{"id":"https://openalex.org/W2138786025","doi":"https://doi.org/10.1145/1935826.1935902","title":"Let web spammers expose themselves","display_name":"Let web spammers expose themselves","publication_year":2011,"publication_date":"2011-02-01","ids":{"openalex":"https://openalex.org/W2138786025","doi":"https://doi.org/10.1145/1935826.1935902","mag":"2138786025"},"language":"en","primary_location":{"id":"doi:10.1145/1935826.1935902","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1935826.1935902","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the fourth ACM international conference on Web search and data mining","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/A5004991630","display_name":"Zhicong Cheng","orcid":"https://orcid.org/0000-0002-6503-4581"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zhicong Cheng","raw_affiliation_strings":["Peking University, Beijing, China","Peking University, Beijing, China#TAB#"],"affiliations":[{"raw_affiliation_string":"Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"Peking University, Beijing, China#TAB#","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101870054","display_name":"Bin Gao","orcid":"https://orcid.org/0000-0001-9993-1013"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bin Gao","raw_affiliation_strings":["Microsoft Research Asia, Beijing, China","Microsoft research Asia, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]},{"raw_affiliation_string":"Microsoft research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029514633","display_name":"Congkai Sun","orcid":null},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Congkai Sun","raw_affiliation_strings":["University of Southern California, Los Angeles, CA, USA","[University of Southern California Los, Angeles, CA, USA]"],"affiliations":[{"raw_affiliation_string":"University of Southern California, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I1174212"]},{"raw_affiliation_string":"[University of Southern California Los, Angeles, CA, USA]","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019392030","display_name":"Yanbing Jiang","orcid":"https://orcid.org/0000-0002-0614-0835"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanbing Jiang","raw_affiliation_strings":["Peking University, Beijing, China","Peking University, Beijing, China#TAB#"],"affiliations":[{"raw_affiliation_string":"Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"Peking University, Beijing, China#TAB#","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101884287","display_name":"Tie\u2010Yan Liu","orcid":"https://orcid.org/0000-0002-0476-8020"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tie-Yan Liu","raw_affiliation_strings":["Microsoft Research Asia, Beijing, China","Microsoft research Asia, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]},{"raw_affiliation_string":"Microsoft research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5004991630"],"corresponding_institution_ids":["https://openalex.org/I20231570"],"apc_list":null,"apc_paid":null,"fwci":5.9115,"has_fulltext":false,"cited_by_count":18,"citation_normalized_percentile":{"value":0.96036497,"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":"525","last_page":"534"},"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/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.9961000084877014,"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"}},{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9958000183105469,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7352714538574219},{"id":"https://openalex.org/keywords/spambot","display_name":"Spambot","score":0.7111762762069702},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.679329514503479},{"id":"https://openalex.org/keywords/spamdexing","display_name":"Spamdexing","score":0.6707695722579956},{"id":"https://openalex.org/keywords/downgrade","display_name":"Downgrade","score":0.6378438472747803},{"id":"https://openalex.org/keywords/spamming","display_name":"Spamming","score":0.5948574542999268},{"id":"https://openalex.org/keywords/link-analysis","display_name":"Link analysis","score":0.5654613971710205},{"id":"https://openalex.org/keywords/forum-spam","display_name":"Forum spam","score":0.5407465100288391},{"id":"https://openalex.org/keywords/link","display_name":"Link (geometry)","score":0.45967936515808105},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.43369194865226746},{"id":"https://openalex.org/keywords/the-internet","display_name":"The Internet","score":0.3305317759513855},{"id":"https://openalex.org/keywords/web-search-engine","display_name":"Web search engine","score":0.31914377212524414},{"id":"https://openalex.org/keywords/web-development","display_name":"Web development","score":0.27405035495758057},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.1656600534915924},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.10160073637962341}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7352714538574219},{"id":"https://openalex.org/C127735637","wikidata":"https://www.wikidata.org/wiki/Q2306702","display_name":"Spambot","level":4,"score":0.7111762762069702},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.679329514503479},{"id":"https://openalex.org/C13565553","wikidata":"https://www.wikidata.org/wiki/Q804206","display_name":"Spamdexing","level":5,"score":0.6707695722579956},{"id":"https://openalex.org/C2779628075","wikidata":"https://www.wikidata.org/wiki/Q1253258","display_name":"Downgrade","level":2,"score":0.6378438472747803},{"id":"https://openalex.org/C158955206","wikidata":"https://www.wikidata.org/wiki/Q83058","display_name":"Spamming","level":3,"score":0.5948574542999268},{"id":"https://openalex.org/C1173588","wikidata":"https://www.wikidata.org/wiki/Q6554294","display_name":"Link analysis","level":2,"score":0.5654613971710205},{"id":"https://openalex.org/C157310412","wikidata":"https://www.wikidata.org/wiki/Q3140915","display_name":"Forum spam","level":5,"score":0.5407465100288391},{"id":"https://openalex.org/C2778753846","wikidata":"https://www.wikidata.org/wiki/Q6554239","display_name":"Link (geometry)","level":2,"score":0.45967936515808105},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.43369194865226746},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.3305317759513855},{"id":"https://openalex.org/C521815418","wikidata":"https://www.wikidata.org/wiki/Q4182287","display_name":"Web search engine","level":4,"score":0.31914377212524414},{"id":"https://openalex.org/C79373723","wikidata":"https://www.wikidata.org/wiki/Q386275","display_name":"Web development","level":3,"score":0.27405035495758057},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.1656600534915924},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.10160073637962341}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1935826.1935902","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1935826.1935902","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the fourth ACM international conference on Web search and data mining","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W202878612","https://openalex.org/W1660390307","https://openalex.org/W1845137714","https://openalex.org/W1987365175","https://openalex.org/W1996802155","https://openalex.org/W2027116318","https://openalex.org/W2028962062","https://openalex.org/W2066055909","https://openalex.org/W2089616424","https://openalex.org/W2117831564","https://openalex.org/W2128272588","https://openalex.org/W2139148100","https://openalex.org/W2146729596","https://openalex.org/W2156632103","https://openalex.org/W2165922980","https://openalex.org/W2169270715","https://openalex.org/W4285719527","https://openalex.org/W6637101025","https://openalex.org/W6683392976","https://openalex.org/W6685179926"],"related_works":["https://openalex.org/W2080521416","https://openalex.org/W4776438","https://openalex.org/W2091208042","https://openalex.org/W359598355","https://openalex.org/W2018000323","https://openalex.org/W2148238780","https://openalex.org/W2098732437","https://openalex.org/W2068696370","https://openalex.org/W2049541992","https://openalex.org/W2138786025"],"abstract_inverted_index":{"This":[0],"paper":[1],"is":[2,25,98,145,175],"concerned":[3],"with":[4,139,226],"mining":[5,160],"link":[6,9,12,64,87,104,120,129,162,196,234],"spams":[7,105,121,163],"(e.g.,":[8],"farm":[10],"and":[11,40,76,142,183,231,268],"exchange)":[13],"from":[14,106,165,223,232],"search":[15,28],"engine":[16],"optimization":[17],"(SEO)":[18],"forums.":[19,171,215,284],"To":[20,198],"provide":[21],"quality":[22],"services,":[23],"it":[24,97],"critical":[26],"for":[27,45,151,220,252],"engines":[29],"to":[30,53,73,79,101,153,192,247,265,273],"address":[31],"web":[32,126,135,238],"spam.":[33,197],"Several":[34],"techniques":[35],"such":[36,259],"as":[37,260],"TrustRank,":[38],"BadRank,":[39],"SpamRank":[41],"have":[42,71],"been":[43],"proposed":[44,308],"this":[46,111],"purpose.":[47],"Most":[48],"of":[49,57,66,147,195,212,287,295,315],"these":[50,188],"methods":[51],"try":[52],"downgrade":[54],"the":[55,58,107,148,155,166,169,173,200,206,210,213,221,237,249,253,307],"effects":[56],"spam":[59,69,92,130,250,261,274,288],"websites":[60,70,84,262,270,289],"by":[61,89,122,300],"identifying":[62],"specific":[63],"patterns":[65],"them.":[67],"However,":[68,172],"appeared":[72],"be":[74,298,311],"more":[75,77],"similar":[78],"normal":[80],"or":[81],"even":[82,184],"good":[83,269,313],"in":[85,168,187,190,209,236],"their":[86,91,224,233],"structures,":[88],"reforming":[90],"techniques.":[93,318],"As":[94],"a":[95,115,243,292,312],"result,":[96],"very":[99],"challenging":[100],"automatically":[102],"detect":[103],"Web":[108],"graph.":[109,239],"In":[110],"paper,":[112],"we":[113,202,217,241],"propose":[114,159],"different":[116],"approach,":[117],"which":[118,255,296],"detects":[119],"looking":[123],"at":[124],"how":[125],"spammers":[127,136],"make":[128],"happen.":[131],"We":[132,157,276],"find":[133],"that":[134,306],"usually":[137,263],"ally":[138],"each":[140,266],"other,":[141,267],"SEO":[143,170,214,283],"forum":[144,227],"one":[146],"major":[149,282],"means":[150],"them":[152],"form":[154],"alliance.":[156],"therefore":[158],"suspicious":[161],"directly":[164],"posts":[167,211],"task":[174],"non-trivial":[176],"because":[177],"there":[178],"are":[179],"also":[180],"other":[181],"information":[182],"noises":[185],"contained":[186,208],"posts,":[189],"addition":[191],"useful":[193],"clues":[194],"tackle":[199],"challenges,":[201],"first":[203],"extract":[204,218],"all":[205],"URLs":[207,222],"Second,":[216],"features":[219],"relationships":[225],"users":[228],"(potential":[229],"spammers)":[230],"structure":[235],"Third,":[240],"build":[242],"semi-supervised":[244],"learning":[245],"framework":[246],"calculate":[248],"scores":[251],"URLs,":[254],"encodes":[256],"several":[257],"heuristics":[258],"linking":[264,272],"seldom":[271],"websites.":[275],"tested":[277],"our":[278],"approach":[279,309],"on":[280],"seven":[281],"A":[285],"lot":[286],"were":[290],"identified,":[291],"significant":[293],"proportion":[294],"cannot":[297],"detected":[299],"conventional":[301],"anti-spam":[302,317],"methods.":[303],"It":[304],"indicates":[305],"can":[310],"complement":[314],"existing":[316]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":2},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":2}],"updated_date":"2026-01-13T01:12:25.745995","created_date":"2025-10-10T00:00:00"}
