{"id":"https://openalex.org/W2130196635","doi":"https://doi.org/10.1145/1277741.1277814","title":"Know your neighbors","display_name":"Know your neighbors","publication_year":2007,"publication_date":"2007-07-23","ids":{"openalex":"https://openalex.org/W2130196635","doi":"https://doi.org/10.1145/1277741.1277814","mag":"2130196635"},"language":"en","primary_location":{"id":"doi:10.1145/1277741.1277814","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1277741.1277814","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th annual international ACM SIGIR conference on Research and development in information retrieval","raw_type":"proceedings-article"},"type":"conference-paper","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/A5084282503","display_name":"Carlos Castillo","orcid":"https://orcid.org/0000-0003-4544-0416"},"institutions":[{"id":"https://openalex.org/I1325784139","display_name":"Yahoo (United Kingdom)","ror":"https://ror.org/038p3gq39","country_code":"GB","type":"company","lineage":["https://openalex.org/I1325784139","https://openalex.org/I4210134091"]},{"id":"https://openalex.org/I2800095910","display_name":"Yahoo (Spain)","ror":"https://ror.org/03gq8sg42","country_code":"ES","type":"company","lineage":["https://openalex.org/I2800095910","https://openalex.org/I4210134091"]}],"countries":["ES","GB"],"is_corresponding":false,"raw_author_name":"Carlos Castillo","raw_affiliation_strings":["Yahoo! Research Barcelona, Catalunya, Spain","Yahoo!, Research Barcelona, Catalunya, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yahoo! Research Barcelona, Catalunya, Spain","institution_ids":["https://openalex.org/I2800095910"]},{"raw_affiliation_string":"Yahoo!, Research Barcelona, Catalunya, Spain","institution_ids":["https://openalex.org/I1325784139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018490566","display_name":"Debora Donato","orcid":null},"institutions":[{"id":"https://openalex.org/I1325784139","display_name":"Yahoo (United Kingdom)","ror":"https://ror.org/038p3gq39","country_code":"GB","type":"company","lineage":["https://openalex.org/I1325784139","https://openalex.org/I4210134091"]},{"id":"https://openalex.org/I2800095910","display_name":"Yahoo (Spain)","ror":"https://ror.org/03gq8sg42","country_code":"ES","type":"company","lineage":["https://openalex.org/I2800095910","https://openalex.org/I4210134091"]}],"countries":["ES","GB"],"is_corresponding":false,"raw_author_name":"Debora Donato","raw_affiliation_strings":["Yahoo! Research Barcelona, Catalunya, Spain","Yahoo!, Research Barcelona, Catalunya, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yahoo! Research Barcelona, Catalunya, Spain","institution_ids":["https://openalex.org/I2800095910"]},{"raw_affiliation_string":"Yahoo!, Research Barcelona, Catalunya, Spain","institution_ids":["https://openalex.org/I1325784139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022164041","display_name":"Aristides Gionis","orcid":"https://orcid.org/0000-0002-5211-112X"},"institutions":[{"id":"https://openalex.org/I1325784139","display_name":"Yahoo (United Kingdom)","ror":"https://ror.org/038p3gq39","country_code":"GB","type":"company","lineage":["https://openalex.org/I1325784139","https://openalex.org/I4210134091"]},{"id":"https://openalex.org/I2800095910","display_name":"Yahoo (Spain)","ror":"https://ror.org/03gq8sg42","country_code":"ES","type":"company","lineage":["https://openalex.org/I2800095910","https://openalex.org/I4210134091"]}],"countries":["ES","GB"],"is_corresponding":false,"raw_author_name":"Aristides Gionis","raw_affiliation_strings":["Yahoo! Research Barcelona, Catalunya, Spain","Yahoo!, Research Barcelona, Catalunya, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yahoo! Research Barcelona, Catalunya, Spain","institution_ids":["https://openalex.org/I2800095910"]},{"raw_affiliation_string":"Yahoo!, Research Barcelona, Catalunya, Spain","institution_ids":["https://openalex.org/I1325784139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060492418","display_name":"Vanessa Murdock","orcid":"https://orcid.org/0000-0003-1682-0081"},"institutions":[{"id":"https://openalex.org/I1325784139","display_name":"Yahoo (United Kingdom)","ror":"https://ror.org/038p3gq39","country_code":"GB","type":"company","lineage":["https://openalex.org/I1325784139","https://openalex.org/I4210134091"]},{"id":"https://openalex.org/I2800095910","display_name":"Yahoo (Spain)","ror":"https://ror.org/03gq8sg42","country_code":"ES","type":"company","lineage":["https://openalex.org/I2800095910","https://openalex.org/I4210134091"]}],"countries":["ES","GB"],"is_corresponding":false,"raw_author_name":"Vanessa Murdock","raw_affiliation_strings":["Yahoo! Research Barcelona, Catalunya, Spain","Yahoo!, Research Barcelona, Catalunya, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yahoo! Research Barcelona, Catalunya, Spain","institution_ids":["https://openalex.org/I2800095910"]},{"raw_affiliation_string":"Yahoo!, Research Barcelona, Catalunya, Spain","institution_ids":["https://openalex.org/I1325784139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5044165871","display_name":"Fabrizio Silvestri","orcid":"https://orcid.org/0000-0001-7669-9055"},"institutions":[{"id":"https://openalex.org/I122991210","display_name":"Istituto di Scienza e Tecnologie dell'Informazione \"Alessandro Faedo\"","ror":"https://ror.org/05kacka20","country_code":"IT","type":"facility","lineage":["https://openalex.org/I122991210","https://openalex.org/I4210155236"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Fabrizio Silvestri","raw_affiliation_strings":["ISTI-CNR, Pisa, Italy","ISTI--CNR, Pisa, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ISTI-CNR, Pisa, Italy","institution_ids":["https://openalex.org/I122991210"]},{"raw_affiliation_string":"ISTI--CNR, Pisa, Italy","institution_ids":["https://openalex.org/I122991210"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":18.3242,"has_fulltext":false,"cited_by_count":316,"citation_normalized_percentile":{"value":0.9959195,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"423","last_page":"430"},"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":0.9987000226974487,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9975000023841858,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/computer-science","display_name":"Computer science","score":0.7900564670562744},{"id":"https://openalex.org/keywords/spamdexing","display_name":"Spamdexing","score":0.7063149213790894},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.5578582286834717},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.5001113414764404},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.4817228615283966},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4751448631286621},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4669573903083801},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.4650704860687256},{"id":"https://openalex.org/keywords/search-engine","display_name":"Search engine","score":0.44988682866096497},{"id":"https://openalex.org/keywords/the-internet","display_name":"The Internet","score":0.4390116035938263},{"id":"https://openalex.org/keywords/web-crawler","display_name":"Web crawler","score":0.43032246828079224},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3607223629951477},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.32387733459472656},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.30443936586380005},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.30057477951049805},{"id":"https://openalex.org/keywords/web-search-engine","display_name":"Web search engine","score":0.25303560495376587},{"id":"https://openalex.org/keywords/web-search-query","display_name":"Web search query","score":0.14687633514404297}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7900564670562744},{"id":"https://openalex.org/C13565553","wikidata":"https://www.wikidata.org/wiki/Q804206","display_name":"Spamdexing","level":5,"score":0.7063149213790894},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5578582286834717},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.5001113414764404},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.4817228615283966},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4751448631286621},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4669573903083801},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.4650704860687256},{"id":"https://openalex.org/C97854310","wikidata":"https://www.wikidata.org/wiki/Q19541","display_name":"Search engine","level":2,"score":0.44988682866096497},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.4390116035938263},{"id":"https://openalex.org/C13743948","wikidata":"https://www.wikidata.org/wiki/Q45842","display_name":"Web crawler","level":2,"score":0.43032246828079224},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3607223629951477},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.32387733459472656},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.30443936586380005},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.30057477951049805},{"id":"https://openalex.org/C521815418","wikidata":"https://www.wikidata.org/wiki/Q4182287","display_name":"Web search engine","level":4,"score":0.25303560495376587},{"id":"https://openalex.org/C164120249","wikidata":"https://www.wikidata.org/wiki/Q995982","display_name":"Web search query","level":3,"score":0.14687633514404297}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/1277741.1277814","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1277741.1277814","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th annual international ACM SIGIR conference on Research and development in information retrieval","raw_type":"proceedings-article"},{"id":"pmh:oai:dnet:people______::934a56bc62833b16be0c4ae705c23f43","is_oa":false,"landing_page_url":"https://openportal.isti.cnr.it/doc?id=people______::934a56bc62833b16be0c4ae705c23f43","pdf_url":null,"source":{"id":"https://openalex.org/S7407055261","display_name":"ISTI Open Portal","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"30th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 423\u2013430, Amsterdam, Netherland, 23-27 July 2007","raw_type":"http://purl.org/coar/resource_type/c_5794"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320333067","display_name":"Sixth Framework Programme","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":52,"referenced_works":["https://openalex.org/W35872195","https://openalex.org/W38924359","https://openalex.org/W49362422","https://openalex.org/W189202421","https://openalex.org/W202878612","https://openalex.org/W1529464143","https://openalex.org/W1604983895","https://openalex.org/W1660390307","https://openalex.org/W1764421085","https://openalex.org/W1845137714","https://openalex.org/W1854214752","https://openalex.org/W1966982551","https://openalex.org/W1967825155","https://openalex.org/W1986831811","https://openalex.org/W1987365175","https://openalex.org/W1994727615","https://openalex.org/W2000273502","https://openalex.org/W2004951603","https://openalex.org/W2009408190","https://openalex.org/W2013316690","https://openalex.org/W2014134732","https://openalex.org/W2025051251","https://openalex.org/W2029500199","https://openalex.org/W2052841581","https://openalex.org/W2066055909","https://openalex.org/W2073562093","https://openalex.org/W2099324655","https://openalex.org/W2102232904","https://openalex.org/W2107428549","https://openalex.org/W2108671511","https://openalex.org/W2112400959","https://openalex.org/W2123504579","https://openalex.org/W2130854091","https://openalex.org/W2139148100","https://openalex.org/W2142604303","https://openalex.org/W2152814537","https://openalex.org/W2154455818","https://openalex.org/W2156632103","https://openalex.org/W2169263924","https://openalex.org/W2169270715","https://openalex.org/W2185268784","https://openalex.org/W2185735208","https://openalex.org/W2187973725","https://openalex.org/W2401383085","https://openalex.org/W2966207845","https://openalex.org/W6601535493","https://openalex.org/W6607569353","https://openalex.org/W6637101025","https://openalex.org/W6639055396","https://openalex.org/W6682494755","https://openalex.org/W6712844215","https://openalex.org/W7055702063"],"related_works":["https://openalex.org/W2368945903","https://openalex.org/W4385695127","https://openalex.org/W2389761961","https://openalex.org/W4255972148","https://openalex.org/W4254300012","https://openalex.org/W2963706618","https://openalex.org/W2113184419","https://openalex.org/W1999548128","https://openalex.org/W2102475112","https://openalex.org/W2062919806"],"abstract_inverted_index":{"Web":[0,49,58,87,148,167],"spam":[1,23,34,75],"can":[2,160],"significantly":[3],"deteriorate":[4],"the":[5,45,48,53,57,69,86,91,100,105,111,118,127,138],"quality":[6],"of":[7,47,84,107,130],"search":[8,19],"engine":[9],"results.":[10],"Thus":[11],"there":[12],"is":[13,142],"a":[14,33,152],"large":[15,153],"incentive":[16],"for":[17,146],"commercial":[18],"engines":[20],"to":[21,66,68,121,165],"detect":[22],"pages":[24],"efficiently":[25],"and":[26,40,43,103,124,136,154],"accurately.":[27],"In":[28],"this":[29],"paper":[30],"we":[31],"present":[32],"detection":[35],"system":[36,145],"that":[37,62,159],"combines":[38],"link-based":[39],"content-based":[41],"features,":[42],"uses":[44],"topology":[46,89],"graph":[50,88],"by":[51,94,113],"exploiting":[52],"link":[54],"dependencies":[55],"among":[56],"pages.":[59],"We":[60,80],"find":[61],"linked":[63],"hosts":[64,109,132],"tend":[65],"belong":[67],"same":[70],"class:":[71],"either":[72],"both":[73,77],"are":[74,78],"or":[76],"non-spam.":[79],"demonstrate":[81],"three":[82],"methods":[83],"incorporating":[85],"into":[90],"predictions":[92],"obtained":[93],"our":[95],"base":[96],"classifier:":[97],"(i)":[98],"clustering":[99],"host":[101],"graph,":[102],"assigning":[104],"label":[106],"all":[108],"in":[110,163],"cluster":[112],"majority":[114],"vote,":[115],"(ii)":[116],"propagating":[117],"predicted":[119,128],"labels":[120,129],"neighboring":[122,131],"hosts,":[123],"(iii)":[125],"using":[126,157],"as":[133],"new":[134],"features":[135],"retraining":[137],"classifier.":[139],"The":[140],"result":[141],"an":[143],"accurate":[144],"detecting":[147],"spam,":[149],"tested":[150],"on":[151],"public":[155],"dataset,":[156],"algorithms":[158],"be":[161],"applied":[162],"practice":[164],"large-scale":[166],"data.":[168]},"counts_by_year":[{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":11},{"year":2020,"cited_by_count":11},{"year":2019,"cited_by_count":12},{"year":2018,"cited_by_count":15},{"year":2017,"cited_by_count":15},{"year":2016,"cited_by_count":12},{"year":2015,"cited_by_count":25},{"year":2014,"cited_by_count":25},{"year":2013,"cited_by_count":31},{"year":2012,"cited_by_count":35}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
