{"id":"https://openalex.org/W2053377618","doi":"https://doi.org/10.1145/1326561.1326564","title":"Tracking Web spam with HTML style similarities","display_name":"Tracking Web spam with HTML style similarities","publication_year":2008,"publication_date":"2008-02-01","ids":{"openalex":"https://openalex.org/W2053377618","doi":"https://doi.org/10.1145/1326561.1326564","mag":"2053377618"},"language":"en","primary_location":{"id":"doi:10.1145/1326561.1326564","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1326561.1326564","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/A5029181942","display_name":"Tanguy Urvoy","orcid":null},"institutions":[{"id":"https://openalex.org/I19370010","display_name":"Orange (France)","ror":"https://ror.org/035j0tq82","country_code":"FR","type":"company","lineage":["https://openalex.org/I19370010"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Tanguy Urvoy","raw_affiliation_strings":["Orange Labs (France Telecom R&amp;D), Lannion cedex, France"],"affiliations":[{"raw_affiliation_string":"Orange Labs (France Telecom R&amp;D), Lannion cedex, France","institution_ids":["https://openalex.org/I19370010"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034194449","display_name":"Emmanuel Chauveau","orcid":null},"institutions":[{"id":"https://openalex.org/I19370010","display_name":"Orange (France)","ror":"https://ror.org/035j0tq82","country_code":"FR","type":"company","lineage":["https://openalex.org/I19370010"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Emmanuel Chauveau","raw_affiliation_strings":["Orange Labs (France Telecom R&amp;D), Lannion cedex, France"],"affiliations":[{"raw_affiliation_string":"Orange Labs (France Telecom R&amp;D), Lannion cedex, France","institution_ids":["https://openalex.org/I19370010"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055246011","display_name":"Pascal Filoche","orcid":null},"institutions":[{"id":"https://openalex.org/I19370010","display_name":"Orange (France)","ror":"https://ror.org/035j0tq82","country_code":"FR","type":"company","lineage":["https://openalex.org/I19370010"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Pascal Filoche","raw_affiliation_strings":["Orange Labs (France Telecom R&amp;D), Lannion cedex, France"],"affiliations":[{"raw_affiliation_string":"Orange Labs (France Telecom R&amp;D), Lannion cedex, France","institution_ids":["https://openalex.org/I19370010"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100774746","display_name":"Thomas Lavergne","orcid":"https://orcid.org/0000-0002-9498-4551"},"institutions":[{"id":"https://openalex.org/I19370010","display_name":"Orange (France)","ror":"https://ror.org/035j0tq82","country_code":"FR","type":"company","lineage":["https://openalex.org/I19370010"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Thomas Lavergne","raw_affiliation_strings":["Orange Labs and ENST Paris, Lannion cedex, France"],"affiliations":[{"raw_affiliation_string":"Orange Labs and ENST Paris, Lannion cedex, France","institution_ids":["https://openalex.org/I19370010"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5029181942"],"corresponding_institution_ids":["https://openalex.org/I19370010"],"apc_list":null,"apc_paid":null,"fwci":18.3704,"has_fulltext":false,"cited_by_count":87,"citation_normalized_percentile":{"value":0.9899556,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"2","issue":"1","first_page":"1","last_page":"28"},"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9994999766349792,"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/T11241","display_name":"Advanced Malware Detection Techniques","score":0.9976000189781189,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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":0.882657527923584},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6160932779312134},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.5399165153503418},{"id":"https://openalex.org/keywords/locality-sensitive-hashing","display_name":"Locality-sensitive hashing","score":0.5187475681304932},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5098225474357605},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.4602768123149872},{"id":"https://openalex.org/keywords/hash-function","display_name":"Hash function","score":0.44926708936691284},{"id":"https://openalex.org/keywords/html-element","display_name":"HTML element","score":0.44788262248039246},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2688775062561035},{"id":"https://openalex.org/keywords/hash-table","display_name":"Hash table","score":0.2251850962638855},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.13789314031600952},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.08882716298103333}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.882657527923584},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6160932779312134},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.5399165153503418},{"id":"https://openalex.org/C74270461","wikidata":"https://www.wikidata.org/wiki/Q1625299","display_name":"Locality-sensitive hashing","level":4,"score":0.5187475681304932},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5098225474357605},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.4602768123149872},{"id":"https://openalex.org/C99138194","wikidata":"https://www.wikidata.org/wiki/Q183427","display_name":"Hash function","level":2,"score":0.44926708936691284},{"id":"https://openalex.org/C81639021","wikidata":"https://www.wikidata.org/wiki/Q179551","display_name":"HTML element","level":3,"score":0.44788262248039246},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2688775062561035},{"id":"https://openalex.org/C67388219","wikidata":"https://www.wikidata.org/wiki/Q207440","display_name":"Hash table","level":3,"score":0.2251850962638855},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.13789314031600952},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.08882716298103333}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/1326561.1326564","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1326561.1326564","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:10.1.1.527.163","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.527.163","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://oniros.org/papers/urvoy2008acmtweb.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.87.5468","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.87.5468","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://research.microsoft.com/users/najork/tsi/htmlstyle.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.550000011920929}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W126536057","https://openalex.org/W140890161","https://openalex.org/W1609518033","https://openalex.org/W1845137714","https://openalex.org/W1965657003","https://openalex.org/W1987365175","https://openalex.org/W2001592424","https://openalex.org/W2012833704","https://openalex.org/W2040075907","https://openalex.org/W2066055909","https://openalex.org/W2073562093","https://openalex.org/W2085922539","https://openalex.org/W2086017131","https://openalex.org/W2101909884","https://openalex.org/W2111295912","https://openalex.org/W2128272588","https://openalex.org/W2130196635","https://openalex.org/W2130854091","https://openalex.org/W2132069633","https://openalex.org/W2144270983","https://openalex.org/W2147717514","https://openalex.org/W2148781362","https://openalex.org/W2152565070","https://openalex.org/W2169270715","https://openalex.org/W2169470206","https://openalex.org/W4255954986"],"related_works":["https://openalex.org/W2000601968","https://openalex.org/W2144265691","https://openalex.org/W2033383639","https://openalex.org/W3108918257","https://openalex.org/W3016124764","https://openalex.org/W1656419755","https://openalex.org/W1539890081","https://openalex.org/W4302086745","https://openalex.org/W2373402338","https://openalex.org/W2114620981"],"abstract_inverted_index":{"Automatically":[0],"generated":[1],"content":[2],"is":[3,60,70,119],"ubiquitous":[4],"in":[5,94],"the":[6,12,46,116,137,148,161],"web:":[7],"dynamic":[8],"sites":[9,24],"built":[10,44],"using":[11,26,45],"three-tier":[13],"paradigm":[14],"are":[15],"good":[16],"examples":[17],"(e.g.,":[18,37],"commercial":[19],"sites,":[20],"blogs":[21],"and":[22,57,80,91,146],"other":[23],"edited":[25],"web":[27],"authoring":[28],"software),":[29],"as":[30,32],"well":[31],"less":[33],"legitimate":[34],"spamdexing":[35],"attempts":[36],"link":[38],"farms,":[39],"faked":[40],"directories).":[41],"Those":[42],"pages":[43,145],"same":[47],"generating":[48],"method":[49],"(template":[50],"or":[51],"script)":[52],"share":[53],"a":[54,101,106],"common":[55,65],"\u201clook":[56],"feel\u201d":[58],"that":[59],"not":[61],"easily":[62],"detected":[63],"by":[64],"text":[66],"classification":[67],"methods,":[68],"but":[69],"more":[71],"related":[72],"to":[73,104,112,135,142],"stylometry.":[74],"In":[75],"this":[76,129],"work":[77],"we":[78,126],"study":[79],"compare":[81],"several":[82],"HTML":[83,95,138],"style":[84,139],"similarity":[85,140],"measures":[86],"based":[87,120],"on":[88,121,160],"both":[89],"textual":[90],"extra-textual":[92],"features":[93],"source":[96],"code.":[97],"We":[98,131,153],"also":[99],"propose":[100],"flexible":[102],"algorithm":[103,118,159],"cluster":[105],"large":[107],"collection":[108],"of":[109,150,157],"documents":[110],"according":[111],"these":[113],"measures.":[114],"Since":[115],"proposed":[117],"locality":[122],"sensitive":[123],"hashing":[124],"(LSH),":[125],"first":[127],"review":[128],"technique.":[130],"then":[132],"describe":[133],"how":[134],"use":[136],"clusters":[141],"pinpoint":[143],"dubious":[144],"enhance":[147],"quality":[149],"spam":[151],"classifiers.":[152],"present":[154],"an":[155],"evaluation":[156],"our":[158],"WEBSPAM-UK2006":[162],"dataset.":[163]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":6},{"year":2017,"cited_by_count":6},{"year":2016,"cited_by_count":6},{"year":2015,"cited_by_count":5},{"year":2014,"cited_by_count":11},{"year":2013,"cited_by_count":6},{"year":2012,"cited_by_count":9}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}
