{"id":"https://openalex.org/W1994441352","doi":"https://doi.org/10.1145/1008694.1008707","title":"Discovery of ads web hosts through traffic data analysis","display_name":"Discovery of ads web hosts through traffic data analysis","publication_year":2004,"publication_date":"2004-06-13","ids":{"openalex":"https://openalex.org/W1994441352","doi":"https://doi.org/10.1145/1008694.1008707","mag":"1994441352"},"language":"en","primary_location":{"id":"doi:10.1145/1008694.1008707","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1008694.1008707","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 9th ACM SIGMOD workshop on Research issues in data mining and knowledge discovery","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/A5021155081","display_name":"V. Bacarella","orcid":null},"institutions":[{"id":"https://openalex.org/I108290504","display_name":"University of Pisa","ror":"https://ror.org/03ad39j10","country_code":"IT","type":"education","lineage":["https://openalex.org/I108290504"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"V. Bacarella","raw_affiliation_strings":["University of Pisa, Pisa, Italy","University of Pisa, Pisa, Italy ("],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Pisa, Pisa, Italy","institution_ids":["https://openalex.org/I108290504"]},{"raw_affiliation_string":"University of Pisa, Pisa, Italy (","institution_ids":["https://openalex.org/I108290504"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024505700","display_name":"Fosca Giannotti","orcid":"https://orcid.org/0000-0003-3099-3835"},"institutions":[{"id":"https://openalex.org/I122991210","display_name":"Istituto di Scienza e Tecnologie dell'Informazione \"Alessandro Faedo\"","ror":"https://ror.org/05kacka20","country_code":"IT","type":"facility","lineage":["https://openalex.org/I122991210","https://openalex.org/I4210155236"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"F. Giannotti","raw_affiliation_strings":["ISTI-CNR, Pisa, Italy","ISTI--CNR, Pisa, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ISTI-CNR, Pisa, Italy","institution_ids":["https://openalex.org/I122991210"]},{"raw_affiliation_string":"ISTI--CNR, Pisa, Italy","institution_ids":["https://openalex.org/I122991210"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009248582","display_name":"Mirco Nanni","orcid":"https://orcid.org/0000-0003-3534-4332"},"institutions":[{"id":"https://openalex.org/I122991210","display_name":"Istituto di Scienza e Tecnologie dell'Informazione \"Alessandro Faedo\"","ror":"https://ror.org/05kacka20","country_code":"IT","type":"facility","lineage":["https://openalex.org/I122991210","https://openalex.org/I4210155236"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"M. Nanni","raw_affiliation_strings":["ISTI-CNR, Pisa, Italy","ISTI--CNR, Pisa, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ISTI-CNR, Pisa, Italy","institution_ids":["https://openalex.org/I122991210"]},{"raw_affiliation_string":"ISTI--CNR, Pisa, Italy","institution_ids":["https://openalex.org/I122991210"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5044898565","display_name":"Dino Pedreschi","orcid":"https://orcid.org/0000-0003-4801-3225"},"institutions":[{"id":"https://openalex.org/I108290504","display_name":"University of Pisa","ror":"https://ror.org/03ad39j10","country_code":"IT","type":"education","lineage":["https://openalex.org/I108290504"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"D. Pedreschi","raw_affiliation_strings":["University of Pisa, Pisa, Italy","University of Pisa, Pisa, Italy ("],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Pisa, Pisa, Italy","institution_ids":["https://openalex.org/I108290504"]},{"raw_affiliation_string":"University of Pisa, Pisa, Italy (","institution_ids":["https://openalex.org/I108290504"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.8077,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.84970325,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"76","last_page":"81"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","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/T12016","display_name":"Web Data Mining and Analysis","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/T10064","display_name":"Complex Network Analysis Techniques","score":0.9714000225067139,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11644","display_name":"Spam and Phishing Detection","score":0.9656999707221985,"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/crawling","display_name":"Crawling","score":0.869786262512207},{"id":"https://openalex.org/keywords/web-crawler","display_name":"Web crawler","score":0.8550590872764587},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8406668901443481},{"id":"https://openalex.org/keywords/blacklist","display_name":"Blacklist","score":0.8293138742446899},{"id":"https://openalex.org/keywords/the-internet","display_name":"The Internet","score":0.6037855744361877},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.557554304599762},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5284849405288696},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.4892082214355469},{"id":"https://openalex.org/keywords/abstraction","display_name":"Abstraction","score":0.4439808428287506},{"id":"https://openalex.org/keywords/web-traffic","display_name":"Web traffic","score":0.41187024116516113},{"id":"https://openalex.org/keywords/web-analytics","display_name":"Web analytics","score":0.41075167059898376},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4031854271888733},{"id":"https://openalex.org/keywords/web-modeling","display_name":"Web modeling","score":0.27163663506507874},{"id":"https://openalex.org/keywords/web-intelligence","display_name":"Web intelligence","score":0.13616925477981567}],"concepts":[{"id":"https://openalex.org/C100368936","wikidata":"https://www.wikidata.org/wiki/Q1411725","display_name":"Crawling","level":2,"score":0.869786262512207},{"id":"https://openalex.org/C13743948","wikidata":"https://www.wikidata.org/wiki/Q45842","display_name":"Web crawler","level":2,"score":0.8550590872764587},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8406668901443481},{"id":"https://openalex.org/C2781345505","wikidata":"https://www.wikidata.org/wiki/Q2535979","display_name":"Blacklist","level":2,"score":0.8293138742446899},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.6037855744361877},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.557554304599762},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5284849405288696},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.4892082214355469},{"id":"https://openalex.org/C124304363","wikidata":"https://www.wikidata.org/wiki/Q673661","display_name":"Abstraction","level":2,"score":0.4439808428287506},{"id":"https://openalex.org/C2777672014","wikidata":"https://www.wikidata.org/wiki/Q1172573","display_name":"Web traffic","level":3,"score":0.41187024116516113},{"id":"https://openalex.org/C516187249","wikidata":"https://www.wikidata.org/wiki/Q10719477","display_name":"Web analytics","level":5,"score":0.41075167059898376},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4031854271888733},{"id":"https://openalex.org/C130436687","wikidata":"https://www.wikidata.org/wiki/Q7978591","display_name":"Web modeling","level":3,"score":0.27163663506507874},{"id":"https://openalex.org/C544335954","wikidata":"https://www.wikidata.org/wiki/Q2553348","display_name":"Web intelligence","level":4,"score":0.13616925477981567},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C105702510","wikidata":"https://www.wikidata.org/wiki/Q514","display_name":"Anatomy","level":1,"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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/1008694.1008707","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1008694.1008707","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 9th ACM SIGMOD workshop on Research issues in data mining and knowledge discovery","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.101.7030","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.101.7030","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://ercolino.isti.cnr.it/mirco/papers/dmkd-04-proceedings.pdf","raw_type":"text"},{"id":"pmh:oai:arpi.unipi.it:11568/86855","is_oa":false,"landing_page_url":"http://hdl.handle.net/11568/86855","pdf_url":null,"source":{"id":"https://openalex.org/S4377196265","display_name":"CINECA IRIS Institutial research information system (University of Pisa)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I108290504","host_organization_name":"University of Pisa","host_organization_lineage":["https://openalex.org/I108290504"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W1489992655","https://openalex.org/W1634410371","https://openalex.org/W1966496085","https://openalex.org/W1996869586","https://openalex.org/W2029341294","https://openalex.org/W2040075907","https://openalex.org/W2050028965","https://openalex.org/W2124777633","https://openalex.org/W2144982204","https://openalex.org/W2166590470","https://openalex.org/W4238940159"],"related_works":["https://openalex.org/W3119324922","https://openalex.org/W2352686120","https://openalex.org/W2372594123","https://openalex.org/W2358310581","https://openalex.org/W2026132847","https://openalex.org/W4385695127","https://openalex.org/W2137810919","https://openalex.org/W2964752624","https://openalex.org/W4255854114","https://openalex.org/W2026661369"],"abstract_inverted_index":{"One":[0],"of":[1,14,20,29,32,71,88,120,125,153,200],"the":[2,10,27,44,59,63,84,108,123,146,154,171,190,198],"most":[3,11],"actual":[4],"problems":[5],"on":[6,145],"web":[7,79,103,156],"crawling":[8,45],"--":[9,25,113,117],"expensive":[12],"task":[13],"any":[15,55],"search":[16],"engine,":[17],"in":[18,48,66,174],"terms":[19],"time":[21,142],"and":[22,78],"bandwidth":[23],"consumption":[24],"is":[26,94],"detection":[28],"useless":[30,134],"segments":[31,38],"Internet.":[33],"In":[34,97],"some":[35],"cases":[36],"such":[37,180],"are":[39],"purposely":[40],"created":[41],"to":[42,62,73,83,107,132,177,183],"deceive":[43],"engine":[46],"while,":[47],"others,":[49],"they":[50],"simply":[51],"do":[52],"not":[53],"contain":[54],"useful":[56],"information.":[57],"Currently,":[58],"typical":[60],"approach":[61],"problem":[64],"consists":[65],"using":[67],"a":[68,102,126,140,164,186],"human-compiled":[69],"blacklist":[70],"sites":[72,77,121,181],"avoid":[74],"(e.g.,":[75],"advertising":[76],"counters),":[80],"but,":[81],"due":[82],"strongly":[85],"dynamical":[86],"nature":[87],"Internet,":[89],"keeping":[90],"them":[91,185],"manually":[92],"up-to-date":[93],"quite":[95],"unfeasible.":[96],"this":[98,175],"work":[99],"we":[100],"present":[101],"usage":[104],"statistics-based":[105],"solution":[106],"problem,":[109],"aimed":[110],"at":[111],"automatically":[112],"and,":[114,194],"therefore,":[115,195],"dynamically":[116],"building":[118],"blacklists":[119],"that":[122],"users":[124],"monitored":[127],"web-community":[128],"consider":[129],"(or":[130],"appear":[131],"consider)":[133],"or":[135,182],"uninteresting.":[136],"Our":[137],"method":[138],"performs":[139],"linear":[141],"complexity":[143],"analysis":[144],"traffic":[147],"information":[148],"which":[149,157],"yields":[150],"an":[151],"abstraction":[152],"linked":[155],"can":[158,169],"be":[159],"incrementally":[160],"up-dated,":[161],"therefore":[162],"allowing":[163],"streaming":[165],"computation.":[166],"The":[167],"crawler":[168],"use":[170],"list":[172],"produced":[173],"way":[176],"prune":[178],"out":[179],"give":[184],"low":[187],"priority":[188],"before":[189],"(re-)spidering":[191],"activity":[192],"starts":[193],"without":[196],"analysing":[197],"content":[199],"crawled":[201],"documents.":[202]},"counts_by_year":[{"year":2012,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
