{"id":"https://openalex.org/W2038002297","doi":"https://doi.org/10.1145/1531914.1531922","title":"Linked latent Dirichlet allocation in web spam filtering","display_name":"Linked latent Dirichlet allocation in web spam filtering","publication_year":2009,"publication_date":"2009-04-21","ids":{"openalex":"https://openalex.org/W2038002297","doi":"https://doi.org/10.1145/1531914.1531922","mag":"2038002297"},"language":"en","primary_location":{"id":"doi:10.1145/1531914.1531922","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1531914.1531922","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 5th 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/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":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/A5040113859","display_name":"D\u00e1vid Sikl\u00f3si","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":"D\u00e1vid Sikl\u00f3si","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/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":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/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":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":4,"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":17.819,"has_fulltext":false,"cited_by_count":72,"citation_normalized_percentile":{"value":0.98961187,"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":"37","last_page":"40"},"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":0.9991000294685364,"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":0.9987999796867371,"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":0.9566808938980103},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7820917367935181},{"id":"https://openalex.org/keywords/topic-model","display_name":"Topic model","score":0.6206157803535461},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5764238834381104},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.5686700940132141},{"id":"https://openalex.org/keywords/document-classification","display_name":"Document classification","score":0.5388647317886353},{"id":"https://openalex.org/keywords/probabilistic-latent-semantic-analysis","display_name":"Probabilistic latent semantic analysis","score":0.44727426767349243},{"id":"https://openalex.org/keywords/latent-semantic-analysis","display_name":"Latent semantic analysis","score":0.44484126567840576},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3751145601272583},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3516180217266083}],"concepts":[{"id":"https://openalex.org/C500882744","wikidata":"https://www.wikidata.org/wiki/Q269236","display_name":"Latent Dirichlet allocation","level":3,"score":0.9566808938980103},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7820917367935181},{"id":"https://openalex.org/C171686336","wikidata":"https://www.wikidata.org/wiki/Q3532085","display_name":"Topic model","level":2,"score":0.6206157803535461},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5764238834381104},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5686700940132141},{"id":"https://openalex.org/C2780479914","wikidata":"https://www.wikidata.org/wiki/Q302088","display_name":"Document classification","level":2,"score":0.5388647317886353},{"id":"https://openalex.org/C112933361","wikidata":"https://www.wikidata.org/wiki/Q2845258","display_name":"Probabilistic latent semantic analysis","level":2,"score":0.44727426767349243},{"id":"https://openalex.org/C170133592","wikidata":"https://www.wikidata.org/wiki/Q1806883","display_name":"Latent semantic analysis","level":2,"score":0.44484126567840576},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3751145601272583},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3516180217266083}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/1531914.1531922","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1531914.1531922","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 5th International Workshop on Adversarial Information Retrieval on the Web","raw_type":"proceedings-article"},{"id":"pmh:oai:eprints.sztaki.hu:5978","is_oa":false,"landing_page_url":"http://eprints.sztaki.hu/5978/","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":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W23149702","https://openalex.org/W1510348581","https://openalex.org/W1534979469","https://openalex.org/W1570448133","https://openalex.org/W1880262756","https://openalex.org/W1967825155","https://openalex.org/W1979870225","https://openalex.org/W1987365175","https://openalex.org/W2001082470","https://openalex.org/W2038002297","https://openalex.org/W2064153289","https://openalex.org/W2066055909","https://openalex.org/W2066546027","https://openalex.org/W2104290684","https://openalex.org/W2108346334","https://openalex.org/W2110591510","https://openalex.org/W2118670840","https://openalex.org/W2128272588","https://openalex.org/W2130196635","https://openalex.org/W2134731454","https://openalex.org/W2138323616","https://openalex.org/W2145677303","https://openalex.org/W2147152072","https://openalex.org/W2165636119","https://openalex.org/W2169270715","https://openalex.org/W2184575469","https://openalex.org/W2303394219","https://openalex.org/W2966207845","https://openalex.org/W2999905431","https://openalex.org/W4231510805","https://openalex.org/W6639619044"],"related_works":["https://openalex.org/W2921491680","https://openalex.org/W1551384396","https://openalex.org/W2251863249","https://openalex.org/W4291700620","https://openalex.org/W2132052677","https://openalex.org/W3159709618","https://openalex.org/W4396666968","https://openalex.org/W2110027950","https://openalex.org/W2995939990","https://openalex.org/W2726875075"],"abstract_inverted_index":{"Latent":[0],"Dirichlet":[1],"allocation":[2],"(LDA)":[3],"(Blei,":[4],"Ng,":[5],"Jordan":[6],"2003)":[7],"is":[8],"a":[9,21,54,128,141],"fully":[10],"generative":[11],"statistical":[12],"language":[13],"model":[14,71],"on":[15,89],"the":[16,57,62,65,90,100,116,152],"content":[17,136],"and":[18,113,135],"topics":[19,47],"of":[20,23,32,99,102,124,132],"corpus":[22],"documents.":[24],"In":[25],"this":[26,125],"paper":[27],"we":[28,104],"apply":[29],"an":[30],"extension":[31],"LDA":[33,40,70,88,110],"for":[34,75],"web":[35],"spam":[36],"classification.":[37],"Our":[38,146],"linked":[39,58,87],"technique":[41],"takes":[42],"also":[43],"linkage":[44],"into":[45],"account:":[46],"are":[48],"propagated":[49],"along":[50],"links":[51],"in":[52,64,97,140,144],"such":[53],"way":[55],"that":[56],"document":[59],"directly":[60],"influences":[61],"words":[63],"linking":[66],"document.":[67],"The":[68,122],"inferred":[69],"can":[72],"be":[73],"applied":[74],"classification":[76],"as":[77],"dimensionality":[78],"reduction":[79],"similarly":[80],"to":[81,127],"latent":[82],"semantic":[83],"indexing.":[84],"We":[85],"test":[86],"WEBSPAM-UK2007":[91],"corpus.":[92],"By":[93],"using":[94],"BayesNet":[95],"classifier,":[96],"terms":[98],"AUC":[101],"classification,":[103],"achieve":[105],"3%":[106,142],"improvement":[107,143],"over":[108,115,151],"plain":[109],"with":[111,120],"BayesNet,":[112],"8%":[114],"public":[117],"link":[118,134],"features":[119],"C4.5.":[121],"addition":[123],"method":[126,147],"log-odds":[129],"based":[130],"combination":[131],"strong":[133],"baseline":[137],"classifiers":[138],"results":[139],"AUC.":[145],"even":[148],"slightly":[149],"improves":[150],"best":[153],"Web":[154],"Spam":[155],"Challenge":[156],"2008":[157],"result.":[158]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":8},{"year":2015,"cited_by_count":9},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":8},{"year":2012,"cited_by_count":7}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}