{"id":"https://openalex.org/W2148406518","doi":"https://doi.org/10.1145/1135777.1136005","title":"Effective web-scale crawling through website analysis","display_name":"Effective web-scale crawling through website analysis","publication_year":2006,"publication_date":"2006-05-23","ids":{"openalex":"https://openalex.org/W2148406518","doi":"https://doi.org/10.1145/1135777.1136005","mag":"2148406518"},"language":"en","primary_location":{"id":"doi:10.1145/1135777.1136005","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1135777.1136005","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 15th 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/A5019004319","display_name":"Iv\u00e1n Gonzlez","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Iv\u00e1n Gonzlez","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, PA"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, PA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112355043","display_name":"Adam Marcus","orcid":"https://orcid.org/0000-0002-1428-2307"},"institutions":[{"id":"https://openalex.org/I165799507","display_name":"Rensselaer Polytechnic Institute","ror":"https://ror.org/01rtyzb94","country_code":"US","type":"education","lineage":["https://openalex.org/I165799507"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Adam Marcus","raw_affiliation_strings":["Rensselaer Polytechnic Institute, Troy, NY"],"affiliations":[{"raw_affiliation_string":"Rensselaer Polytechnic Institute, Troy, NY","institution_ids":["https://openalex.org/I165799507"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073557621","display_name":"Daniel N. Meredith","orcid":null},"institutions":[{"id":"https://openalex.org/I4210085935","display_name":"IBM Research - Almaden","ror":"https://ror.org/005w8dd04","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210085935","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Daniel N. Meredith","raw_affiliation_strings":["IBM Almaden Research Center, San Jose, CA"],"affiliations":[{"raw_affiliation_string":"IBM Almaden Research Center, San Jose, CA","institution_ids":["https://openalex.org/I4210085935"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103288542","display_name":"Linda Nguyen","orcid":null},"institutions":[{"id":"https://openalex.org/I4210085935","display_name":"IBM Research - Almaden","ror":"https://ror.org/005w8dd04","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210085935","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Linda A. Nguyen","raw_affiliation_strings":["IBM Almaden Research Center, San Jose, CA"],"affiliations":[{"raw_affiliation_string":"IBM Almaden Research Center, San Jose, CA","institution_ids":["https://openalex.org/I4210085935"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5019004319"],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.14496494,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1041","last_page":"1042"},"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":0.9865999817848206,"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/T11241","display_name":"Advanced Malware Detection Techniques","score":0.9715999960899353,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/web-crawler","display_name":"Web crawler","score":0.8955007195472717},{"id":"https://openalex.org/keywords/crawling","display_name":"Crawling","score":0.8160625696182251},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.7659318447113037},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7247768640518188},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.6566382646560669},{"id":"https://openalex.org/keywords/web-analytics","display_name":"Web analytics","score":0.5926633477210999},{"id":"https://openalex.org/keywords/web-search-engine","display_name":"Web search engine","score":0.49966883659362793},{"id":"https://openalex.org/keywords/focused-crawler","display_name":"Focused crawler","score":0.4720669090747833},{"id":"https://openalex.org/keywords/analytics","display_name":"Analytics","score":0.4492343068122864},{"id":"https://openalex.org/keywords/web-navigation","display_name":"Web navigation","score":0.40210777521133423},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3874492645263672},{"id":"https://openalex.org/keywords/static-web-page","display_name":"Static web page","score":0.3758843243122101},{"id":"https://openalex.org/keywords/web-development","display_name":"Web development","score":0.370189368724823},{"id":"https://openalex.org/keywords/web-intelligence","display_name":"Web intelligence","score":0.23921918869018555},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.2299896776676178}],"concepts":[{"id":"https://openalex.org/C13743948","wikidata":"https://www.wikidata.org/wiki/Q45842","display_name":"Web crawler","level":2,"score":0.8955007195472717},{"id":"https://openalex.org/C100368936","wikidata":"https://www.wikidata.org/wiki/Q1411725","display_name":"Crawling","level":2,"score":0.8160625696182251},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.7659318447113037},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7247768640518188},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.6566382646560669},{"id":"https://openalex.org/C516187249","wikidata":"https://www.wikidata.org/wiki/Q10719477","display_name":"Web analytics","level":5,"score":0.5926633477210999},{"id":"https://openalex.org/C521815418","wikidata":"https://www.wikidata.org/wiki/Q4182287","display_name":"Web search engine","level":4,"score":0.49966883659362793},{"id":"https://openalex.org/C73340581","wikidata":"https://www.wikidata.org/wiki/Q5463958","display_name":"Focused crawler","level":5,"score":0.4720669090747833},{"id":"https://openalex.org/C79158427","wikidata":"https://www.wikidata.org/wiki/Q485396","display_name":"Analytics","level":2,"score":0.4492343068122864},{"id":"https://openalex.org/C61096286","wikidata":"https://www.wikidata.org/wiki/Q7978592","display_name":"Web navigation","level":3,"score":0.40210777521133423},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3874492645263672},{"id":"https://openalex.org/C173576120","wikidata":"https://www.wikidata.org/wiki/Q2641220","display_name":"Static web page","level":4,"score":0.3758843243122101},{"id":"https://openalex.org/C79373723","wikidata":"https://www.wikidata.org/wiki/Q386275","display_name":"Web development","level":3,"score":0.370189368724823},{"id":"https://openalex.org/C544335954","wikidata":"https://www.wikidata.org/wiki/Q2553348","display_name":"Web intelligence","level":4,"score":0.23921918869018555},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.2299896776676178},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0},{"id":"https://openalex.org/C105702510","wikidata":"https://www.wikidata.org/wiki/Q514","display_name":"Anatomy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1135777.1136005","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1135777.1136005","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 15th 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/W1489992655","https://openalex.org/W2013723863","https://openalex.org/W2029341294"],"related_works":["https://openalex.org/W2095543197","https://openalex.org/W2417265363","https://openalex.org/W2402678663","https://openalex.org/W2377634017","https://openalex.org/W3201526811","https://openalex.org/W2379145789","https://openalex.org/W2610451498","https://openalex.org/W1994958611","https://openalex.org/W4200125296","https://openalex.org/W3046853877"],"abstract_inverted_index":{"The":[0],"web":[1,53,63,91],"crawler":[2,20,125],"space":[3],"is":[4,100],"often":[5],"delimited":[6],"into":[7],"two":[8,27],"general":[9,68],"areas:":[10],"full-web":[11],"crawling":[12],"and":[13,44,115,124],"focused":[14],"crawling.":[15,36],"We":[16],"present":[17],"netSifter,":[18],"a":[19,39,50,56,84,94],"system":[21],"which":[22,46],"integrates":[23],"features":[24],"from":[25,55,117],"these":[26],"areas":[28],"to":[29,49,65,103],"provide":[30],"an":[31,80],"effective":[32],"mechanism":[33],"for":[34],"web-scale":[35],"netSifter":[37,77,99],"utilizes":[38],"combination":[40],"of":[41,52,70,83,89,97,108,120],"page-level":[42],"analytics":[43],"heuristics":[45],"are":[47],"applied":[48],"sample":[51],"pages":[54,64],"given":[57],"website.":[58,73],"These":[59],"algorithms":[60],"score":[61],"individual":[62],"determine":[66],"the":[67,71,87,105,118,129],"utility":[69],"overall":[72],"In":[74],"doing":[75],"so,":[76],"can":[78],"formulate":[79],"in-depth":[81],"opinion":[82],"website":[85],"(and":[86],"entirety":[88],"its":[90,109],"pages)":[92],"with":[93],"relative":[95],"minimum":[96],"work.":[98],"then":[101],"able":[102],"bias":[104],"future":[106],"efforts":[107],"crawl":[110],"towards":[111],"higher":[112],"quality":[113,122],"websites,":[114],"away":[116],"myriad":[119],"low":[121],"websites":[123],"traps":[126],"that":[127],"litter":[128],"World":[130],"Wide":[131],"Web.":[132]},"counts_by_year":[{"year":2017,"cited_by_count":1},{"year":2012,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
