{"id":"https://openalex.org/W2128184786","doi":"https://doi.org/10.1145/1964114.1964121","title":"Web spam classification","display_name":"Web spam classification","publication_year":2011,"publication_date":"2011-03-28","ids":{"openalex":"https://openalex.org/W2128184786","doi":"https://doi.org/10.1145/1964114.1964121","mag":"2128184786"},"language":"en","primary_location":{"id":"doi:10.1145/1964114.1964121","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1964114.1964121","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2011 Joint WICOW/AIRWeb Workshop on Web Quality","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/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":["Hungarian Academy of Sciences and University of Pannonia, Veszpr\u00e9m"],"affiliations":[{"raw_affiliation_string":"Hungarian Academy of Sciences and University of Pannonia, Veszpr\u00e9m","institution_ids":["https://openalex.org/I140275651","https://openalex.org/I7597260"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056644592","display_name":"Andr\u00e1s Garz\u00f3","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"]}],"countries":["HU"],"is_corresponding":false,"raw_author_name":"Andr\u00e1s Garz\u00f3","raw_affiliation_strings":["Hungarian Academy of Sciences"],"affiliations":[{"raw_affiliation_string":"Hungarian Academy of Sciences","institution_ids":["https://openalex.org/I7597260"]}]},{"author_position":"last","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"]}],"countries":["HU"],"is_corresponding":false,"raw_author_name":"Andr\u00e1s A. Bencz\u00far","raw_affiliation_strings":["Hungarian Academy of Sciences"],"affiliations":[{"raw_affiliation_string":"Hungarian Academy of Sciences","institution_ids":["https://openalex.org/I7597260"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5061654929"],"corresponding_institution_ids":["https://openalex.org/I140275651","https://openalex.org/I7597260"],"apc_list":null,"apc_paid":null,"fwci":24.3856,"has_fulltext":false,"cited_by_count":69,"citation_normalized_percentile":{"value":0.99359041,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"27","last_page":"34"},"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":0.9988999962806702,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9984999895095825,"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/computer-science","display_name":"Computer science","score":0.8281890153884888},{"id":"https://openalex.org/keywords/spambot","display_name":"Spambot","score":0.594327986240387},{"id":"https://openalex.org/keywords/spamdexing","display_name":"Spamdexing","score":0.5822827219963074},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5158088207244873},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.514746904373169},{"id":"https://openalex.org/keywords/web-application","display_name":"Web application","score":0.4231984615325928},{"id":"https://openalex.org/keywords/statistical-classification","display_name":"Statistical classification","score":0.4154902696609497},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41254982352256775},{"id":"https://openalex.org/keywords/forum-spam","display_name":"Forum spam","score":0.41150712966918945},{"id":"https://openalex.org/keywords/bag-of-words-model","display_name":"Bag-of-words model","score":0.4109792709350586},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.40014076232910156},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.34974202513694763},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.32241806387901306},{"id":"https://openalex.org/keywords/the-internet","display_name":"The Internet","score":0.3140770494937897},{"id":"https://openalex.org/keywords/spamming","display_name":"Spamming","score":0.2058527171611786},{"id":"https://openalex.org/keywords/web-2.0","display_name":"Web 2.0","score":0.14741837978363037},{"id":"https://openalex.org/keywords/web-search-engine","display_name":"Web search engine","score":0.0650697648525238}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8281890153884888},{"id":"https://openalex.org/C127735637","wikidata":"https://www.wikidata.org/wiki/Q2306702","display_name":"Spambot","level":4,"score":0.594327986240387},{"id":"https://openalex.org/C13565553","wikidata":"https://www.wikidata.org/wiki/Q804206","display_name":"Spamdexing","level":5,"score":0.5822827219963074},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5158088207244873},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.514746904373169},{"id":"https://openalex.org/C118643609","wikidata":"https://www.wikidata.org/wiki/Q189210","display_name":"Web application","level":2,"score":0.4231984615325928},{"id":"https://openalex.org/C110083411","wikidata":"https://www.wikidata.org/wiki/Q1744628","display_name":"Statistical classification","level":2,"score":0.4154902696609497},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41254982352256775},{"id":"https://openalex.org/C157310412","wikidata":"https://www.wikidata.org/wiki/Q3140915","display_name":"Forum spam","level":5,"score":0.41150712966918945},{"id":"https://openalex.org/C13672336","wikidata":"https://www.wikidata.org/wiki/Q3460803","display_name":"Bag-of-words model","level":2,"score":0.4109792709350586},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.40014076232910156},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.34974202513694763},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.32241806387901306},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.3140770494937897},{"id":"https://openalex.org/C158955206","wikidata":"https://www.wikidata.org/wiki/Q83058","display_name":"Spamming","level":3,"score":0.2058527171611786},{"id":"https://openalex.org/C136699151","wikidata":"https://www.wikidata.org/wiki/Q131164","display_name":"Web 2.0","level":3,"score":0.14741837978363037},{"id":"https://openalex.org/C521815418","wikidata":"https://www.wikidata.org/wiki/Q4182287","display_name":"Web search engine","level":4,"score":0.0650697648525238}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1964114.1964121","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1964114.1964121","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2011 Joint WICOW/AIRWeb Workshop on Web Quality","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":46,"referenced_works":["https://openalex.org/W23149702","https://openalex.org/W174542576","https://openalex.org/W569220443","https://openalex.org/W1534276167","https://openalex.org/W1534979469","https://openalex.org/W1570448133","https://openalex.org/W1845137714","https://openalex.org/W1967825155","https://openalex.org/W1976446088","https://openalex.org/W1979870225","https://openalex.org/W1980264541","https://openalex.org/W1986473509","https://openalex.org/W1999391954","https://openalex.org/W2003362605","https://openalex.org/W2009408190","https://openalex.org/W2014415866","https://openalex.org/W2024046085","https://openalex.org/W2027116318","https://openalex.org/W2038002297","https://openalex.org/W2053724458","https://openalex.org/W2066055909","https://openalex.org/W2073562093","https://openalex.org/W2088807748","https://openalex.org/W2089616424","https://openalex.org/W2101694308","https://openalex.org/W2102232904","https://openalex.org/W2118942057","https://openalex.org/W2130196635","https://openalex.org/W2130758745","https://openalex.org/W2137168471","https://openalex.org/W2139146018","https://openalex.org/W2141243388","https://openalex.org/W2142604303","https://openalex.org/W2145800633","https://openalex.org/W2150446468","https://openalex.org/W2169270715","https://openalex.org/W2184575469","https://openalex.org/W2303394219","https://openalex.org/W2407316094","https://openalex.org/W2596281011","https://openalex.org/W2626710409","https://openalex.org/W2911964244","https://openalex.org/W2966207845","https://openalex.org/W4236002984","https://openalex.org/W4240176047","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W2080521416","https://openalex.org/W4776438","https://openalex.org/W2091208042","https://openalex.org/W359598355","https://openalex.org/W2148238780","https://openalex.org/W2049541992","https://openalex.org/W2049645829","https://openalex.org/W2098732437","https://openalex.org/W2006090454","https://openalex.org/W2099937822"],"abstract_inverted_index":{"In":[0],"this":[1],"paper":[2],"we":[3],"investigate":[4],"how":[5],"much":[6],"various":[7],"classes":[8],"of":[9],"Web":[10],"spam":[11,56],"features,":[12],"some":[13],"requiring":[14],"very":[15],"high":[16],"computational":[17],"effort,":[18],"add":[19],"to":[20],"the":[21,39],"classification":[22],"accuracy.":[23],"We":[24],"realize":[25],"that":[26,33],"advances":[27],"in":[28,38,51],"machine":[29],"learning,":[30],"an":[31],"area":[32],"has":[34],"received":[35],"less":[36],"attention":[37],"adversarial":[40],"IR":[41],"community,":[42],"yields":[43],"more":[44],"improvement":[45],"than":[46],"new":[47],"features":[48],"and":[49],"result":[50],"low":[52],"cost":[53],"yet":[54],"accurate":[55],"filters.":[57],"Our":[58],"original":[59],"contributions":[60],"are":[61],"as":[62],"follows:":[63]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":5},{"year":2016,"cited_by_count":6},{"year":2015,"cited_by_count":8},{"year":2014,"cited_by_count":10},{"year":2013,"cited_by_count":11},{"year":2012,"cited_by_count":11}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
