{"id":"https://openalex.org/W2096679947","doi":"https://doi.org/10.1109/icsmc.2009.5346290","title":"A boosted semi-supervised learning framework for web page filtering","display_name":"A boosted semi-supervised learning framework for web page filtering","publication_year":2009,"publication_date":"2009-10-01","ids":{"openalex":"https://openalex.org/W2096679947","doi":"https://doi.org/10.1109/icsmc.2009.5346290","mag":"2096679947"},"language":"en","primary_location":{"id":"doi:10.1109/icsmc.2009.5346290","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icsmc.2009.5346290","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE International Conference on Systems, Man and Cybernetics","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/A5101493869","display_name":"He Zhu","orcid":"https://orcid.org/0000-0002-6539-9601"},"institutions":[{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zhu He","raw_affiliation_strings":["National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy and Sciences, Beijing, China","National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, No. 95 East Zhongguancun Road, 100190, Beijing, China"],"affiliations":[{"raw_affiliation_string":"National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy and Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210112150"]},{"raw_affiliation_string":"National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, No. 95 East Zhongguancun Road, 100190, Beijing, China","institution_ids":["https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062325535","display_name":"Xi Li","orcid":"https://orcid.org/0000-0002-3015-513X"},"institutions":[{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xi Li","raw_affiliation_strings":["National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy and Sciences, Beijing, China","National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, No. 95 East Zhongguancun Road, 100190, Beijing, China"],"affiliations":[{"raw_affiliation_string":"National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy and Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210112150"]},{"raw_affiliation_string":"National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, No. 95 East Zhongguancun Road, 100190, Beijing, China","institution_ids":["https://openalex.org/I19820366"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5114549594","display_name":"Weiming Hu","orcid":"https://orcid.org/0000-0001-9237-8825"},"institutions":[{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weiming Hu","raw_affiliation_strings":["National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy and Sciences, Beijing, China","National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, No. 95 East Zhongguancun Road, 100190, Beijing, China"],"affiliations":[{"raw_affiliation_string":"National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy and Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210112150"]},{"raw_affiliation_string":"National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, No. 95 East Zhongguancun Road, 100190, Beijing, China","institution_ids":["https://openalex.org/I19820366"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5101493869"],"corresponding_institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210112150"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.14573594,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"14","issue":null,"first_page":"2133","last_page":"2136"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11644","display_name":"Spam and Phishing Detection","score":0.9987000226974487,"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":0.9987000226974487,"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":0.9983000159263611,"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":0.998199999332428,"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/web-page","display_name":"Web page","score":0.8095428943634033},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.806485116481781},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.5712661147117615},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5655012130737305},{"id":"https://openalex.org/keywords/the-internet","display_name":"The Internet","score":0.5268358588218689},{"id":"https://openalex.org/keywords/boosting","display_name":"Boosting (machine learning)","score":0.4567079246044159},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.4371919333934784},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.4179137349128723},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.2500862777233124},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.24501073360443115}],"concepts":[{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.8095428943634033},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.806485116481781},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.5712661147117615},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5655012130737305},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.5268358588218689},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.4567079246044159},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.4371919333934784},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.4179137349128723},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2500862777233124},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.24501073360443115},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icsmc.2009.5346290","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icsmc.2009.5346290","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE International Conference on Systems, Man and Cybernetics","raw_type":"proceedings-article"},{"id":"pmh:oai:digital.library.adelaide.edu.au:2440/68615","is_oa":false,"landing_page_url":"http://hdl.handle.net/2440/68615","pdf_url":null,"source":{"id":"https://openalex.org/S4306401835","display_name":"Adelaide Research & Scholarship (AR&S) (University of Adelaide)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I5681781","host_organization_name":"The University of Adelaide","host_organization_lineage":["https://openalex.org/I5681781"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://dx.doi.org/10.1109/icsmc.2009.5346290","raw_type":"Conference paper"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W1599428996","https://openalex.org/W1956559956","https://openalex.org/W1988790447","https://openalex.org/W2005422315","https://openalex.org/W2032210760","https://openalex.org/W2048679005","https://openalex.org/W2087788978","https://openalex.org/W2098162425","https://openalex.org/W2125052648","https://openalex.org/W2156909104","https://openalex.org/W2325227998","https://openalex.org/W2535800192","https://openalex.org/W4244952642","https://openalex.org/W6635848021"],"related_works":["https://openalex.org/W2125652721","https://openalex.org/W1540371141","https://openalex.org/W4231274751","https://openalex.org/W1549363203","https://openalex.org/W2154063878","https://openalex.org/W2556012038","https://openalex.org/W1489772951","https://openalex.org/W1538046993","https://openalex.org/W2571255492","https://openalex.org/W4239293476"],"abstract_inverted_index":{"The":[0],"World":[1],"Wide":[2],"Web":[3,34,50,58,78,93,100,136],"provides":[4],"great":[5],"convenience":[6],"for":[7,92,121,134],"users":[8],"to":[9,31,55],"obtain":[10],"information.":[11,28],"However,":[12,69],"there":[13],"exists":[14],"much":[15],"harmful":[16,33,49,135],"information":[17],"on":[18,36],"the":[19,37,46,70,142],"Internet,":[20],"such":[21],"as":[22],"pornographic":[23],"content":[24],"and":[25],"prohibited":[26],"drugs'":[27],"Thus,":[29],"how":[30],"filter":[32],"pages":[35,79],"Internet":[38],"is":[39,53,80,102,119,132],"quite":[40],"an":[41],"important":[42],"issue.":[43],"In":[44,96],"general,":[45],"problem":[47],"of":[48,57,64,72,77,106,144],"page":[51,59,94,101,137],"filtering":[52],"converted":[54],"that":[56],"classification,":[60],"which":[61],"needs":[62],"plenty":[63],"well":[65,124],"labeled":[66,125],"training":[67,126],"samples.":[68,127],"cost":[71],"labeling":[73],"a":[74,89,115,129],"large":[75],"set":[76],"very":[81],"expensive.":[82],"To":[83],"address":[84],"this":[85,97],"problem,":[86],"we":[87],"adopt":[88],"semi-supervised":[90,116],"framework":[91],"filtering.":[95,138],"framework,":[98],"each":[99],"represented":[103],"by":[104],"bags":[105],"different":[107],"features,":[108],"extracted":[109],"using":[110],"its":[111],"HTML":[112],"structure.":[113],"Then":[114],"learning":[117],"strategy":[118],"taken":[120],"efficiently":[122],"obtaining":[123],"Finally,":[128],"boosting":[130],"classifier":[131],"utilized":[133],"Experiments":[139],"have":[140],"demonstrated":[141],"effectiveness":[143],"our":[145],"framework.":[146]},"counts_by_year":[{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
