{"id":"https://openalex.org/W2101694308","doi":"https://doi.org/10.1145/1531914.1531918","title":"Web spam filtering in internet archives","display_name":"Web spam filtering in internet archives","publication_year":2009,"publication_date":"2009-04-21","ids":{"openalex":"https://openalex.org/W2101694308","doi":"https://doi.org/10.1145/1531914.1531918","mag":"2101694308"},"language":"en","primary_location":{"id":"doi:10.1145/1531914.1531918","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1531914.1531918","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/A5061654929","display_name":"Mikl\u00f3s Erd\u00e9lyi","orcid":"https://orcid.org/0000-0001-5152-0020"},"institutions":[{"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/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/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":true,"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"],"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"]}]},{"author_position":"middle","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":false,"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/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/A5061654929"],"corresponding_institution_ids":["https://openalex.org/I140275651","https://openalex.org/I4210117195","https://openalex.org/I7597260"],"apc_list":null,"apc_paid":null,"fwci":7.7474,"has_fulltext":false,"cited_by_count":25,"citation_normalized_percentile":{"value":0.97203017,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"17","last_page":"20"},"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/T10400","display_name":"Network Security and Intrusion Detection","score":0.9983999729156494,"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"}},{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9976000189781189,"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/computer-science","display_name":"Computer science","score":0.6782478094100952},{"id":"https://openalex.org/keywords/the-internet","display_name":"The Internet","score":0.6715502738952637},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.6151610016822815},{"id":"https://openalex.org/keywords/forum-spam","display_name":"Forum spam","score":0.4869724214076996},{"id":"https://openalex.org/keywords/web-application","display_name":"Web application","score":0.4287313222885132},{"id":"https://openalex.org/keywords/spambot","display_name":"Spambot","score":0.34999167919158936},{"id":"https://openalex.org/keywords/spamming","display_name":"Spamming","score":0.22412142157554626}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6782478094100952},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.6715502738952637},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.6151610016822815},{"id":"https://openalex.org/C157310412","wikidata":"https://www.wikidata.org/wiki/Q3140915","display_name":"Forum spam","level":5,"score":0.4869724214076996},{"id":"https://openalex.org/C118643609","wikidata":"https://www.wikidata.org/wiki/Q189210","display_name":"Web application","level":2,"score":0.4287313222885132},{"id":"https://openalex.org/C127735637","wikidata":"https://www.wikidata.org/wiki/Q2306702","display_name":"Spambot","level":4,"score":0.34999167919158936},{"id":"https://openalex.org/C158955206","wikidata":"https://www.wikidata.org/wiki/Q83058","display_name":"Spamming","level":3,"score":0.22412142157554626}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/1531914.1531918","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1531914.1531918","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:10.1.1.455.2030","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.455.2030","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/p17-erdelyi.pdf","raw_type":"text"},{"id":"pmh:oai:eprints.sztaki.hu:5979","is_oa":false,"landing_page_url":"http://eprints.sztaki.hu/5979/","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":[{"display_name":"Decent work and economic growth","id":"https://metadata.un.org/sdg/8","score":0.44999998807907104}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W23149702","https://openalex.org/W189202421","https://openalex.org/W202878612","https://openalex.org/W1566984846","https://openalex.org/W1570448133","https://openalex.org/W1845137714","https://openalex.org/W1967825155","https://openalex.org/W1969301668","https://openalex.org/W1978555214","https://openalex.org/W1987272746","https://openalex.org/W1987365175","https://openalex.org/W1999391954","https://openalex.org/W2000273502","https://openalex.org/W2066055909","https://openalex.org/W2073562093","https://openalex.org/W2099789730","https://openalex.org/W2108671511","https://openalex.org/W2112400959","https://openalex.org/W2118577797","https://openalex.org/W2118942057","https://openalex.org/W2128272588","https://openalex.org/W2130196635","https://openalex.org/W2130854091","https://openalex.org/W2139148100","https://openalex.org/W2169263924","https://openalex.org/W2169270715","https://openalex.org/W2184575469","https://openalex.org/W2303394219","https://openalex.org/W2626710409","https://openalex.org/W2913520302","https://openalex.org/W2966207845","https://openalex.org/W3204318296","https://openalex.org/W4236002984","https://openalex.org/W4251434705","https://openalex.org/W4285719527"],"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/W4253934582","https://openalex.org/W3168401190","https://openalex.org/W2186984153","https://openalex.org/W2095720311","https://openalex.org/W1502194589"],"abstract_inverted_index":{"While":[0],"Web":[1,14,28,36,72],"spam":[2,29,73],"is":[3],"targeted":[4],"for":[5,85],"the":[6,41,68],"high":[7,82],"commercial":[8],"value":[9],"of":[10,64,70],"top-ranked":[11],"search-engine":[12],"results,":[13],"archives":[15,57],"observe":[16],"quality":[17,83],"deterioration":[18],"and":[19],"resource":[20],"waste":[21],"as":[22,43],"a":[23,46,61,81],"side":[24],"effect.":[25],"So":[26],"far":[27],"filtering":[30,74],"technologies":[31],"are":[32],"rarely":[33],"used":[34],"by":[35],"archivists":[37],"but":[38,75],"planned":[39],"in":[40,45],"future":[42],"indicated":[44],"survey":[47],"with":[48],"responses":[49],"from":[50],"more":[51],"than":[52],"20":[53],"institutions":[54],"worldwide.":[55],"These":[56],"typically":[58],"operate":[59],"on":[60],"modest":[62],"level":[63],"budget":[65],"that":[66],"prohibits":[67],"operation":[69],"standalone":[71],"collaborative":[76],"efforts":[77],"could":[78],"lead":[79],"to":[80],"solution":[84],"them.":[86]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":2},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":4},{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":2}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}