{"id":"https://openalex.org/W2138323616","doi":"https://doi.org/10.1145/1451983.1451991","title":"Latent dirichlet allocation in web spam filtering","display_name":"Latent dirichlet allocation in web spam filtering","publication_year":2008,"publication_date":"2008-04-22","ids":{"openalex":"https://openalex.org/W2138323616","doi":"https://doi.org/10.1145/1451983.1451991","mag":"2138323616"},"language":"en","primary_location":{"id":"doi:10.1145/1451983.1451991","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1451983.1451991","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 4th 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/A5044904415","display_name":"Istv\u00e1n B\u00edr\u00f3","orcid":"https://orcid.org/0000-0002-3223-6558"},"institutions":[{"id":"https://openalex.org/I7597260","display_name":"Hungarian Academy of Sciences","ror":"https://ror.org/02ks8qq67","country_code":"HU","type":"funder","lineage":["https://openalex.org/I7597260"]},{"id":"https://openalex.org/I4210117195","display_name":"Institute for Computer Science and Control","ror":"https://ror.org/0249v7n71","country_code":"HU","type":"facility","lineage":["https://openalex.org/I4210117195","https://openalex.org/I7597260"]}],"countries":["HU"],"is_corresponding":true,"raw_author_name":"Istv\u00e1n B\u00edr\u00f3","raw_affiliation_strings":["Computer and Automation Research Institute of the Hungarian Academy of Sciences"],"affiliations":[{"raw_affiliation_string":"Computer and Automation Research Institute of the Hungarian Academy of Sciences","institution_ids":["https://openalex.org/I7597260","https://openalex.org/I4210117195"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109584874","display_name":"J\u00e1cint Szab\u00f3","orcid":null},"institutions":[{"id":"https://openalex.org/I4210117195","display_name":"Institute for Computer Science and Control","ror":"https://ror.org/0249v7n71","country_code":"HU","type":"facility","lineage":["https://openalex.org/I4210117195","https://openalex.org/I7597260"]},{"id":"https://openalex.org/I7597260","display_name":"Hungarian Academy of Sciences","ror":"https://ror.org/02ks8qq67","country_code":"HU","type":"funder","lineage":["https://openalex.org/I7597260"]}],"countries":["HU"],"is_corresponding":false,"raw_author_name":"J\u00e1cint Szab\u00f3","raw_affiliation_strings":["Computer and Automation Research Institute of the Hungarian Academy of Sciences"],"affiliations":[{"raw_affiliation_string":"Computer and Automation Research Institute of the Hungarian Academy of Sciences","institution_ids":["https://openalex.org/I7597260","https://openalex.org/I4210117195"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5021452458","display_name":"Andr\u00e1s A. Bencz\u00far","orcid":"https://orcid.org/0000-0002-9392-0986"},"institutions":[{"id":"https://openalex.org/I4210117195","display_name":"Institute for Computer Science and Control","ror":"https://ror.org/0249v7n71","country_code":"HU","type":"facility","lineage":["https://openalex.org/I4210117195","https://openalex.org/I7597260"]},{"id":"https://openalex.org/I7597260","display_name":"Hungarian Academy of Sciences","ror":"https://ror.org/02ks8qq67","country_code":"HU","type":"funder","lineage":["https://openalex.org/I7597260"]}],"countries":["HU"],"is_corresponding":false,"raw_author_name":"Andr\u00e1s A. Bencz\u00far","raw_affiliation_strings":["Computer and Automation Research Institute of the Hungarian Academy of Sciences"],"affiliations":[{"raw_affiliation_string":"Computer and Automation Research Institute of the Hungarian Academy of Sciences","institution_ids":["https://openalex.org/I7597260","https://openalex.org/I4210117195"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5044904415"],"corresponding_institution_ids":["https://openalex.org/I4210117195","https://openalex.org/I7597260"],"apc_list":null,"apc_paid":null,"fwci":16.6187,"has_fulltext":false,"cited_by_count":85,"citation_normalized_percentile":{"value":0.98864333,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"29","last_page":"32"},"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9995999932289124,"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/T10028","display_name":"Topic Modeling","score":0.9986000061035156,"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/latent-dirichlet-allocation","display_name":"Latent Dirichlet allocation","score":0.9623185992240906},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7756189107894897},{"id":"https://openalex.org/keywords/topic-model","display_name":"Topic model","score":0.598770260810852},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5768101811408997},{"id":"https://openalex.org/keywords/spamdexing","display_name":"Spamdexing","score":0.541535496711731},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.40341904759407043},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.40193355083465576},{"id":"https://openalex.org/keywords/search-engine","display_name":"Search engine","score":0.1657257080078125},{"id":"https://openalex.org/keywords/web-search-query","display_name":"Web search query","score":0.1456456184387207},{"id":"https://openalex.org/keywords/web-search-engine","display_name":"Web search engine","score":0.10971811413764954}],"concepts":[{"id":"https://openalex.org/C500882744","wikidata":"https://www.wikidata.org/wiki/Q269236","display_name":"Latent Dirichlet allocation","level":3,"score":0.9623185992240906},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7756189107894897},{"id":"https://openalex.org/C171686336","wikidata":"https://www.wikidata.org/wiki/Q3532085","display_name":"Topic model","level":2,"score":0.598770260810852},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5768101811408997},{"id":"https://openalex.org/C13565553","wikidata":"https://www.wikidata.org/wiki/Q804206","display_name":"Spamdexing","level":5,"score":0.541535496711731},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.40341904759407043},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.40193355083465576},{"id":"https://openalex.org/C97854310","wikidata":"https://www.wikidata.org/wiki/Q19541","display_name":"Search engine","level":2,"score":0.1657257080078125},{"id":"https://openalex.org/C164120249","wikidata":"https://www.wikidata.org/wiki/Q995982","display_name":"Web search query","level":3,"score":0.1456456184387207},{"id":"https://openalex.org/C521815418","wikidata":"https://www.wikidata.org/wiki/Q4182287","display_name":"Web search engine","level":4,"score":0.10971811413764954}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/1451983.1451991","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1451983.1451991","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 4th international workshop on Adversarial information retrieval on the web","raw_type":"proceedings-article"},{"id":"pmh:oai:eprints.sztaki.hu:5534","is_oa":false,"landing_page_url":"http://eprints.sztaki.hu/5534/","pdf_url":null,"source":{"id":"https://openalex.org/S4306401907","display_name":"SZTAKI Publication Repository (Hungarian Academy of Sciences)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I7597260","host_organization_name":"Hungarian Academy of Sciences","host_organization_lineage":["https://openalex.org/I7597260"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference or Workshop Item"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4481225701","display_name":null,"funder_award_id":"NK 72845","funder_id":"https://openalex.org/F4320321994","funder_display_name":"Hungarian Scientific Research Fund"}],"funders":[{"id":"https://openalex.org/F4320321994","display_name":"Hungarian Scientific Research Fund","ror":"https://ror.org/00v349e63"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W23149702","https://openalex.org/W569220443","https://openalex.org/W1536860849","https://openalex.org/W1570448133","https://openalex.org/W1880262756","https://openalex.org/W1967825155","https://openalex.org/W1979870225","https://openalex.org/W1987365175","https://openalex.org/W1988711048","https://openalex.org/W2001082470","https://openalex.org/W2042980227","https://openalex.org/W2050028965","https://openalex.org/W2066055909","https://openalex.org/W2066546027","https://openalex.org/W2068687483","https://openalex.org/W2103658758","https://openalex.org/W2104290684","https://openalex.org/W2104924585","https://openalex.org/W2107034620","https://openalex.org/W2107743791","https://openalex.org/W2110591510","https://openalex.org/W2128272588","https://openalex.org/W2130196635","https://openalex.org/W2169270715","https://openalex.org/W2184575469","https://openalex.org/W2303394219","https://openalex.org/W2966207845","https://openalex.org/W4231510805","https://openalex.org/W4233135949","https://openalex.org/W4285719527","https://openalex.org/W6639619044","https://openalex.org/W6644910505","https://openalex.org/W6686076552","https://openalex.org/W7048191986"],"related_works":["https://openalex.org/W2888805565","https://openalex.org/W4312773271","https://openalex.org/W4315588616","https://openalex.org/W2769501189","https://openalex.org/W2962686197","https://openalex.org/W2207653751","https://openalex.org/W4293863151","https://openalex.org/W3159709618","https://openalex.org/W2611137333","https://openalex.org/W3005513013"],"abstract_inverted_index":{"Latent":[0],"Dirichlet":[1],"allocation":[2],"(LDA)":[3],"(Blei,":[4],"Ng,":[5],"Jordan":[6],"2003)":[7],"is":[8,97,106,116],"a":[9,21,30,45,108,134,142],"fully":[10],"generative":[11],"statistical":[12],"language":[13],"model":[14],"on":[15,56,128],"the":[16,34,57,79,83,88,117,129],"content":[17,151],"and":[18,52,64,73,93,132,150],"topics":[19,75],"of":[20,23,32,59,71,90,122,137],"corpus":[22,58],"documents.":[24],"In":[25,67,82],"this":[26,68,115,126],"paper":[27],"we":[28,86,113],"apply":[29],"modification":[31],"LDA,":[33],"novel":[35],"multi-corpus":[36],"LDA":[37,54],"technique":[38],"for":[39,48],"web":[40,119],"spam":[41,63,72,99,103],"classification.":[42],"We":[43,124],"create":[44],"bag-of-words":[46],"document":[47],"every":[49],"Web":[50],"site":[51,96],"run":[53],"both":[55],"sites":[60],"labeled":[61],"as":[62,65,112],"non-spam.":[66],"way":[69],"collections":[70],"non-spam":[74],"are":[76],"created":[77],"in":[78,139],"training":[80],"phase.":[81],"test":[84,125],"phase":[85],"take":[87],"union":[89],"these":[91],"collections,":[92],"an":[94],"unseen":[95],"deemed":[98],"if":[100],"its":[101],"total":[102],"topic":[104],"probability":[105],"above":[107],"threshold.":[109],"As":[110],"far":[111],"know,":[114],"first":[118],"retrieval":[120],"application":[121],"LDA.":[123],"method":[127],"UK2007-WEBSPAM":[130],"corpus,":[131],"reach":[133],"relative":[135],"improvement":[136],"11%":[138],"F-measure":[140],"by":[141],"logistic":[143],"regression":[144],"based":[145],"combination":[146],"with":[147],"strong":[148],"link":[149],"baseline":[152],"classifiers.":[153]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":7},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":6},{"year":2017,"cited_by_count":6},{"year":2016,"cited_by_count":9},{"year":2015,"cited_by_count":11},{"year":2014,"cited_by_count":6},{"year":2013,"cited_by_count":6},{"year":2012,"cited_by_count":7}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}