{"id":"https://openalex.org/W1999391954","doi":"https://doi.org/10.1145/1531914.1531928","title":"Web spam challenge proposal for filtering in archives","display_name":"Web spam challenge proposal for filtering in archives","publication_year":2009,"publication_date":"2009-04-21","ids":{"openalex":"https://openalex.org/W1999391954","doi":"https://doi.org/10.1145/1531914.1531928","mag":"1999391954"},"language":"en","primary_location":{"id":"doi:10.1145/1531914.1531928","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1531914.1531928","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 5th International Workshop on Adversarial Information Retrieval on the Web","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/A5021452458","display_name":"Andr\u00e1s A. Bencz\u00far","orcid":"https://orcid.org/0000-0002-9392-0986"},"institutions":[{"id":"https://openalex.org/I7597260","display_name":"Hungarian Academy of Sciences","ror":"https://ror.org/02ks8qq67","country_code":"HU","type":"funder","lineage":["https://openalex.org/I7597260"]},{"id":"https://openalex.org/I4210117195","display_name":"Institute for Computer Science and Control","ror":"https://ror.org/0249v7n71","country_code":"HU","type":"facility","lineage":["https://openalex.org/I4210117195","https://openalex.org/I7597260"]}],"countries":["HU"],"is_corresponding":true,"raw_author_name":"Andr\u00e1s A. Bencz\u00far","raw_affiliation_strings":["Computer and Automation Research Institute of the Hungarian Academy of Sciences"],"affiliations":[{"raw_affiliation_string":"Computer and Automation Research Institute of the Hungarian Academy of Sciences","institution_ids":["https://openalex.org/I7597260","https://openalex.org/I4210117195"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061654929","display_name":"Mikl\u00f3s Erd\u00e9lyi","orcid":"https://orcid.org/0000-0001-5152-0020"},"institutions":[{"id":"https://openalex.org/I4210117195","display_name":"Institute for Computer Science and Control","ror":"https://ror.org/0249v7n71","country_code":"HU","type":"facility","lineage":["https://openalex.org/I4210117195","https://openalex.org/I7597260"]},{"id":"https://openalex.org/I140275651","display_name":"University of Pannonia","ror":"https://ror.org/03y5egs41","country_code":"HU","type":"education","lineage":["https://openalex.org/I140275651"]},{"id":"https://openalex.org/I7597260","display_name":"Hungarian Academy of Sciences","ror":"https://ror.org/02ks8qq67","country_code":"HU","type":"funder","lineage":["https://openalex.org/I7597260"]}],"countries":["HU"],"is_corresponding":false,"raw_author_name":"Mikl\u00f3s Erd\u00e9lyi","raw_affiliation_strings":["University of Pannonia and Computer and Automation Research Institute of the Hungarian Academy of Sciences","University of Pannonia and Computer and Automation Research Institute of the Hungarian Academy of Sciences#TAB#"],"affiliations":[{"raw_affiliation_string":"University of Pannonia and Computer and Automation Research Institute of the Hungarian Academy of Sciences","institution_ids":["https://openalex.org/I140275651","https://openalex.org/I4210117195","https://openalex.org/I7597260"]},{"raw_affiliation_string":"University of Pannonia and Computer and Automation Research Institute of the Hungarian Academy of Sciences#TAB#","institution_ids":["https://openalex.org/I7597260"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053866570","display_name":"Julien Masan\u00e9s","orcid":null},"institutions":[{"id":"https://openalex.org/I4210160905","display_name":"Internet Memory Foundation","ror":"https://ror.org/05vhqss82","country_code":"FR","type":"nonprofit","lineage":["https://openalex.org/I4210160905"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Julien Masan\u00e9s","raw_affiliation_strings":["European Archive Foundation, France"],"affiliations":[{"raw_affiliation_string":"European Archive Foundation, France","institution_ids":["https://openalex.org/I4210160905"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040113859","display_name":"D\u00e1vid Sikl\u00f3si","orcid":null},"institutions":[{"id":"https://openalex.org/I7597260","display_name":"Hungarian Academy of Sciences","ror":"https://ror.org/02ks8qq67","country_code":"HU","type":"funder","lineage":["https://openalex.org/I7597260"]},{"id":"https://openalex.org/I4210117195","display_name":"Institute for Computer Science and Control","ror":"https://ror.org/0249v7n71","country_code":"HU","type":"facility","lineage":["https://openalex.org/I4210117195","https://openalex.org/I7597260"]}],"countries":["HU"],"is_corresponding":false,"raw_author_name":"D\u00e1vid Sikl\u00f3si","raw_affiliation_strings":["Computer and Automation Research Institute of the Hungarian Academy of Sciences"],"affiliations":[{"raw_affiliation_string":"Computer and Automation Research Institute of the Hungarian Academy of Sciences","institution_ids":["https://openalex.org/I7597260","https://openalex.org/I4210117195"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5021452458"],"corresponding_institution_ids":["https://openalex.org/I4210117195","https://openalex.org/I7597260"],"apc_list":null,"apc_paid":null,"fwci":3.8737,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.94179851,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"61","last_page":"62"},"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":0.9998999834060669,"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/T11478","display_name":"Caching and Content Delivery","score":0.9976999759674072,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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":0.8014412522315979},{"id":"https://openalex.org/keywords/snapshot","display_name":"Snapshot (computer storage)","score":0.5615156292915344},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.48584768176078796},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4837510585784912},{"id":"https://openalex.org/keywords/web-application","display_name":"Web application","score":0.4367646872997284},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3274723291397095},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.21866366267204285}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8014412522315979},{"id":"https://openalex.org/C55282118","wikidata":"https://www.wikidata.org/wiki/Q252683","display_name":"Snapshot (computer storage)","level":2,"score":0.5615156292915344},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.48584768176078796},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4837510585784912},{"id":"https://openalex.org/C118643609","wikidata":"https://www.wikidata.org/wiki/Q189210","display_name":"Web application","level":2,"score":0.4367646872997284},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3274723291397095},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.21866366267204285}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/1531914.1531928","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1531914.1531928","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 5th International Workshop on Adversarial Information Retrieval on the Web","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.504.9410","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.504.9410","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/2009/papers/p61-benczur.pdf","raw_type":"text"},{"id":"pmh:oai:eprints.sztaki.hu:5977","is_oa":false,"landing_page_url":"http://eprints.sztaki.hu/5977/","pdf_url":null,"source":{"id":"https://openalex.org/S4306401907","display_name":"SZTAKI Publication Repository (Hungarian Academy of Sciences)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I7597260","host_organization_name":"Hungarian Academy of Sciences","host_organization_lineage":["https://openalex.org/I7597260"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference or Workshop Item"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W1978555214","https://openalex.org/W2000273502","https://openalex.org/W2027116318","https://openalex.org/W2038002297","https://openalex.org/W2066055909","https://openalex.org/W2073562093","https://openalex.org/W2089616424","https://openalex.org/W2101694308","https://openalex.org/W2184575469"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W2542847180","https://openalex.org/W3034994054","https://openalex.org/W2805712290","https://openalex.org/W2155226960","https://openalex.org/W2909129499","https://openalex.org/W2392087771","https://openalex.org/W2761598930","https://openalex.org/W2553994394","https://openalex.org/W2356600124"],"abstract_inverted_index":{"In":[0],"this":[1],"paper":[2],"we":[3],"propose":[4],"new":[5,99],"tasks":[6,80],"for":[7,90],"a":[8,48],"possible":[9],"future":[10],"Web":[11,23],"Spam":[12],"Challenge":[13,79],"motivated":[14],"by":[15,72],"the":[16,19,63,84,102],"needs":[17],"of":[18,27,44,51,62,66,86,97,101],"archival":[20,24],"community.":[21],"The":[22],"community":[25],"consists":[26],"several":[28],"relatively":[29],"small":[30],"institutions":[31],"that":[32],"operate":[33],"independently":[34],"and":[35,69],"possibly":[36],"over":[37],"different":[38,76,106],"top":[39],"level":[40],"domains":[41],"(TLDs).":[42],"Each":[43],"them":[45],"may":[46],"have":[47],"large":[49],"set":[50],"historic":[52],"crawls.":[53],"Efficient":[54],"filtering":[55],"would":[56],"hence":[57,82],"require":[58],"(1)":[59],"enhanced":[60],"use":[61],"time":[64],"series":[65],"domain":[67],"snapshots":[68],"(2)":[70],"collaboration":[71],"transferring":[73],"models":[74],"across":[75],"TLDs.":[77,107],"Corresponding":[78],"could":[81],"include":[83],"distribution":[85],"crawl":[87],"snapshot":[88],"data":[89],"feature":[91],"generation":[92],"as":[93,95],"well":[94],"classification":[96],"unlabeled":[98],"crawls":[100],"same":[103],"or":[104],"even":[105]},"counts_by_year":[{"year":2019,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}