{"id":"https://openalex.org/W2079799661","doi":"https://doi.org/10.1145/1244408.1244424","title":"Web spam detection via commercial intent analysis","display_name":"Web spam detection via commercial intent analysis","publication_year":2007,"publication_date":"2007-05-08","ids":{"openalex":"https://openalex.org/W2079799661","doi":"https://doi.org/10.1145/1244408.1244424","mag":"2079799661"},"language":"en","primary_location":{"id":"doi:10.1145/1244408.1244424","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1244408.1244424","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 3rd 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/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":true,"raw_author_name":"Andr\u00e1s 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"]}]},{"author_position":"middle","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":false,"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/A5015372725","display_name":"K\u00e1roly Csalog\u00e1ny","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":"K\u00e1roly Csalog\u00e1ny","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/A5082122135","display_name":"Tam\u00e1s Sarl\u00f3s","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":"Tam\u00e1s Sarl\u00f3s","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/A5021452458"],"corresponding_institution_ids":["https://openalex.org/I4210117195","https://openalex.org/I7597260"],"apc_list":null,"apc_paid":null,"fwci":9.1114,"has_fulltext":false,"cited_by_count":33,"citation_normalized_percentile":{"value":0.97395893,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"89","last_page":"92"},"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9993000030517578,"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":0.9983000159263611,"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":0.7746368646621704},{"id":"https://openalex.org/keywords/spamdexing","display_name":"Spamdexing","score":0.5750702619552612},{"id":"https://openalex.org/keywords/search-engine","display_name":"Search engine","score":0.5553052425384521},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5416969656944275},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.5249826312065125},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.5052459836006165},{"id":"https://openalex.org/keywords/volume","display_name":"Volume (thermodynamics)","score":0.42713066935539246},{"id":"https://openalex.org/keywords/the-internet","display_name":"The Internet","score":0.41149234771728516},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3355732560157776},{"id":"https://openalex.org/keywords/web-search-engine","display_name":"Web search engine","score":0.2762916088104248},{"id":"https://openalex.org/keywords/web-search-query","display_name":"Web search query","score":0.26065075397491455}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7746368646621704},{"id":"https://openalex.org/C13565553","wikidata":"https://www.wikidata.org/wiki/Q804206","display_name":"Spamdexing","level":5,"score":0.5750702619552612},{"id":"https://openalex.org/C97854310","wikidata":"https://www.wikidata.org/wiki/Q19541","display_name":"Search engine","level":2,"score":0.5553052425384521},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5416969656944275},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.5249826312065125},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.5052459836006165},{"id":"https://openalex.org/C20556612","wikidata":"https://www.wikidata.org/wiki/Q4469374","display_name":"Volume (thermodynamics)","level":2,"score":0.42713066935539246},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.41149234771728516},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3355732560157776},{"id":"https://openalex.org/C521815418","wikidata":"https://www.wikidata.org/wiki/Q4182287","display_name":"Web search engine","level":4,"score":0.2762916088104248},{"id":"https://openalex.org/C164120249","wikidata":"https://www.wikidata.org/wiki/Q995982","display_name":"Web search query","level":3,"score":0.26065075397491455},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/1244408.1244424","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1244408.1244424","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 3rd international workshop on Adversarial information retrieval on the web","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.89.2612","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.89.2612","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://airweb.cse.lehigh.edu/2007/papers/paper_109.pdf","raw_type":"text"},{"id":"pmh:oai:eprints.sztaki.hu:5060","is_oa":false,"landing_page_url":"http://eprints.sztaki.hu/5060/","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W20238101","https://openalex.org/W189202421","https://openalex.org/W202878612","https://openalex.org/W1570448133","https://openalex.org/W1845137714","https://openalex.org/W1967825155","https://openalex.org/W1987365175","https://openalex.org/W2009408190","https://openalex.org/W2066055909","https://openalex.org/W2073562093","https://openalex.org/W2112400959","https://openalex.org/W2113455164","https://openalex.org/W2120926619","https://openalex.org/W2130196635","https://openalex.org/W2130854091","https://openalex.org/W2131746181","https://openalex.org/W2156037541","https://openalex.org/W2169263924","https://openalex.org/W2169270715","https://openalex.org/W2966207845","https://openalex.org/W6607569353","https://openalex.org/W7048191986"],"related_works":["https://openalex.org/W2368945903","https://openalex.org/W4255972148","https://openalex.org/W2062919806","https://openalex.org/W2922524414","https://openalex.org/W3437724","https://openalex.org/W4312784821","https://openalex.org/W2222022498","https://openalex.org/W2280900438","https://openalex.org/W2227686825","https://openalex.org/W2078337952"],"abstract_inverted_index":{"We":[0,48,99],"propose":[1],"a":[2,67,114],"number":[3],"of":[4,14,19,55,77,93,117,121,132],"features":[5,27,127,137],"for":[6],"Web":[7,78,122],"spam":[8,52,123],"filtering":[9,53],"based":[10,89],"on":[11,90,96,103],"the":[12,51,56,73,91,97,104,119,129,133],"occurrence":[13,92],"keywords":[15],"that":[16],"are":[17],"either":[18,81],"high":[20,39],"advertisement":[21],"value":[22,61],"or":[23,41,83],"highly":[24],"spammed.":[25],"Our":[26,126],"include":[28],"popular":[29],"words":[30,43],"from":[31],"search":[32],"engine":[33],"query":[34],"logs":[35],"as":[36,38,80,85,87,113],"well":[37,86],"cost":[40],"volume":[42],"according":[44],"to":[45,63],"Google":[46,94],"AdWords.":[47],"also":[49],"demonstrate":[50],"power":[54],"Online":[57],"Commercial":[58],"Intention":[59],"(OCI)":[60],"assigned":[62],"an":[64],"URL":[65],"in":[66],"Microsoft":[68],"adCenter":[69],"Labs":[70],"Demonstration":[71],"and":[72],"Yahoo!":[74],"Mindset":[75],"classification":[76,130],"pages":[79],"commercial":[82],"non-commercial":[84],"metrics":[88],"ads":[95],"page.":[98],"run":[100],"our":[101],"tests":[102],"WEBSPAM-UK2006":[105,136],"dataset":[106],"recently":[107],"compiled":[108],"by":[109,138],"Castillo":[110],"et":[111],"al.":[112],"standard":[115],"means":[116],"measuring":[118],"performance":[120],"detection":[124],"algorithms.":[125],"improve":[128],"accuracy":[131],"publicly":[134],"available":[135],"3%.":[139]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":5},{"year":2012,"cited_by_count":3}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}