{"id":"https://openalex.org/W1988814344","doi":"https://doi.org/10.1145/1326561.1326563","title":"Link analysis for Web spam detection","display_name":"Link analysis for Web spam detection","publication_year":2008,"publication_date":"2008-02-01","ids":{"openalex":"https://openalex.org/W1988814344","doi":"https://doi.org/10.1145/1326561.1326563","mag":"1988814344"},"language":"en","primary_location":{"id":"doi:10.1145/1326561.1326563","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1326561.1326563","pdf_url":null,"source":{"id":"https://openalex.org/S131231701","display_name":"ACM Transactions on the Web","issn_l":"1559-1131","issn":["1559-1131","1559-114X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on the Web","raw_type":"journal-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/A5039929633","display_name":"Luca Becchetti","orcid":"https://orcid.org/0000-0002-4941-0532"},"institutions":[{"id":"https://openalex.org/I861853513","display_name":"Sapienza University of Rome","ror":"https://ror.org/02be6w209","country_code":"IT","type":"education","lineage":["https://openalex.org/I861853513"]}],"countries":["IT"],"is_corresponding":true,"raw_author_name":"Luca Becchetti","raw_affiliation_strings":["Universit\u00e0 di Roma La Sapienza"],"affiliations":[{"raw_affiliation_string":"Universit\u00e0 di Roma La Sapienza","institution_ids":["https://openalex.org/I861853513"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084282503","display_name":"Carlos Castillo","orcid":"https://orcid.org/0000-0003-4544-0416"},"institutions":[{"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"]},{"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"]}],"countries":["ES","GB"],"is_corresponding":false,"raw_author_name":"Carlos Castillo","raw_affiliation_strings":["Yahoo! Research, Barcelona","Yahoo&excl; Research, Barcelona"],"affiliations":[{"raw_affiliation_string":"Yahoo! Research, Barcelona","institution_ids":["https://openalex.org/I2800095910"]},{"raw_affiliation_string":"Yahoo&excl; Research, Barcelona","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","Yahoo&excl; Research, Barcelona"],"affiliations":[{"raw_affiliation_string":"Yahoo! Research, Barcelona","institution_ids":["https://openalex.org/I2800095910"]},{"raw_affiliation_string":"Yahoo&excl; Research, Barcelona","institution_ids":["https://openalex.org/I1325784139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076204770","display_name":"Ricardo Baeza\u2010Yates","orcid":"https://orcid.org/0000-0003-3208-9778"},"institutions":[{"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"]},{"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"]}],"countries":["ES","GB"],"is_corresponding":false,"raw_author_name":"Ricardo Baeza-YATES","raw_affiliation_strings":["Yahoo! Research, Barcelona","Yahoo&excl; Research, Barcelona"],"affiliations":[{"raw_affiliation_string":"Yahoo! Research, Barcelona","institution_ids":["https://openalex.org/I2800095910"]},{"raw_affiliation_string":"Yahoo&excl; Research, Barcelona","institution_ids":["https://openalex.org/I1325784139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102836759","display_name":"Stefano Leonardi","orcid":"https://orcid.org/0000-0002-9809-7191"},"institutions":[{"id":"https://openalex.org/I861853513","display_name":"Sapienza University of Rome","ror":"https://ror.org/02be6w209","country_code":"IT","type":"education","lineage":["https://openalex.org/I861853513"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Stefano Leonardi","raw_affiliation_strings":["Universit\u00e0 di Roma La Sapienza"],"affiliations":[{"raw_affiliation_string":"Universit\u00e0 di Roma La Sapienza","institution_ids":["https://openalex.org/I861853513"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5039929633"],"corresponding_institution_ids":["https://openalex.org/I861853513"],"apc_list":null,"apc_paid":null,"fwci":34.112,"has_fulltext":false,"cited_by_count":124,"citation_normalized_percentile":{"value":0.99655375,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":"2","issue":"1","first_page":"1","last_page":"42"},"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/T10064","display_name":"Complex Network Analysis Techniques","score":0.9987000226974487,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9973999857902527,"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":0.8468146324157715},{"id":"https://openalex.org/keywords/spamdexing","display_name":"Spamdexing","score":0.639912486076355},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.5910828113555908},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5508648157119751},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.48198384046554565},{"id":"https://openalex.org/keywords/pagerank","display_name":"PageRank","score":0.46926066279411316},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.4329950213432312},{"id":"https://openalex.org/keywords/web-analytics","display_name":"Web analytics","score":0.42240530252456665},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3965032696723938},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.3675752878189087},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.33495795726776123},{"id":"https://openalex.org/keywords/web-search-engine","display_name":"Web search engine","score":0.2743367552757263},{"id":"https://openalex.org/keywords/web-application-security","display_name":"Web application security","score":0.26112717390060425},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2502583861351013},{"id":"https://openalex.org/keywords/web-development","display_name":"Web development","score":0.20203867554664612},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.1845676600933075}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8468146324157715},{"id":"https://openalex.org/C13565553","wikidata":"https://www.wikidata.org/wiki/Q804206","display_name":"Spamdexing","level":5,"score":0.639912486076355},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.5910828113555908},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5508648157119751},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.48198384046554565},{"id":"https://openalex.org/C2779172887","wikidata":"https://www.wikidata.org/wiki/Q184316","display_name":"PageRank","level":2,"score":0.46926066279411316},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.4329950213432312},{"id":"https://openalex.org/C516187249","wikidata":"https://www.wikidata.org/wiki/Q10719477","display_name":"Web analytics","level":5,"score":0.42240530252456665},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3965032696723938},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.3675752878189087},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33495795726776123},{"id":"https://openalex.org/C521815418","wikidata":"https://www.wikidata.org/wiki/Q4182287","display_name":"Web search engine","level":4,"score":0.2743367552757263},{"id":"https://openalex.org/C59241245","wikidata":"https://www.wikidata.org/wiki/Q4781497","display_name":"Web application security","level":4,"score":0.26112717390060425},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2502583861351013},{"id":"https://openalex.org/C79373723","wikidata":"https://www.wikidata.org/wiki/Q386275","display_name":"Web development","level":3,"score":0.20203867554664612},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.1845676600933075}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/1326561.1326563","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1326561.1326563","pdf_url":null,"source":{"id":"https://openalex.org/S131231701","display_name":"ACM Transactions on the Web","issn_l":"1559-1131","issn":["1559-1131","1559-114X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on the Web","raw_type":"journal-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.147.1303","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.147.1303","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.chato.cl/papers/becchetti_2007_link_analysis_web_spam_detection.pdf","raw_type":"text"},{"id":"pmh:oai:iris.uniroma1.it:11573/115157","is_oa":false,"landing_page_url":"http://hdl.handle.net/11573/115157","pdf_url":null,"source":{"id":"https://openalex.org/S4377196107","display_name":"IRIS Research product catalog (Sapienza University of Rome)","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":"","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1686337506","display_name":null,"funder_award_id":"IST-015964 AEOLUSIST-001907 DELIS","funder_id":"https://openalex.org/F4320334960","funder_display_name":"Seventh Framework Programme"},{"id":"https://openalex.org/G6956838420","display_name":null,"funder_award_id":"RBIN047MH9","funder_id":"https://openalex.org/F4320321873","funder_display_name":"Ministero dell\u2019Istruzione, dell\u2019Universit\u00e0 e della Ricerca"}],"funders":[{"id":"https://openalex.org/F4320321873","display_name":"Ministero dell\u2019Istruzione, dell\u2019Universit\u00e0 e della Ricerca","ror":"https://ror.org/0166hxq48"},{"id":"https://openalex.org/F4320334960","display_name":"Seventh Framework Programme","ror":"https://ror.org/00k4n6c32"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":59,"referenced_works":["https://openalex.org/W3397180","https://openalex.org/W49362422","https://openalex.org/W202878612","https://openalex.org/W1529464143","https://openalex.org/W1562405179","https://openalex.org/W1587364696","https://openalex.org/W1595409123","https://openalex.org/W1596752792","https://openalex.org/W1604983895","https://openalex.org/W1660390307","https://openalex.org/W1761167196","https://openalex.org/W1764421085","https://openalex.org/W1845137714","https://openalex.org/W1854214752","https://openalex.org/W1908728294","https://openalex.org/W1965996575","https://openalex.org/W1966982551","https://openalex.org/W1987365175","https://openalex.org/W1993284846","https://openalex.org/W2000273502","https://openalex.org/W2013316690","https://openalex.org/W2014134732","https://openalex.org/W2025051251","https://openalex.org/W2029173860","https://openalex.org/W2040615703","https://openalex.org/W2046441184","https://openalex.org/W2064710146","https://openalex.org/W2066055909","https://openalex.org/W2073562093","https://openalex.org/W2078399861","https://openalex.org/W2080676333","https://openalex.org/W2080745194","https://openalex.org/W2097362268","https://openalex.org/W2099324655","https://openalex.org/W2099789730","https://openalex.org/W2102232904","https://openalex.org/W2106750965","https://openalex.org/W2107428549","https://openalex.org/W2111708605","https://openalex.org/W2112400959","https://openalex.org/W2123504579","https://openalex.org/W2130196635","https://openalex.org/W2131873610","https://openalex.org/W2139148100","https://openalex.org/W2152814537","https://openalex.org/W2156632103","https://openalex.org/W2165753192","https://openalex.org/W2169263924","https://openalex.org/W2169270715","https://openalex.org/W2493235950","https://openalex.org/W2620403137","https://openalex.org/W2899702797","https://openalex.org/W2912934387","https://openalex.org/W2966207845","https://openalex.org/W4249653116","https://openalex.org/W6633452139","https://openalex.org/W6633534558","https://openalex.org/W6637101025","https://openalex.org/W6683392976"],"related_works":["https://openalex.org/W2154222238","https://openalex.org/W2106626222","https://openalex.org/W2734818785","https://openalex.org/W2794551092","https://openalex.org/W2302347121","https://openalex.org/W1980745463","https://openalex.org/W2376574812","https://openalex.org/W1968521419","https://openalex.org/W4312824761","https://openalex.org/W2947611096"],"abstract_inverted_index":{"We":[0,56,121],"propose":[1],"link-based":[2],"techniques":[3,18],"for":[4],"automatic":[5],"detection":[6],"of":[7,29,44,61,65,73,79,114,118,126,129,131,148,164],"Web":[8,30,46,66,81,92,105,149],"spam,":[9],"a":[10,58,62,95,124,145,159],"term":[11],"referring":[12],"to":[13,19,36,40,103,162,175],"pages":[14],"which":[15,47,108],"use":[16,28,169],"deceptive":[17],"obtain":[20],"undeservedly":[21],"high":[22],"scores":[23],"in":[24,50,76,94],"search":[25],"engines.":[26],"The":[27],"spam":[31,106,166],"is":[32],"widespread":[33],"and":[34,86],"difficult":[35],"solve,":[37],"mostly":[38],"due":[39],"the":[41,45,74,77,90,111,115,127,132],"large":[42,63,146],"size":[43],"means":[48],"that,":[49],"practice,":[51],"many":[52],"algorithms":[53],"are":[54,101,173],"infeasible.":[55],"perform":[57],"statistical":[59,99],"analysis":[60],"collection":[64,147],"pages.":[67],"In":[68],"particular,":[69],"we":[70],"compute":[71],"statistics":[72],"links":[75],"vicinity":[78],"every":[80],"page":[82,119],"applying":[83],"rank":[84],"propagation":[85],"probabilistic":[87],"counting":[88],"over":[89,144],"entire":[91],"graph":[93],"scalable":[96],"way.":[97],"These":[98],"features":[100],"used":[102],"build":[104],"classifiers":[107,133,157,167],"only":[109],"consider":[110],"link":[112,150],"structure":[113],"Web,":[116],"regardless":[117],"contents.":[120],"then":[122],"present":[123],"study":[125],"performance":[128,160],"each":[130],"alone,":[134],"as":[135,137],"well":[136],"their":[138],"combined":[139],"performance,":[140],"by":[141],"testing":[142],"them":[143],"spam.":[151],"After":[152],"tenfold":[153],"cross-validation,":[154],"our":[155],"best":[156],"have":[158],"comparable":[161],"that":[163,168],"state-of-the-art":[165],"content":[170],"attributes,":[171],"but":[172],"orthogonal":[174],"content-based":[176],"methods.":[177]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":6},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":8},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":7},{"year":2015,"cited_by_count":9},{"year":2014,"cited_by_count":10},{"year":2013,"cited_by_count":14},{"year":2012,"cited_by_count":11}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}
