{"id":"https://openalex.org/W1974950122","doi":"https://doi.org/10.1145/1531914.1531927","title":"Nullification test collections for web spam and SEO","display_name":"Nullification test collections for web spam and SEO","publication_year":2009,"publication_date":"2009-04-21","ids":{"openalex":"https://openalex.org/W1974950122","doi":"https://doi.org/10.1145/1531914.1531927","mag":"1974950122"},"language":"en","primary_location":{"id":"doi:10.1145/1531914.1531927","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1531914.1531927","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 5th International Workshop on Adversarial Information Retrieval on the 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/A5078526867","display_name":"Timothy W. Jones","orcid":"https://orcid.org/0000-0001-8930-7364"},"institutions":[{"id":"https://openalex.org/I118347636","display_name":"Australian National University","ror":"https://ror.org/019wvm592","country_code":"AU","type":"education","lineage":["https://openalex.org/I118347636"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Timothy Jones","raw_affiliation_strings":["The Australian National University, Canberra, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Australian National University, Canberra, Australia","institution_ids":["https://openalex.org/I118347636"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073093333","display_name":"Ramesh Sankaranarayana","orcid":"https://orcid.org/0000-0002-7001-5369"},"institutions":[{"id":"https://openalex.org/I118347636","display_name":"Australian National University","ror":"https://ror.org/019wvm592","country_code":"AU","type":"education","lineage":["https://openalex.org/I118347636"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Ramesh Sankaranarayana","raw_affiliation_strings":["The Australian National University, Canberra, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Australian National University, Canberra, Australia","institution_ids":["https://openalex.org/I118347636"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032211209","display_name":"David Hawking","orcid":"https://orcid.org/0000-0002-3704-5398"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"David Hawking","raw_affiliation_strings":["Funnelback Pty Ltd, Canberra, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Funnelback Pty Ltd, Canberra, Australia","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5055132321","display_name":"Nick Craswell","orcid":"https://orcid.org/0000-0002-9351-8137"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]},{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB","US"],"is_corresponding":false,"raw_author_name":"Nick Craswell","raw_affiliation_strings":["Microsoft Research, Cambridge, UK","Microsoft Research, Cambridge, UK;"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research, Cambridge, UK","institution_ids":["https://openalex.org/I4210164937"]},{"raw_affiliation_string":"Microsoft Research, Cambridge, UK;","institution_ids":["https://openalex.org/I1290206253"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.8822,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.94127861,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"53","last_page":"60"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11644","display_name":"Spam and Phishing Detection","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/T11644","display_name":"Spam and Phishing Detection","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/T12016","display_name":"Web Data Mining and Analysis","score":0.998199999332428,"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/T11147","display_name":"Misinformation and Its Impacts","score":0.9977999925613403,"subfield":{"id":"https://openalex.org/subfields/3312","display_name":"Sociology and Political Science"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7694714069366455},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.7406235933303833},{"id":"https://openalex.org/keywords/ranking","display_name":"Ranking (information retrieval)","score":0.663422167301178},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.5778408646583557},{"id":"https://openalex.org/keywords/web-crawler","display_name":"Web crawler","score":0.5587030053138733},{"id":"https://openalex.org/keywords/blacklisting","display_name":"Blacklisting","score":0.4826236665248871},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.4257763624191284},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.09340208768844604}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7694714069366455},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.7406235933303833},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.663422167301178},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.5778408646583557},{"id":"https://openalex.org/C13743948","wikidata":"https://www.wikidata.org/wiki/Q45842","display_name":"Web crawler","level":2,"score":0.5587030053138733},{"id":"https://openalex.org/C2779797433","wikidata":"https://www.wikidata.org/wiki/Q632959","display_name":"Blacklisting","level":2,"score":0.4826236665248871},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.4257763624191284},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.09340208768844604}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/1531914.1531927","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1531914.1531927","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 5th International Workshop on Adversarial Information Retrieval on the Web","raw_type":"proceedings-article"},{"id":"pmh:oai:openresearch-repository.anu.edu.au:1885/56223","is_oa":false,"landing_page_url":"http://hdl.handle.net/1885/56223","pdf_url":null,"source":{"id":"https://openalex.org/S4306402539","display_name":"ANU Open Research (Australian National University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I118347636","host_organization_name":"Australian National University","host_organization_lineage":["https://openalex.org/I118347636"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://doi.acm.org/10.1145/1531914.1531927","raw_type":"Conference paper"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W1660390307","https://openalex.org/W1845137714","https://openalex.org/W1854214752","https://openalex.org/W1967825155","https://openalex.org/W1967879792","https://openalex.org/W1987365175","https://openalex.org/W2008778571","https://openalex.org/W2031317221","https://openalex.org/W2066636486","https://openalex.org/W2073562093","https://openalex.org/W2079672501","https://openalex.org/W2085030399","https://openalex.org/W2116504754","https://openalex.org/W2121672615","https://openalex.org/W2122505515","https://openalex.org/W2129235726","https://openalex.org/W2133968343","https://openalex.org/W2138621811","https://openalex.org/W2139148100","https://openalex.org/W2142604303","https://openalex.org/W2154610494","https://openalex.org/W2158601853","https://openalex.org/W2160952429","https://openalex.org/W2164052363","https://openalex.org/W2169270715","https://openalex.org/W2184111937","https://openalex.org/W2246912952","https://openalex.org/W2401383085","https://openalex.org/W2402775959","https://openalex.org/W4240407914","https://openalex.org/W6637101025","https://openalex.org/W6639055396","https://openalex.org/W6678180042","https://openalex.org/W6691009775","https://openalex.org/W6712844215"],"related_works":["https://openalex.org/W2118564381","https://openalex.org/W4385695127","https://openalex.org/W2389761961","https://openalex.org/W2163901716","https://openalex.org/W2963706618","https://openalex.org/W2152204162","https://openalex.org/W2113184419","https://openalex.org/W2739821120","https://openalex.org/W2150136235","https://openalex.org/W2026095310"],"abstract_inverted_index":{"Research":[0],"in":[1,83,166],"the":[2,12,15,30,42,56,66,88,119,167,186,194,205,208],"area":[3],"of":[4,14,33,44,58,62,69,77,110,144,190,196,207],"adversarial":[5,130],"information":[6],"retrieval":[7],"has":[8],"been":[9],"facilitated":[10],"by":[11,51,141,158],"availability":[13],"UK-2006/UK-2007":[16],"collections,":[17],"comprising":[18],"crawl":[19,72,155],"data,":[20],"link":[21],"graph,":[22],"and":[23,114,137,148,161,188,193],"spam":[24,34],"labels.":[25],"However,":[26],"research":[27],"into":[28],"nullifying":[29],"negative":[31],"effect":[32],"or":[35,61],"excessive":[36],"search":[37,101],"engine":[38],"optimisation":[39],"(SEO)":[40],"on":[41],"ranking":[43],"non-spam":[45],"pages":[46,97],"is":[47,55,134,139,172],"not":[48,135],"well":[49],"supported":[50,140],"these":[52,84],"resources.":[53],"Nor":[54],"study":[57],"cloaking":[59],"techniques":[60],"click":[63],"spam.":[64],"Finally,":[65],"domain-restricted":[67,136],"nature":[68],"a":[70,122,126,142,175,179],".uk":[71],"means":[73],"that":[74],"only":[75],"parts":[76],"link-farm":[78],"icebergs":[79],"may":[80],"be":[81,164],"visible":[82],"crawls.":[85],"We":[86,103,124,184],"introduce":[87],"term":[89],"nullification":[90],"which":[91,133,138,162],"we":[92],"define":[93],"as":[94,121,174,200],"\"preventing":[95],"problem":[96],"from":[98],"negatively":[99],"affecting":[100],"results\".":[102],"show":[104],"some":[105],"important":[106],"differences":[107],"between":[108],"properties":[109],"current":[111],".uk-restricted":[112],"crawls":[113],"those":[115],"previously":[116],"reported":[117],"for":[118,128,178,210],"Web":[120,170],"whole.":[123],"identify":[125],"need":[127],"an":[129],"IR":[131],"collection":[132,209],"set":[143],"appropriate":[145],"query":[146,201],"sets":[147],"(optimistically)":[149],"user-behaviour":[150],"data.":[151],"The":[152],"billion-page":[153],"unrestricted":[154],"being":[156],"conducted":[157],"CMU":[159],"(web09-bst)":[160],"will":[163],"used":[165],"2009":[168],"TREC":[169],"Track":[171],"assessed":[173],"possible":[176],"basis":[177],"new":[180],"AIR":[181,211],"test":[182],"collection.":[183],"discuss":[185],"pros":[187],"cons":[189],"its":[191],"scale,":[192],"feasibility":[195],"adding":[197],"resources":[198],"such":[199],"lists":[202],"to":[203],"enhance":[204],"utility":[206],"research.":[212]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2013,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}