{"id":"https://openalex.org/W2073562093","doi":"https://doi.org/10.1145/1189702.1189703","title":"A reference collection for web spam","display_name":"A reference collection for web spam","publication_year":2006,"publication_date":"2006-12-01","ids":{"openalex":"https://openalex.org/W2073562093","doi":"https://doi.org/10.1145/1189702.1189703","mag":"2073562093"},"language":"en","primary_location":{"id":"doi:10.1145/1189702.1189703","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1189702.1189703","pdf_url":null,"source":{"id":"https://openalex.org/S6756005","display_name":"ACM SIGIR Forum","issn_l":"0163-5840","issn":["0163-5840","1558-0229"],"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 SIGIR Forum","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/A5084282503","display_name":"Carlos Castillo","orcid":"https://orcid.org/0000-0003-4544-0416"},"institutions":[{"id":"https://openalex.org/I2800095910","display_name":"Yahoo (Spain)","ror":"https://ror.org/03gq8sg42","country_code":"ES","type":"company","lineage":["https://openalex.org/I2800095910","https://openalex.org/I4210134091"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Carlos Castillo","raw_affiliation_strings":["Universit\u00e0 di Roma, Rome, Italy and Yahoo! Research, Barcelona, Catalunya, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universit\u00e0 di Roma, Rome, Italy and Yahoo! Research, Barcelona, Catalunya, Spain","institution_ids":["https://openalex.org/I2800095910"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018490566","display_name":"Debora Donato","orcid":null},"institutions":[{"id":"https://openalex.org/I2800095910","display_name":"Yahoo (Spain)","ror":"https://ror.org/03gq8sg42","country_code":"ES","type":"company","lineage":["https://openalex.org/I2800095910","https://openalex.org/I4210134091"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Debora Donato","raw_affiliation_strings":["Universit\u00e0 di Roma, Rome, Italy and Yahoo! Research, Barcelona, Catalunya, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universit\u00e0 di Roma, Rome, Italy and Yahoo! Research, Barcelona, Catalunya, Spain","institution_ids":["https://openalex.org/I2800095910"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039929633","display_name":"Luca Becchetti","orcid":"https://orcid.org/0000-0002-4941-0532"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Luca Becchetti","raw_affiliation_strings":["Universit\u00e0 di Roma, Rome, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universit\u00e0 di Roma, Rome, Italy","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038842358","display_name":"Paolo Boldi","orcid":"https://orcid.org/0000-0002-8297-6255"},"institutions":[{"id":"https://openalex.org/I189158943","display_name":"University of Milan","ror":"https://ror.org/00wjc7c48","country_code":"IT","type":"education","lineage":["https://openalex.org/I189158943"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Paolo Boldi","raw_affiliation_strings":["Universit\u00e0 degli Studi, Milan, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universit\u00e0 degli Studi, Milan, Italy","institution_ids":["https://openalex.org/I189158943"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102836759","display_name":"Stefano Leonardi","orcid":"https://orcid.org/0000-0002-9809-7191"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Stefano Leonardi","raw_affiliation_strings":["Universit\u00e0 di Roma, Rome, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universit\u00e0 di Roma, Rome, Italy","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078458093","display_name":"Massimo Santini","orcid":"https://orcid.org/0000-0003-1416-0673"},"institutions":[{"id":"https://openalex.org/I189158943","display_name":"University of Milan","ror":"https://ror.org/00wjc7c48","country_code":"IT","type":"education","lineage":["https://openalex.org/I189158943"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Massimo Santini","raw_affiliation_strings":["Universit\u00e0 degli Studi, Milan, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universit\u00e0 degli Studi, Milan, Italy","institution_ids":["https://openalex.org/I189158943"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5027824085","display_name":"Sebastiano Vigna","orcid":"https://orcid.org/0000-0002-3257-651X"},"institutions":[{"id":"https://openalex.org/I189158943","display_name":"University of Milan","ror":"https://ror.org/00wjc7c48","country_code":"IT","type":"education","lineage":["https://openalex.org/I189158943"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Sebastiano Vigna","raw_affiliation_strings":["Universit\u00e0 degli Studi, Milan, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universit\u00e0 degli Studi, Milan, Italy","institution_ids":["https://openalex.org/I189158943"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":45.5601,"has_fulltext":false,"cited_by_count":205,"citation_normalized_percentile":{"value":0.99795501,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":"40","issue":"2","first_page":"11","last_page":"24"},"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":0.9998000264167786,"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":0.9962000250816345,"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":0.8912645578384399},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.7314366102218628},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5231117606163025},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.48626530170440674},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.48479264974594116},{"id":"https://openalex.org/keywords/spamdexing","display_name":"Spamdexing","score":0.42301642894744873},{"id":"https://openalex.org/keywords/web-development","display_name":"Web development","score":0.22816506028175354},{"id":"https://openalex.org/keywords/web-search-engine","display_name":"Web search engine","score":0.1477724313735962}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8912645578384399},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.7314366102218628},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5231117606163025},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.48626530170440674},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.48479264974594116},{"id":"https://openalex.org/C13565553","wikidata":"https://www.wikidata.org/wiki/Q804206","display_name":"Spamdexing","level":5,"score":0.42301642894744873},{"id":"https://openalex.org/C79373723","wikidata":"https://www.wikidata.org/wiki/Q386275","display_name":"Web development","level":3,"score":0.22816506028175354},{"id":"https://openalex.org/C521815418","wikidata":"https://www.wikidata.org/wiki/Q4182287","display_name":"Web search engine","level":4,"score":0.1477724313735962},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1145/1189702.1189703","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1189702.1189703","pdf_url":null,"source":{"id":"https://openalex.org/S6756005","display_name":"ACM SIGIR Forum","issn_l":"0163-5840","issn":["0163-5840","1558-0229"],"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 SIGIR Forum","raw_type":"journal-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.210.3026","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.210.3026","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://sigir.org/forum/2006D/2006d_sigirforum_castillo.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.69.31","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.69.31","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.dcc.uchile.cl/~ccastill/papers/castillo_2006_reference_collection_spam.pdf","raw_type":"text"},{"id":"pmh:oai:iris.uniroma1.it:11573/103514","is_oa":false,"landing_page_url":"http://hdl.handle.net/11573/103514","pdf_url":null,"source":{"id":"https://openalex.org/S4377196107","display_name":"IRIS Research product catalog (Sapienza University of Rome)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W202878612","https://openalex.org/W1529464143","https://openalex.org/W1845137714","https://openalex.org/W1854214752","https://openalex.org/W1975879668","https://openalex.org/W1986831811","https://openalex.org/W1994727615","https://openalex.org/W2000273502","https://openalex.org/W2066055909","https://openalex.org/W2097362268","https://openalex.org/W2130854091","https://openalex.org/W2156632103","https://openalex.org/W2169263924","https://openalex.org/W2169270715","https://openalex.org/W3170068245","https://openalex.org/W4285719527","https://openalex.org/W6631624008","https://openalex.org/W6683392976","https://openalex.org/W6794788510"],"related_works":["https://openalex.org/W1488511360","https://openalex.org/W1781894645","https://openalex.org/W2894902932","https://openalex.org/W569715723","https://openalex.org/W188332989","https://openalex.org/W2982387199","https://openalex.org/W2000745862","https://openalex.org/W2120930843","https://openalex.org/W4247875831","https://openalex.org/W42013907"],"abstract_inverted_index":{"We":[0],"describe":[1],"the":[2,20,31],"WEBSPAM-UK2006":[3],"collection,":[4],"a":[5,50],"large":[6,51],"set":[7,54],"of":[8,55],"Web":[9,24,35],"pages":[10],"that":[11,38,45],"have":[12],"been":[13,47],"manually":[14],"annotated":[15],"with":[16],"labels":[17],"indicating":[18],"if":[19],"hosts":[21],"are":[22],"include":[23],"spam":[25,36],"aspects":[26],"or":[27],"not.":[28],"This":[29],"is":[30],"first":[32],"publicly":[33],"available":[34],"collection":[37],"includes":[39],"page":[40],"contents":[41],"and":[42,44,52],"links,":[43],"has":[46],"labelled":[48],"by":[49],"diverse":[53],"judges.":[56]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":8},{"year":2017,"cited_by_count":8},{"year":2016,"cited_by_count":11},{"year":2015,"cited_by_count":19},{"year":2014,"cited_by_count":16},{"year":2013,"cited_by_count":19},{"year":2012,"cited_by_count":15}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}