{"id":"https://openalex.org/W3022882875","doi":"https://doi.org/10.1145/3366424.3385773","title":"Scalable Anti-TrustRank with Qualified Site-level Seeds for Link-based Web Spam Detection","display_name":"Scalable Anti-TrustRank with Qualified Site-level Seeds for Link-based Web Spam Detection","publication_year":2020,"publication_date":"2020-04-20","ids":{"openalex":"https://openalex.org/W3022882875","doi":"https://doi.org/10.1145/3366424.3385773","mag":"3022882875"},"language":"en","primary_location":{"id":"doi:10.1145/3366424.3385773","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3366424.3385773","pdf_url":null,"source":{"id":"https://openalex.org/S4306506651","display_name":"Companion Proceedings of the Web Conference 2020","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion Proceedings of the Web Conference 2020","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/A5090741314","display_name":"Joyce Jiyoung Whang","orcid":"https://orcid.org/0000-0002-4773-3194"},"institutions":[{"id":"https://openalex.org/I848706","display_name":"Sungkyunkwan University","ror":"https://ror.org/04q78tk20","country_code":"KR","type":"education","lineage":["https://openalex.org/I848706"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Joyce Jiyoung Whang","raw_affiliation_strings":["","Sungkyunkwan University, Seoul, South Korea"],"affiliations":[{"raw_affiliation_string":"","institution_ids":[]},{"raw_affiliation_string":"Sungkyunkwan University, Seoul, South Korea","institution_ids":["https://openalex.org/I848706"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110559235","display_name":"Yeonsung Jung","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yeonsung Jung","raw_affiliation_strings":[""],"affiliations":[{"raw_affiliation_string":"","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109458239","display_name":"Seonggoo Kang","orcid":null},"institutions":[{"id":"https://openalex.org/I60922564","display_name":"Naver (South Korea)","ror":"https://ror.org/04nzrnx83","country_code":"KR","type":"company","lineage":["https://openalex.org/I60922564"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Seonggoo Kang","raw_affiliation_strings":["","Naver (South Korea), Seongnam-si, South Korea"],"affiliations":[{"raw_affiliation_string":"","institution_ids":[]},{"raw_affiliation_string":"Naver (South Korea), Seongnam-si, South Korea","institution_ids":["https://openalex.org/I60922564"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102403631","display_name":"Dongho Yoo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dongho Yoo","raw_affiliation_strings":[""],"affiliations":[{"raw_affiliation_string":"","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5063459703","display_name":"Inderjit S. Dhillon","orcid":"https://orcid.org/0000-0002-2759-1416"},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Inderjit S. Dhillon","raw_affiliation_strings":["","The University of Texas at Austin, Austin, United States"],"affiliations":[{"raw_affiliation_string":"","institution_ids":[]},{"raw_affiliation_string":"The University of Texas at Austin, Austin, United States","institution_ids":["https://openalex.org/I86519309"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5090741314"],"corresponding_institution_ids":["https://openalex.org/I848706"],"apc_list":null,"apc_paid":null,"fwci":1.3218,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.81919192,"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":"593","last_page":"602"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11644","display_name":"Spam and Phishing Detection","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/T11644","display_name":"Spam and Phishing Detection","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/T12016","display_name":"Web Data Mining and Analysis","score":0.9980000257492065,"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":0.9947999715805054,"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/computer-science","display_name":"Computer science","score":0.8336769342422485},{"id":"https://openalex.org/keywords/spambot","display_name":"Spambot","score":0.7023882865905762},{"id":"https://openalex.org/keywords/spamdexing","display_name":"Spamdexing","score":0.6314660310745239},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5685957074165344},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.5487280488014221},{"id":"https://openalex.org/keywords/forum-spam","display_name":"Forum spam","score":0.4697924852371216},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.42524251341819763},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.40120404958724976},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3530445098876953},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.3406914472579956},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.325781911611557},{"id":"https://openalex.org/keywords/spamming","display_name":"Spamming","score":0.3249039947986603},{"id":"https://openalex.org/keywords/the-internet","display_name":"The Internet","score":0.28614646196365356},{"id":"https://openalex.org/keywords/web-navigation","display_name":"Web navigation","score":0.25189870595932007},{"id":"https://openalex.org/keywords/web-search-engine","display_name":"Web search engine","score":0.16846302151679993},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.14022639393806458},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.10321071743965149}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8336769342422485},{"id":"https://openalex.org/C127735637","wikidata":"https://www.wikidata.org/wiki/Q2306702","display_name":"Spambot","level":4,"score":0.7023882865905762},{"id":"https://openalex.org/C13565553","wikidata":"https://www.wikidata.org/wiki/Q804206","display_name":"Spamdexing","level":5,"score":0.6314660310745239},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5685957074165344},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.5487280488014221},{"id":"https://openalex.org/C157310412","wikidata":"https://www.wikidata.org/wiki/Q3140915","display_name":"Forum spam","level":5,"score":0.4697924852371216},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.42524251341819763},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.40120404958724976},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3530445098876953},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.3406914472579956},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.325781911611557},{"id":"https://openalex.org/C158955206","wikidata":"https://www.wikidata.org/wiki/Q83058","display_name":"Spamming","level":3,"score":0.3249039947986603},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.28614646196365356},{"id":"https://openalex.org/C61096286","wikidata":"https://www.wikidata.org/wiki/Q7978592","display_name":"Web navigation","level":3,"score":0.25189870595932007},{"id":"https://openalex.org/C521815418","wikidata":"https://www.wikidata.org/wiki/Q4182287","display_name":"Web search engine","level":4,"score":0.16846302151679993},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.14022639393806458},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.10321071743965149}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3366424.3385773","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3366424.3385773","pdf_url":null,"source":{"id":"https://openalex.org/S4306506651","display_name":"Companion Proceedings of the Web Conference 2020","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion Proceedings of the Web Conference 2020","raw_type":"proceedings-article"},{"id":"pmh:oai:koasas.kaist.ac.kr:10203/277597","is_oa":false,"landing_page_url":"http://hdl.handle.net/10203/277597","pdf_url":null,"source":{"id":"https://openalex.org/S4306402435","display_name":"KAIST Institutional Repository (KAIST)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I157485424","host_organization_name":"Korea Advanced Institute of Science and Technology","host_organization_lineage":["https://openalex.org/I157485424"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"CONF"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W1518660678","https://openalex.org/W1527356121","https://openalex.org/W1845137714","https://openalex.org/W1969867713","https://openalex.org/W1988814344","https://openalex.org/W1993924397","https://openalex.org/W2005427757","https://openalex.org/W2059586463","https://openalex.org/W2066636486","https://openalex.org/W2067314954","https://openalex.org/W2090552478","https://openalex.org/W2091208042","https://openalex.org/W2095376951","https://openalex.org/W2099789730","https://openalex.org/W2100738695","https://openalex.org/W2117138276","https://openalex.org/W2118942057","https://openalex.org/W2121430617","https://openalex.org/W2122505515","https://openalex.org/W2128184786","https://openalex.org/W2130196635","https://openalex.org/W2138621811","https://openalex.org/W2138786025","https://openalex.org/W2139146018","https://openalex.org/W2139148100","https://openalex.org/W2146008005","https://openalex.org/W2268119334","https://openalex.org/W2513566807","https://openalex.org/W2902892638","https://openalex.org/W2911964244","https://openalex.org/W2914874661","https://openalex.org/W2915063781","https://openalex.org/W2918008835","https://openalex.org/W2954127006","https://openalex.org/W2962756421","https://openalex.org/W2997591727","https://openalex.org/W3099558206","https://openalex.org/W4206597598","https://openalex.org/W4230918692","https://openalex.org/W4240486361","https://openalex.org/W4248949446","https://openalex.org/W4251166437","https://openalex.org/W4392366624"],"related_works":["https://openalex.org/W2018000323","https://openalex.org/W2095720311","https://openalex.org/W2091208042","https://openalex.org/W2080521416","https://openalex.org/W3098355271","https://openalex.org/W2920666515","https://openalex.org/W2738482239","https://openalex.org/W2246912952","https://openalex.org/W2552201931","https://openalex.org/W1551975479"],"abstract_inverted_index":{"Web":[0],"spam":[1,17,29,43,59,149,183],"detection":[2,30],"is":[3,103],"one":[4],"of":[5,24,53,57,69,78,129,148,172],"the":[6,33,37,42,54,67,70,76,79,85,96,119,133,140,145,152,169,173,179,187],"most":[7],"important":[8],"and":[9],"challenging":[10],"tasks":[11],"in":[12,181],"web":[13,16,28,38,58,62,72],"search.":[14],"Since":[15],"pages":[18,39,150,184],"tend":[19],"to":[20,40,64,104,117,143,166],"have":[21],"a":[22,50,90,106,109,115,127],"lot":[23],"spurious":[25],"links,":[26],"many":[27],"algorithms":[31,162],"exploit":[32],"hyperlink":[34],"structure":[35,56,77],"between":[36],"detect":[41,144],"pages.":[44],"In":[45],"this":[46],"paper,":[47],"we":[48,88,113,123,157],"conduct":[49],"comprehensive":[51],"analysis":[52],"link":[55],"using":[60],"real-world":[61],"graphs":[63],"systemically":[65],"investigate":[66],"characteristics":[68],"link-based":[71],"spam.":[73],"By":[74],"exploring":[75],"page-level":[80],"graph":[81],"as":[82,84],"well":[83],"site-level":[86,92],"graph,":[87],"propose":[89],"scalable":[91],"seeding":[93,137],"methodology":[94],"for":[95,132],"Anti-TrustRank":[97],"(ATR)":[98],"algorithm.":[99,135],"The":[100],"key":[101],"idea":[102],"map":[105],"website":[107],"into":[108],"feature":[110],"space":[111],"where":[112],"learn":[114],"classifier":[116],"prioritize":[118],"websites":[120],"so":[121],"that":[122],"can":[124],"effectively":[125],"select":[126],"set":[128],"good":[130],"seeds":[131],"ATR":[134,141,161,175],"This":[136],"method":[138],"enables":[139],"algorithm":[142,176],"largest":[146],"number":[147],"among":[151],"competitive":[153],"baseline":[154],"methods.":[155],"Furthermore,":[156],"design":[158],"work-efficient":[159],"asynchronous":[160],"which":[163],"are":[164],"able":[165],"significantly":[167],"reduce":[168],"computational":[170],"cost":[171],"traditional":[174],"without":[177],"degrading":[178],"performance":[180],"detecting":[182],"while":[185],"guaranteeing":[186],"convergence.":[188]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":2}],"updated_date":"2026-03-18T14:38:29.013473","created_date":"2025-10-10T00:00:00"}
