{"id":"https://openalex.org/W2169470206","doi":null,"title":"Tracking Web Spam with Hidden Style Similarity","display_name":"Tracking Web Spam with Hidden Style Similarity","publication_year":2006,"publication_date":"2006-01-01","ids":{"openalex":"https://openalex.org/W2169470206","mag":"2169470206"},"language":"en","primary_location":{"id":"pmh:oai:CiteSeerX.psu:10.1.1.61.7462","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.61.7462","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/2006/urvoy.pdf","raw_type":"text"},"volume":null,"type":"article","is_traditional":true,"indexed_in":[],"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":"https://orcid.org/0009-0006-8881-1976","observed_orcids":["https://orcid.org/0009-0006-8881-1976"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tanguy Urvoy","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Thomas Lavergne","orcid":"https://orcid.org/0000-0002-9498-4551","observed_orcids":["https://orcid.org/0000-0002-9498-4551"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Thomas Lavergne","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-9498-4551","affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5055246011","display_name":"Pascal Filoche","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pascal Filoche","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":9.9311,"has_fulltext":false,"cited_by_count":44,"citation_normalized_percentile":{"value":0.97633693,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":93,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"25","last_page":"31"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11644","display_name":"Spam and Phishing Detection","score":0.9922000169754028,"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":0.9922000169754028,"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/T12380","display_name":"Authorship Attribution and Profiling","score":0.0020000000949949026,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.0019000000320374966,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/web-spam","display_name":"web spam","score":0.9210000038146973},{"id":"https://openalex.org/keywords/style-similarity","display_name":"style similarity","score":0.5559999942779541},{"id":"https://openalex.org/keywords/stylometry","display_name":"stylometry","score":0.8970000147819519},{"id":"https://openalex.org/keywords/look-and-feel","display_name":"look and feel","score":0.5170000195503235},{"id":"https://openalex.org/keywords/spam-detection","display_name":"spam detection","score":0.38499999046325684}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8141522407531738},{"id":"https://openalex.org/C13743948","wikidata":"https://www.wikidata.org/wiki/Q45842","display_name":"Web crawler","level":2,"score":0.7723566293716431},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6091132164001465},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5402090549468994},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.5336030125617981},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.5149279832839966},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.514032244682312},{"id":"https://openalex.org/C46721378","wikidata":"https://www.wikidata.org/wiki/Q221989","display_name":"Deep Web","level":3,"score":0.42353859543800354},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3392254114151001},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.21703320741653442},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.09893348813056946}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:CiteSeerX.psu:10.1.1.61.7462","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.61.7462","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/2006/urvoy.pdf","raw_type":"text"},{"id":"mag:2169470206","doi":null,"is_oa":false,"landing_page_url":"http://airweb.cse.lehigh.edu/2006/urvoy.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306417632","display_name":"Adversarial Information Retrieval on the Web","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"Adversarial Information Retrieval on the Web","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W126536057","https://openalex.org/W140890161","https://openalex.org/W1845137714","https://openalex.org/W1965657003","https://openalex.org/W1987365175","https://openalex.org/W2128272588","https://openalex.org/W2132069633","https://openalex.org/W2144270983","https://openalex.org/W2146888100","https://openalex.org/W2147717514","https://openalex.org/W2152565070","https://openalex.org/W2169270715","https://openalex.org/W2949696181"],"related_works":["https://openalex.org/W2053377618","https://openalex.org/W6930400174","https://openalex.org/W2082769365","https://openalex.org/W1520253427","https://openalex.org/W7025539898","https://openalex.org/W2374283646","https://openalex.org/W48167437","https://openalex.org/W2028900141","https://openalex.org/W1997805268","https://openalex.org/W2128272588"],"abstract_inverted_index":{"Automatically":[0],"generated":[1],"content":[2],"is":[3,64,74],"ubiquitous":[4],"in":[5],"the":[6,12,50],"web:":[7],"dynamic":[8],"sites":[9,24],"built":[10,48],"using":[11,49],"three-tier":[13],"paradigm":[14],"are":[15],"good":[16],"examples":[17],"(e.g.":[18,38],"commercial":[19],"sites,":[20],"blogs":[21],"and":[22,61],"other":[23],"powered":[25],"by":[26,68],"a":[27,58],"web":[28],"authoring":[29],"software),":[30],"as":[31,33],"well":[32],"less":[34],"legitimous":[35],"spamdexing":[36],"attempts":[37],"link":[39],"farms,":[40],"faked":[41],"directories.":[42],".":[43,44],").":[45],"Those":[46],"pages":[47],"same":[51],"generating":[52],"method":[53],"(template":[54],"or":[55],"script)":[56],"share":[57],"common":[59,69],"\"look":[60],"feel\"":[62],"that":[63],"not":[65],"easily":[66],"detected":[67],"text":[70],"classification":[71],"methods,":[72],"but":[73],"more":[75],"related":[76],"to":[77],"stylometry.":[78]},"counts_by_year":[{"year":2020,"cited_by_count":2},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":2},{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":4}],"updated_date":"2026-11-08T12:12:28.789561","created_date":"2016-06-24T00:00:00"}
