":[14,45,95],"select":[15],"and":[16,26,43,53,75],"order":[17],"URLs":[18],"in":[19,68],"crawling.":[20],"Most":[21],"sophisticated":[22],"(e.g.":[24],"breadth-first":[25],"PageRank)":[27],"are":[28,79,93],"based":[29],"on":[30,65],"link":[31],"structure.":[32],"In":[33],"this":[34,69],"paper,":[35,70],"we":[36],"treat":[37],"problem":[39],"from":[40,55],"another":[41],"perspective":[42],"propose":[44],"measure":[46],"through":[49],"mining":[50,74],"user":[51],"interest":[52],"behaviors":[54],"browse":[57],"logs.":[58],"Unlike":[59],"most":[60],"existing":[61],"approaches":[62],"which":[63],"work":[64],"single":[66],"URL,":[67],"both":[71],"log":[73],"crawl":[77,91],"ordering":[78],"performed":[80],"at":[81],"granularity":[83],"URL":[85,89],"pattern.":[86],"The":[87],"proposed":[88],"pattern-based":[90],"orderings":[92],"capable":[94],"properly":[96],"predict":[97],"newly":[101],"created":[102],"(unseen)":[103],"URLs.":[104],"Promising":[105],"experimental":[106],"results":[107],"proved":[108],"feasibility":[110],"our":[112],"approach.":[113]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2018,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":4},{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":1}],"updated_date":"2026-11-12T12:28:57.059296","created_date":"2016-06-24T00:00:00"}
