{"id":"https://openalex.org/W2124758299","doi":"https://doi.org/10.1145/1367497.1367685","title":"Improving web spam detection with re-extracted features","display_name":"Improving web spam detection with re-extracted features","publication_year":2008,"publication_date":"2008-04-21","ids":{"openalex":"https://openalex.org/W2124758299","doi":"https://doi.org/10.1145/1367497.1367685","mag":"2124758299"},"language":"en","primary_location":{"id":"doi:10.1145/1367497.1367685","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1367497.1367685","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 17th international conference on World Wide 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/A5035643851","display_name":"Guanggang Geng","orcid":"https://orcid.org/0000-0002-9039-6883"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guanggang Geng","raw_affiliation_strings":["Chinese Academy of Sciences, Beijing, China","Chinese Academy of Sciences , Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366"]},{"raw_affiliation_string":"Chinese Academy of Sciences , Beijing, China","institution_ids":["https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041494720","display_name":"Chunheng Wang","orcid":"https://orcid.org/0000-0002-9589-8284"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chunheng Wang","raw_affiliation_strings":["Chinese Academy of Sciences, Beijing, China","Chinese Academy of Sciences , Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366"]},{"raw_affiliation_string":"Chinese Academy of Sciences , Beijing, China","institution_ids":["https://openalex.org/I19820366"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5024206808","display_name":"Qiudan Li","orcid":"https://orcid.org/0000-0002-8714-4562"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qiudan Li","raw_affiliation_strings":["Chinese Academy of Sciences, Beijing, China","Chinese Academy of Sciences , Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366"]},{"raw_affiliation_string":"Chinese Academy of Sciences , Beijing, China","institution_ids":["https://openalex.org/I19820366"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.8757,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.85039959,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1119","last_page":"1120"},"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/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"}},{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9976999759674072,"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":0.8025906085968018},{"id":"https://openalex.org/keywords/spamdexing","display_name":"Spamdexing","score":0.6675884127616882},{"id":"https://openalex.org/keywords/the-internet","display_name":"The Internet","score":0.5887591242790222},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.5822252035140991},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5637811422348022},{"id":"https://openalex.org/keywords/heuristic","display_name":"Heuristic","score":0.5616562366485596},{"id":"https://openalex.org/keywords/spambot","display_name":"Spambot","score":0.5325789451599121},{"id":"https://openalex.org/keywords/deep-web","display_name":"Deep Web","score":0.4258747696876526},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4244700074195862},{"id":"https://openalex.org/keywords/search-engine","display_name":"Search engine","score":0.3699546456336975},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3650304079055786},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.29740238189697266},{"id":"https://openalex.org/keywords/web-search-query","display_name":"Web search query","score":0.23066446185112},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.2171858847141266},{"id":"https://openalex.org/keywords/spamming","display_name":"Spamming","score":0.166788250207901},{"id":"https://openalex.org/keywords/web-search-engine","display_name":"Web search engine","score":0.14252790808677673}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8025906085968018},{"id":"https://openalex.org/C13565553","wikidata":"https://www.wikidata.org/wiki/Q804206","display_name":"Spamdexing","level":5,"score":0.6675884127616882},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.5887591242790222},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.5822252035140991},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5637811422348022},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.5616562366485596},{"id":"https://openalex.org/C127735637","wikidata":"https://www.wikidata.org/wiki/Q2306702","display_name":"Spambot","level":4,"score":0.5325789451599121},{"id":"https://openalex.org/C46721378","wikidata":"https://www.wikidata.org/wiki/Q221989","display_name":"Deep Web","level":3,"score":0.4258747696876526},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4244700074195862},{"id":"https://openalex.org/C97854310","wikidata":"https://www.wikidata.org/wiki/Q19541","display_name":"Search engine","level":2,"score":0.3699546456336975},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3650304079055786},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.29740238189697266},{"id":"https://openalex.org/C164120249","wikidata":"https://www.wikidata.org/wiki/Q995982","display_name":"Web search query","level":3,"score":0.23066446185112},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.2171858847141266},{"id":"https://openalex.org/C158955206","wikidata":"https://www.wikidata.org/wiki/Q83058","display_name":"Spamming","level":3,"score":0.166788250207901},{"id":"https://openalex.org/C521815418","wikidata":"https://www.wikidata.org/wiki/Q4182287","display_name":"Web search engine","level":4,"score":0.14252790808677673},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/1367497.1367685","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1367497.1367685","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 17th international conference on World Wide Web","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.400.9212","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.400.9212","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www2008.org/papers/pdf/p1119-gengA.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure","score":0.5600000023841858}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":4,"referenced_works":["https://openalex.org/W2066055909","https://openalex.org/W2103456180","https://openalex.org/W2112358949","https://openalex.org/W2130196635"],"related_works":["https://openalex.org/W2368945903","https://openalex.org/W4255972148","https://openalex.org/W2222022498","https://openalex.org/W2062919806","https://openalex.org/W3437724","https://openalex.org/W4312784821","https://openalex.org/W2922524414","https://openalex.org/W2091208042","https://openalex.org/W4776438","https://openalex.org/W2098732437"],"abstract_inverted_index":{"Web":[0],"spam":[1,67],"detection":[2,30,68],"has":[3],"become":[4],"one":[5],"of":[6,16,50,65],"the":[7,11,29,34,39,43,63],"top":[8],"challenges":[9],"for":[10],"Internet":[12],"search":[13],"industry.":[14],"Instead":[15],"using":[17],"some":[18],"heuristic":[19],"rules,":[20],"we":[21],"propose":[22],"a":[23],"feature":[24],"re-extraction":[25],"strategy":[26],"to":[27],"optimize":[28],"result.":[31],"Based":[32],"on":[33,55],"predicted":[35],"spamicity":[36],"obtained":[37],"by":[38],"preliminary":[40],"detection,":[41],"through":[42],"host":[44],"level":[45],"web":[46,66],"graph,":[47],"three":[48],"types":[49],"features":[51],"are":[52],"extracted.":[53],"Experiments":[54],"WEBSPAM-UK2006":[56],"benchmark":[57],"show":[58],"that":[59],"with":[60],"this":[61],"strategy,":[62],"performance":[64],"can":[69],"be":[70],"improved":[71],"evidently.":[72],"Categories":[73],"and":[74],"Subject":[75],"Descriptors":[76]},"counts_by_year":[{"year":2018,"cited_by_count":3},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
