{"id":"https://openalex.org/W2133433261","doi":"https://doi.org/10.1145/1526709.1526870","title":"Graph based crawler seed selection","display_name":"Graph based crawler seed selection","publication_year":2009,"publication_date":"2009-04-20","ids":{"openalex":"https://openalex.org/W2133433261","doi":"https://doi.org/10.1145/1526709.1526870","mag":"2133433261"},"language":"en","primary_location":{"id":"doi:10.1145/1526709.1526870","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1526709.1526870","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 18th international conference on World wide web","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/A5078436441","display_name":"Shuyi Zheng","orcid":null},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Shuyi Zheng","raw_affiliation_strings":["Pennsylvania State University, University Park, PA, USA"],"affiliations":[{"raw_affiliation_string":"Pennsylvania State University, University Park, PA, USA","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020697231","display_name":"Pavel Dmitriev","orcid":"https://orcid.org/0000-0001-5740-5146"},"institutions":[{"id":"https://openalex.org/I4210134091","display_name":"Yahoo (United States)","ror":"https://ror.org/040dkzz12","country_code":"US","type":"company","lineage":["https://openalex.org/I4210134091"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Pavel Dmitriev","raw_affiliation_strings":["Yahoo! Labs, Santa Clara, CA, USA","Yahoo! Labs., Santa Clara, CA, USA#TAB#"],"affiliations":[{"raw_affiliation_string":"Yahoo! Labs, Santa Clara, CA, USA","institution_ids":["https://openalex.org/I4210134091"]},{"raw_affiliation_string":"Yahoo! Labs., Santa Clara, CA, USA#TAB#","institution_ids":["https://openalex.org/I4210134091"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001294898","display_name":"C. Lee Giles","orcid":"https://orcid.org/0000-0002-1931-585X"},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"C. Lee Giles","raw_affiliation_strings":["Pennsylvania State University, University Park, PA, USA"],"affiliations":[{"raw_affiliation_string":"Pennsylvania State University, University Park, PA, USA","institution_ids":["https://openalex.org/I130769515"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5078436441"],"corresponding_institution_ids":["https://openalex.org/I130769515"],"apc_list":null,"apc_paid":null,"fwci":2.9612,"has_fulltext":false,"cited_by_count":17,"citation_normalized_percentile":{"value":0.93217607,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1089","last_page":"1090"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9991999864578247,"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":0.9991999864578247,"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/T11106","display_name":"Data Management and Algorithms","score":0.9952999949455261,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T10743","display_name":"Software Testing and Debugging Techniques","score":0.9871000051498413,"subfield":{"id":"https://openalex.org/subfields/1712","display_name":"Software"},"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":0.8051483631134033},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.699820876121521},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.4990243911743164},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.41895341873168945},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3838540017604828},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.1956290304660797},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.15622225403785706}],"concepts":[{"id":"https://openalex.org/C13743948","wikidata":"https://www.wikidata.org/wiki/Q45842","display_name":"Web crawler","level":2,"score":0.8051483631134033},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.699820876121521},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.4990243911743164},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.41895341873168945},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3838540017604828},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.1956290304660797},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.15622225403785706}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1526709.1526870","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1526709.1526870","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 18th international conference on World wide web","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":3,"referenced_works":["https://openalex.org/W1503924817","https://openalex.org/W1974757757","https://openalex.org/W3152156937"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W3005260231","https://openalex.org/W2904469652","https://openalex.org/W4362647146","https://openalex.org/W2383572231","https://openalex.org/W2042034567","https://openalex.org/W3179424333","https://openalex.org/W2782340266","https://openalex.org/W4230722125","https://openalex.org/W2149158941"],"abstract_inverted_index":{"This":[0],"paper":[1],"identifies":[2],"and":[3,40,49],"explores":[4],"the":[5,32,55,58,62],"problem":[6],"of":[7,34,57,61,71],"seed":[8,17,67],"selection":[9,18,68],"in":[10,43],"a":[11,21,36,44],"web-scale":[12],"crawler.":[13],"We":[14],"argue":[15],"that":[16],"is":[19,74],"not":[20],"trivial":[22],"but":[23],"very":[24],"important":[25],"problem.":[26],"Selecting":[27],"proper":[28],"seeds":[29],"can":[30,41],"increase":[31],"number":[33],"pages":[35],"crawler":[37],"will":[38],"discover,":[39],"result":[42],"collection":[45],"with":[46],"more":[47],"``good\"":[48],"less":[50],"\"bad\"":[51],"pages.":[52],"Based":[53],"on":[54,80],"analysis":[56],"graph":[59],"structure":[60],"web,":[63],"we":[64],"propose":[65],"several":[66],"algorithms.":[69],"Effectiveness":[70],"these":[72],"algorithms":[73],"proved":[75],"by":[76],"our":[77],"experimental":[78],"results":[79],"real":[81],"web":[82],"data.":[83]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":1},{"year":2014,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
