{"id":"https://openalex.org/W2164517760","doi":"https://doi.org/10.1145/2487788.2488139","title":"Cross-lingual web spam classification","display_name":"Cross-lingual web spam classification","publication_year":2013,"publication_date":"2013-05-13","ids":{"openalex":"https://openalex.org/W2164517760","doi":"https://doi.org/10.1145/2487788.2488139","mag":"2164517760"},"language":"en","primary_location":{"id":"doi:10.1145/2487788.2488139","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2487788.2488139","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 22nd International Conference on World Wide 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/A5056644592","display_name":"Andr\u00e1s Garz\u00f3","orcid":null},"institutions":[{"id":"https://openalex.org/I106118109","display_name":"E\u00f6tv\u00f6s Lor\u00e1nd University","ror":"https://ror.org/01jsq2704","country_code":"HU","type":"education","lineage":["https://openalex.org/I106118109"]},{"id":"https://openalex.org/I4210117195","display_name":"HUN-REN Institute for Computer Science and Control","ror":"https://ror.org/0249v7n71","country_code":"HU","type":"facility","lineage":["https://openalex.org/I4210117195","https://openalex.org/I4387152226"]},{"id":"https://openalex.org/I7597260","display_name":"Hungarian Academy of Sciences","ror":"https://ror.org/02ks8qq67","country_code":"HU","type":"government","lineage":["https://openalex.org/I7597260"]}],"countries":["HU"],"is_corresponding":false,"raw_author_name":"Andr\u00e1s Garz\u00f3","raw_affiliation_strings":["Institute for Computer Science and Control, Hungarian Academy of Sciences (MTA SZTAKI), E\u00f6tv\u00f6s University, Budapest, Hungary"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Computer Science and Control, Hungarian Academy of Sciences (MTA SZTAKI), E\u00f6tv\u00f6s University, Budapest, Hungary","institution_ids":["https://openalex.org/I4210117195","https://openalex.org/I7597260","https://openalex.org/I106118109"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046405655","display_name":"B\u00e1lint Dar\u00f3czy","orcid":"https://orcid.org/0000-0001-6233-3490"},"institutions":[{"id":"https://openalex.org/I106118109","display_name":"E\u00f6tv\u00f6s Lor\u00e1nd University","ror":"https://ror.org/01jsq2704","country_code":"HU","type":"education","lineage":["https://openalex.org/I106118109"]},{"id":"https://openalex.org/I4210117195","display_name":"HUN-REN Institute for Computer Science and Control","ror":"https://ror.org/0249v7n71","country_code":"HU","type":"facility","lineage":["https://openalex.org/I4210117195","https://openalex.org/I4387152226"]},{"id":"https://openalex.org/I7597260","display_name":"Hungarian Academy of Sciences","ror":"https://ror.org/02ks8qq67","country_code":"HU","type":"government","lineage":["https://openalex.org/I7597260"]}],"countries":["HU"],"is_corresponding":false,"raw_author_name":"B\u00e1lint Dar\u00f3czy","raw_affiliation_strings":["Institute for Computer Science and Control, Hungarian Academy of Sciences (MTA SZTAKI), E\u00f6tv\u00f6s University, Budapest, Hungary"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Computer Science and Control, Hungarian Academy of Sciences (MTA SZTAKI), E\u00f6tv\u00f6s University, Budapest, Hungary","institution_ids":["https://openalex.org/I4210117195","https://openalex.org/I7597260","https://openalex.org/I106118109"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103207848","display_name":"Tam\u00e1s Kiss","orcid":"https://orcid.org/0000-0001-6360-0714"},"institutions":[{"id":"https://openalex.org/I106118109","display_name":"E\u00f6tv\u00f6s Lor\u00e1nd University","ror":"https://ror.org/01jsq2704","country_code":"HU","type":"education","lineage":["https://openalex.org/I106118109"]},{"id":"https://openalex.org/I4210117195","display_name":"HUN-REN Institute for Computer Science and Control","ror":"https://ror.org/0249v7n71","country_code":"HU","type":"facility","lineage":["https://openalex.org/I4210117195","https://openalex.org/I4387152226"]},{"id":"https://openalex.org/I7597260","display_name":"Hungarian Academy of Sciences","ror":"https://ror.org/02ks8qq67","country_code":"HU","type":"government","lineage":["https://openalex.org/I7597260"]}],"countries":["HU"],"is_corresponding":false,"raw_author_name":"Tam\u00e1s Kiss","raw_affiliation_strings":["Institute for Computer Science and Control, Hungarian Academy of Sciences (MTA SZTAKI), E\u00f6tv\u00f6s University, Budapest, Hungary"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Computer Science and Control, Hungarian Academy of Sciences (MTA SZTAKI), E\u00f6tv\u00f6s University, Budapest, Hungary","institution_ids":["https://openalex.org/I4210117195","https://openalex.org/I7597260","https://openalex.org/I106118109"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040113859","display_name":"D\u00e1vid Sikl\u00f3si","orcid":null},"institutions":[{"id":"https://openalex.org/I106118109","display_name":"E\u00f6tv\u00f6s Lor\u00e1nd University","ror":"https://ror.org/01jsq2704","country_code":"HU","type":"education","lineage":["https://openalex.org/I106118109"]},{"id":"https://openalex.org/I4210117195","display_name":"HUN-REN Institute for Computer Science and Control","ror":"https://ror.org/0249v7n71","country_code":"HU","type":"facility","lineage":["https://openalex.org/I4210117195","https://openalex.org/I4387152226"]},{"id":"https://openalex.org/I7597260","display_name":"Hungarian Academy of Sciences","ror":"https://ror.org/02ks8qq67","country_code":"HU","type":"government","lineage":["https://openalex.org/I7597260"]}],"countries":["HU"],"is_corresponding":false,"raw_author_name":"D\u00e1vid Sikl\u00f3si","raw_affiliation_strings":["Institute for Computer Science and Control, Hungarian Academy of Sciences (MTA SZTAKI), E\u00f6tv\u00f6s University, Budapest, Hungary"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Computer Science and Control, Hungarian Academy of Sciences (MTA SZTAKI), E\u00f6tv\u00f6s University, Budapest, Hungary","institution_ids":["https://openalex.org/I4210117195","https://openalex.org/I7597260","https://openalex.org/I106118109"]}]},{"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/I106118109","display_name":"E\u00f6tv\u00f6s Lor\u00e1nd University","ror":"https://ror.org/01jsq2704","country_code":"HU","type":"education","lineage":["https://openalex.org/I106118109"]},{"id":"https://openalex.org/I4210117195","display_name":"HUN-REN Institute for Computer Science and Control","ror":"https://ror.org/0249v7n71","country_code":"HU","type":"facility","lineage":["https://openalex.org/I4210117195","https://openalex.org/I4387152226"]},{"id":"https://openalex.org/I7597260","display_name":"Hungarian Academy of Sciences","ror":"https://ror.org/02ks8qq67","country_code":"HU","type":"government","lineage":["https://openalex.org/I7597260"]}],"countries":["HU"],"is_corresponding":false,"raw_author_name":"Andr\u00e1s A. Bencz\u00far","raw_affiliation_strings":["Institute for Computer Science and Control, Hungarian Academy of Sciences (MTA SZTAKI), E\u00f6tv\u00f6s University, Budapest, Hungary"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Computer Science and Control, Hungarian Academy of Sciences (MTA SZTAKI), E\u00f6tv\u00f6s University, Budapest, Hungary","institution_ids":["https://openalex.org/I4210117195","https://openalex.org/I7597260","https://openalex.org/I106118109"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.316,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.93512158,"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":"1149","last_page":"1156"},"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9983999729156494,"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/T12380","display_name":"Authorship Attribution and Profiling","score":0.9980999827384949,"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/computer-science","display_name":"Computer science","score":0.8528525829315186},{"id":"https://openalex.org/keywords/portuguese","display_name":"Portuguese","score":0.7194527387619019},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6291006207466125},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5586625337600708},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.5247963666915894},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.503009021282196},{"id":"https://openalex.org/keywords/web-application","display_name":"Web application","score":0.4522278606891632},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.4513794183731079},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.44117167592048645},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.4269372224807739},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.42573556303977966},{"id":"https://openalex.org/keywords/simple","display_name":"Simple (philosophy)","score":0.42569828033447266},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3991404175758362},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.17097598314285278}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8528525829315186},{"id":"https://openalex.org/C35219183","wikidata":"https://www.wikidata.org/wiki/Q5146","display_name":"Portuguese","level":2,"score":0.7194527387619019},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6291006207466125},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5586625337600708},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.5247963666915894},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.503009021282196},{"id":"https://openalex.org/C118643609","wikidata":"https://www.wikidata.org/wiki/Q189210","display_name":"Web application","level":2,"score":0.4522278606891632},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.4513794183731079},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.44117167592048645},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4269372224807739},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.42573556303977966},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.42569828033447266},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3991404175758362},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.17097598314285278},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/2487788.2488139","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2487788.2488139","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 22nd International Conference on World Wide Web","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.360.303","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.360.303","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.dl.kuis.kyoto-u.ac.jp/webquality2013/p1149.pdf","raw_type":"text"},{"id":"pmh:oai:eprints.sztaki.hu:7656","is_oa":false,"landing_page_url":"http://eprints.sztaki.hu/7656/","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":[{"score":0.7099999785423279,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320321994","display_name":"Hungarian Scientific Research Fund","ror":"https://ror.org/00v349e63"},{"id":"https://openalex.org/F4320322192","display_name":"Magyar Tudom\u00e1nyos Akad\u00e9mia","ror":"https://ror.org/02ks8qq67"},{"id":"https://openalex.org/F4320328860","display_name":"Magyarorsz\u00e1g Korm\u00e1nya","ror":"https://ror.org/007ekx298"},{"id":"https://openalex.org/F4320338080","display_name":"European Social Fund","ror":"https://ror.org/00k4n6c32"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":54,"referenced_works":["https://openalex.org/W23149702","https://openalex.org/W50119190","https://openalex.org/W85972746","https://openalex.org/W202878612","https://openalex.org/W245306944","https://openalex.org/W1489959797","https://openalex.org/W1527227399","https://openalex.org/W1534276167","https://openalex.org/W1570448133","https://openalex.org/W1571373268","https://openalex.org/W1585529040","https://openalex.org/W1594833364","https://openalex.org/W1685426458","https://openalex.org/W1845137714","https://openalex.org/W1860880244","https://openalex.org/W1952841266","https://openalex.org/W1967825155","https://openalex.org/W1979870225","https://openalex.org/W1987365175","https://openalex.org/W1994966918","https://openalex.org/W1999391954","https://openalex.org/W2009408190","https://openalex.org/W2048679005","https://openalex.org/W2066055909","https://openalex.org/W2071018795","https://openalex.org/W2071399839","https://openalex.org/W2073562093","https://openalex.org/W2090502034","https://openalex.org/W2097089247","https://openalex.org/W2097411811","https://openalex.org/W2099031744","https://openalex.org/W2101005742","https://openalex.org/W2104290684","https://openalex.org/W2118942057","https://openalex.org/W2128184786","https://openalex.org/W2128272588","https://openalex.org/W2130196635","https://openalex.org/W2136504847","https://openalex.org/W2145800633","https://openalex.org/W2148861942","https://openalex.org/W2153635508","https://openalex.org/W2161453060","https://openalex.org/W2167660864","https://openalex.org/W2169270715","https://openalex.org/W2171068337","https://openalex.org/W2397651480","https://openalex.org/W2626710409","https://openalex.org/W2915906546","https://openalex.org/W2966207845","https://openalex.org/W4236002984","https://openalex.org/W4285719527","https://openalex.org/W6641027487","https://openalex.org/W6644910505","https://openalex.org/W6680140577"],"related_works":["https://openalex.org/W2912615426","https://openalex.org/W1964944391","https://openalex.org/W2104166387","https://openalex.org/W4299785812","https://openalex.org/W4391101703","https://openalex.org/W563704311","https://openalex.org/W4322721676","https://openalex.org/W2972060578","https://openalex.org/W4285877427","https://openalex.org/W783305165"],"abstract_inverted_index":{"While":[0],"Web":[1,21,80,117],"spam":[2],"training":[3,106],"data":[4],"exists":[5],"in":[6,23,70],"English,":[7],"we":[8,16,30,60,73,123],"face":[9],"an":[10,86],"expensive":[11],"human":[12],"labeling":[13],"procedure":[14,72],"if":[15],"want":[17],"to":[18],"filter":[19],"a":[20,24,110],"domain":[22],"different":[25],"language.":[26],"In":[27,58],"this":[28,71],"paper":[29],"overview":[31],"how":[32,41,52],"existing":[33],"content":[34,132],"and":[35,51,54,69,109,126,133,140],"link":[36,134],"based":[37,135],"classification":[38],"techniques":[39],"work,":[40],"models":[42],"can":[43],"be":[44],"\"translated\"":[45],"from":[46],"English":[47,87,107],"into":[48],"another":[49],"language,":[50],"language-dependent":[53],"independent":[55],"methods":[56],"combine.":[57],"particular":[59],"show":[61],"that":[62,84],"simple":[63],"bag-of-words":[64],"translation":[65,88],"works":[66],"very":[67],"well":[68],"may":[74],"also":[75],"rely":[76],"on":[77,100],"mixed":[78],"language":[79,94],"hosts,":[81],"i.e.":[82],"those":[83],"contain":[85],"of":[89,91,114,129],"part":[90],"the":[92,101,105,115,141],"local":[93],"text.":[95],"Our":[96],"experiments":[97],"are":[98],"conducted":[99],"ClueWeb09":[102,139],"corpus":[103],"as":[104],"collection":[108],"large":[111],"Portuguese":[112,116,142],"crawl":[113],"Archive.":[118],"To":[119],"foster":[120],"further":[121],"research,":[122],"provide":[124],"labels":[125],"precomputed":[127],"values":[128],"term":[130],"frequencies,":[131],"features":[136],"for":[137],"both":[138],"data.":[143]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":3},{"year":2013,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}