{"id":"https://openalex.org/W2250919057","doi":"https://doi.org/10.1145/2740908.2742127","title":"Identification of Web Spam through Clustering of Website Structures","display_name":"Identification of Web Spam through Clustering of Website Structures","publication_year":2015,"publication_date":"2015-05-18","ids":{"openalex":"https://openalex.org/W2250919057","doi":"https://doi.org/10.1145/2740908.2742127","mag":"2250919057"},"language":"en","primary_location":{"id":"doi:10.1145/2740908.2742127","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2740908.2742127","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 24th International Conference on World Wide Web","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"http://puma.isti.cnr.it/dfdownloadnew.php?ident=cnr.iit/cnr.iit/2015-A2-047","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5033343264","display_name":"Filippo Geraci","orcid":"https://orcid.org/0000-0001-6993-6761"},"institutions":[{"id":"https://openalex.org/I4210130157","display_name":"Institute of Informatics and Telematics","ror":"https://ror.org/02gdcn153","country_code":"IT","type":"facility","lineage":["https://openalex.org/I4210130157","https://openalex.org/I4210155236"]}],"countries":["IT"],"is_corresponding":true,"raw_author_name":"Filippo Geraci","raw_affiliation_strings":["Instituto di Informatica Telematica, CNR, Pisa, Italy"],"affiliations":[{"raw_affiliation_string":"Instituto di Informatica Telematica, CNR, Pisa, Italy","institution_ids":["https://openalex.org/I4210130157"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5033343264"],"corresponding_institution_ids":["https://openalex.org/I4210130157"],"apc_list":null,"apc_paid":null,"fwci":1.6441,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.88896716,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1447","last_page":"1452"},"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":0.9990000128746033,"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":0.998199999332428,"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/spambot","display_name":"Spambot","score":0.6681602001190186},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6378008723258972},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.6316670775413513},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.6011639833450317},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5962919592857361},{"id":"https://openalex.org/keywords/revenue","display_name":"Revenue","score":0.5866525769233704},{"id":"https://openalex.org/keywords/server","display_name":"Server","score":0.5383509397506714},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.5010881423950195},{"id":"https://openalex.org/keywords/forum-spam","display_name":"Forum spam","score":0.49263864755630493},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.47054439783096313},{"id":"https://openalex.org/keywords/internet-privacy","display_name":"Internet privacy","score":0.4640236496925354},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4582158923149109},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.37470489740371704},{"id":"https://openalex.org/keywords/business","display_name":"Business","score":0.33797943592071533},{"id":"https://openalex.org/keywords/spamming","display_name":"Spamming","score":0.2968747913837433},{"id":"https://openalex.org/keywords/the-internet","display_name":"The Internet","score":0.2935207486152649},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.1094900369644165},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09514710307121277}],"concepts":[{"id":"https://openalex.org/C127735637","wikidata":"https://www.wikidata.org/wiki/Q2306702","display_name":"Spambot","level":4,"score":0.6681602001190186},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6378008723258972},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.6316670775413513},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.6011639833450317},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5962919592857361},{"id":"https://openalex.org/C195487862","wikidata":"https://www.wikidata.org/wiki/Q850210","display_name":"Revenue","level":2,"score":0.5866525769233704},{"id":"https://openalex.org/C93996380","wikidata":"https://www.wikidata.org/wiki/Q44127","display_name":"Server","level":2,"score":0.5383509397506714},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.5010881423950195},{"id":"https://openalex.org/C157310412","wikidata":"https://www.wikidata.org/wiki/Q3140915","display_name":"Forum spam","level":5,"score":0.49263864755630493},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.47054439783096313},{"id":"https://openalex.org/C108827166","wikidata":"https://www.wikidata.org/wiki/Q175975","display_name":"Internet privacy","level":1,"score":0.4640236496925354},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4582158923149109},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.37470489740371704},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.33797943592071533},{"id":"https://openalex.org/C158955206","wikidata":"https://www.wikidata.org/wiki/Q83058","display_name":"Spamming","level":3,"score":0.2968747913837433},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.2935207486152649},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.1094900369644165},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09514710307121277},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C121955636","wikidata":"https://www.wikidata.org/wiki/Q4116214","display_name":"Accounting","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/2740908.2742127","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2740908.2742127","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 24th International Conference on World Wide Web","raw_type":"proceedings-article"},{"id":"pmh:oai:pumaoai.isti.cnr.it:cnr.iit/cnr.iit/2015-A2-047","is_oa":true,"landing_page_url":"http://puma.isti.cnr.it/dfdownloadnew.php?ident=cnr.iit/cnr.iit/2015-A2-047","pdf_url":null,"source":null,"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"In: WWW2015 - 24th International Conference on World Wide Web Companion (Firenze, Italia, 18/22-05 2015). Proceedings, pp. 1447 - 1452. ACM, 2015.","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"pmh:oai:pumaoai.isti.cnr.it:cnr.iit/cnr.iit/2015-A2-047","is_oa":true,"landing_page_url":"http://puma.isti.cnr.it/dfdownloadnew.php?ident=cnr.iit/cnr.iit/2015-A2-047","pdf_url":null,"source":null,"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"In: WWW2015 - 24th International Conference on World Wide Web Companion (Firenze, Italia, 18/22-05 2015). Proceedings, pp. 1447 - 1452. ACM, 2015.","raw_type":"info:eu-repo/semantics/conferenceObject"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W33239550","https://openalex.org/W1973264045","https://openalex.org/W2031843194","https://openalex.org/W2033709196","https://openalex.org/W2053377618","https://openalex.org/W2055674801","https://openalex.org/W2071949631","https://openalex.org/W2073562093","https://openalex.org/W2074231493","https://openalex.org/W2082868123","https://openalex.org/W2098732437","https://openalex.org/W2104890789","https://openalex.org/W2130196635","https://openalex.org/W2155867184","https://openalex.org/W2169070925","https://openalex.org/W2169270715","https://openalex.org/W2398205506"],"related_works":["https://openalex.org/W2018000323","https://openalex.org/W1937320931","https://openalex.org/W2951492669","https://openalex.org/W359598355","https://openalex.org/W2080521416","https://openalex.org/W3168401190","https://openalex.org/W2186984153","https://openalex.org/W2095720311","https://openalex.org/W1502194589","https://openalex.org/W4394836179"],"abstract_inverted_index":{"Spam":[0],"websites":[1,46],"are":[2,6,19],"domains":[3],"whose":[4],"owners":[5],"not":[7],"interested":[8],"in":[9,24,40,55],"using":[10],"them":[11],"as":[12],"gates":[13],"for":[14],"their":[15],"activities":[16],"but":[17],"they":[18],"parked":[20],"to":[21,96],"be":[22],"sold":[23],"the":[25,33,36,56,63,98],"secondary":[26],"market":[27],"of":[28,35,43,53,81],"web":[29],"domains.":[30],"To":[31],"transform":[32],"costs":[34],"annual":[37],"registration":[38],"fees":[39],"an":[41],"opportunity":[42],"revenues,":[44],"spam":[45],"most":[47],"often":[48],"host":[49],"a":[50,75,78,90],"large":[51,79],"amount":[52],"ads":[54],"hope":[57],"that":[58,93],"someone":[59],"who":[60],"lands":[61],"on":[62,68],"site":[64],"by":[65],"chance":[66],"clicks":[67],"some":[69],"ads.":[70],"Since":[71],"parking":[72,89],"has":[73],"become":[74],"widespread":[76],"activity,":[77],"number":[80],"specialized":[82],"companies":[83],"have":[84],"come":[85],"out":[86],"and":[87],"made":[88],"straightforward":[91],"task":[92],"simply":[94],"requires":[95],"set":[97],"domain's":[99],"name":[100],"servers":[101],"appropriately.":[102]},"counts_by_year":[{"year":2023,"cited_by_count":2},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}
