{"id":"https://openalex.org/W3019238116","doi":"https://doi.org/10.1045/february2006-smith","title":"Observed Web Robot Behavior on Decaying Web Subsites","display_name":"Observed Web Robot Behavior on Decaying Web Subsites","publication_year":2006,"publication_date":"2006-02-01","ids":{"openalex":"https://openalex.org/W3019238116","doi":"https://doi.org/10.1045/february2006-smith","mag":"3019238116"},"language":"en","primary_location":{"id":"doi:10.1045/february2006-smith","is_oa":true,"landing_page_url":"https://doi.org/10.1045/february2006-smith","pdf_url":"http://www.vldb.org/conf/2004/RS15P3.PDF","source":{"id":"https://openalex.org/S119508283","display_name":"D-Lib Magazine","issn_l":"1082-9873","issn":["1082-9873"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310316316","host_organization_name":"Corporation for National Research Initiatives","host_organization_lineage":["https://openalex.org/P4310316316"],"host_organization_lineage_names":["Corporation for National Research Initiatives"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"D-Lib Magazine","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"http://www.vldb.org/conf/2004/RS15P3.PDF","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5113726511","display_name":"Joan A. Smith","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Joan A. Smith","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024007359","display_name":"Frank McCown","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Frank McCown","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5081811192","display_name":"Michael L. Nelson","orcid":"https://orcid.org/0000-0003-3749-8116"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Michael L. Nelson","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5113726511"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":9.534,"has_fulltext":true,"cited_by_count":18,"citation_normalized_percentile":{"value":0.97524769,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"12","issue":"2","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9997000098228455,"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":0.9997000098228455,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9165999889373779,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.9061999917030334,"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/crawling","display_name":"Crawling","score":0.7933013439178467},{"id":"https://openalex.org/keywords/search-engine","display_name":"Search engine","score":0.6465334296226501},{"id":"https://openalex.org/keywords/web-crawler","display_name":"Web crawler","score":0.635971188545227},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5871635675430298},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.5050016045570374},{"id":"https://openalex.org/keywords/traverse","display_name":"Traverse","score":0.49991607666015625},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.471306174993515},{"id":"https://openalex.org/keywords/web-search-query","display_name":"Web search query","score":0.41908133029937744},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.41184598207473755},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.09782534837722778},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.0782085657119751}],"concepts":[{"id":"https://openalex.org/C100368936","wikidata":"https://www.wikidata.org/wiki/Q1411725","display_name":"Crawling","level":2,"score":0.7933013439178467},{"id":"https://openalex.org/C97854310","wikidata":"https://www.wikidata.org/wiki/Q19541","display_name":"Search engine","level":2,"score":0.6465334296226501},{"id":"https://openalex.org/C13743948","wikidata":"https://www.wikidata.org/wiki/Q45842","display_name":"Web crawler","level":2,"score":0.635971188545227},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5871635675430298},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.5050016045570374},{"id":"https://openalex.org/C176809094","wikidata":"https://www.wikidata.org/wiki/Q15401496","display_name":"Traverse","level":2,"score":0.49991607666015625},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.471306174993515},{"id":"https://openalex.org/C164120249","wikidata":"https://www.wikidata.org/wiki/Q995982","display_name":"Web search query","level":3,"score":0.41908133029937744},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.41184598207473755},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.09782534837722778},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0782085657119751},{"id":"https://openalex.org/C105702510","wikidata":"https://www.wikidata.org/wiki/Q514","display_name":"Anatomy","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1045/february2006-smith","is_oa":true,"landing_page_url":"https://doi.org/10.1045/february2006-smith","pdf_url":"http://www.vldb.org/conf/2004/RS15P3.PDF","source":{"id":"https://openalex.org/S119508283","display_name":"D-Lib Magazine","issn_l":"1082-9873","issn":["1082-9873"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310316316","host_organization_name":"Corporation for National Research Initiatives","host_organization_lineage":["https://openalex.org/P4310316316"],"host_organization_lineage_names":["Corporation for National Research Initiatives"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"D-Lib Magazine","raw_type":"journal-article"},{"id":"pmh:oai:scholarworks.harding.edu:computer-science-facpub-1003","is_oa":true,"landing_page_url":"https://scholarworks.harding.edu/computer-science-facpub/2","pdf_url":null,"source":{"id":"https://openalex.org/S4377196751","display_name":"Scholar Works at Harding (Harding University Main Campus)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I107363760","host_organization_name":"Harding University Main Campus","host_organization_lineage":["https://openalex.org/I107363760"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Computer Science Faculty Research and Publications","raw_type":"text"}],"best_oa_location":{"id":"doi:10.1045/february2006-smith","is_oa":true,"landing_page_url":"https://doi.org/10.1045/february2006-smith","pdf_url":"http://www.vldb.org/conf/2004/RS15P3.PDF","source":{"id":"https://openalex.org/S119508283","display_name":"D-Lib Magazine","issn_l":"1082-9873","issn":["1082-9873"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310316316","host_organization_name":"Corporation for National Research Initiatives","host_organization_lineage":["https://openalex.org/P4310316316"],"host_organization_lineage_names":["Corporation for National Research Initiatives"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"D-Lib Magazine","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3019238116.pdf","grobid_xml":"https://content.openalex.org/works/W3019238116.grobid-xml"},"referenced_works_count":17,"referenced_works":["https://openalex.org/W1562405179","https://openalex.org/W1648885110","https://openalex.org/W1660390307","https://openalex.org/W1854214752","https://openalex.org/W1981202432","https://openalex.org/W2002089154","https://openalex.org/W2014478203","https://openalex.org/W2138621811","https://openalex.org/W2156523427","https://openalex.org/W2161118554","https://openalex.org/W4233775226","https://openalex.org/W4247585808","https://openalex.org/W4254761308","https://openalex.org/W4302339081","https://openalex.org/W6636944375","https://openalex.org/W6639055396","https://openalex.org/W6697054577"],"related_works":["https://openalex.org/W2566658409","https://openalex.org/W3119324922","https://openalex.org/W2352686120","https://openalex.org/W2372594123","https://openalex.org/W2358310581","https://openalex.org/W2964752624","https://openalex.org/W2026132847","https://openalex.org/W2137810919","https://openalex.org/W4255854114","https://openalex.org/W4385695127"],"abstract_inverted_index":{"Web":[0,114],"spam":[1,134],"pages":[2,42,53,79],"use":[3,69],"various":[4],"techniques":[5,36],"to":[6,25,37,54,76,83,93],"achieve":[7],"higher-than-deserved":[8],"rankings":[9],"in":[10],"a":[11,28,48,136,144],"search":[12],"engine's":[13],"results.":[14],"While":[15],"human":[16],"experts":[17],"can":[18,130],"identify":[19,63],"spam,":[20],"it":[21],"is":[22],"too":[23],"expensive":[24],"manually":[26,62],"evaluate":[27,119],"large":[29],"number":[30],"of":[31,51,73,101,107,122,139,148],"pages.":[32,103],"Instead,":[33],"we":[34,61,68,89,129],"propose":[35],"semi-automatically":[38],"separate":[39],"reputable,":[40],"good":[41,102,145],"from":[43,135],"spam.":[44],"We":[45,104],"first":[46],"select":[47],"small":[49],"set":[50,147],"seed":[52,66,96,146],"be":[55,84],"evaluated":[56],"by":[57,116],"an":[58],"expert.":[59],"Once":[60],"the":[64,70,74,95,99,111,120,140],"reputable":[65],"pages,":[67],"link":[71],"structure":[72],"web":[75],"discover":[77],"other":[78],"that":[80,128],"are":[81],"likely":[82],"good.":[85],"In":[86],"this":[87],"paper":[88],"discuss":[90],"possible":[91],"ways":[92],"implement":[94],"selection":[97],"and":[98,118],"discovery":[100],"present":[105],"results":[106,126],"experiments":[108],"run":[109],"on":[110,143],"World":[112],"Wide":[113],"indexed":[115],"AltaVista":[117],"performance":[121],"our":[123],"techniques.":[124],"Our":[125],"show":[127],"effectively":[131],"filter":[132],"out":[133],"significant":[137],"fraction":[138],"web,":[141],"based":[142],"less":[149],"than":[150],"200":[151],"sites.":[152]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2014,"cited_by_count":1}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}
