{"id":"https://openalex.org/W1992369071","doi":"https://doi.org/10.1145/1458082.1458364","title":"Semi-supervised text categorization by active search","display_name":"Semi-supervised text categorization by active search","publication_year":2008,"publication_date":"2008-10-26","ids":{"openalex":"https://openalex.org/W1992369071","doi":"https://doi.org/10.1145/1458082.1458364","mag":"1992369071"},"language":"en","primary_location":{"id":"doi:10.1145/1458082.1458364","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1458082.1458364","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 ACM conference on Information and knowledge management","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/A5051227924","display_name":"Zenglin Xu","orcid":"https://orcid.org/0000-0001-5550-6461"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zenglin Xu","raw_affiliation_strings":["The Chinese University of Hong Kong, Shatin, N.T., Hong Kong","The Chinese University of Hong Kong, Shatin, N. T. Hong Kong"],"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong, Shatin, N.T., Hong Kong","institution_ids":["https://openalex.org/I177725633"]},{"raw_affiliation_string":"The Chinese University of Hong Kong, Shatin, N. T. Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069394608","display_name":"Rong Jin","orcid":"https://orcid.org/0000-0002-8797-4646"},"institutions":[{"id":"https://openalex.org/I87216513","display_name":"Michigan State University","ror":"https://ror.org/05hs6h993","country_code":"US","type":"education","lineage":["https://openalex.org/I87216513"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rong Jin","raw_affiliation_strings":["Michigan State University, East Lansing, MI, USA"],"affiliations":[{"raw_affiliation_string":"Michigan State University, East Lansing, MI, USA","institution_ids":["https://openalex.org/I87216513"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026022035","display_name":"Kaizhu Huang","orcid":"https://orcid.org/0000-0002-3034-9639"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kaizhu Huang","raw_affiliation_strings":["The Chinese University of Hong Kong, Shatin, N.T., Hong Kong","The Chinese University of Hong Kong, Shatin, N. T. Hong Kong"],"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong, Shatin, N.T., Hong Kong","institution_ids":["https://openalex.org/I177725633"]},{"raw_affiliation_string":"The Chinese University of Hong Kong, Shatin, N. T. Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069596903","display_name":"Michael R. Lyu","orcid":"https://orcid.org/0000-0002-3666-5798"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Michael R. Lyu","raw_affiliation_strings":["The Chinese University of Hong Kong, Shatin, N.T., Hong Kong","The Chinese University of Hong Kong, Shatin, N. T. Hong Kong"],"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong, Shatin, N.T., Hong Kong","institution_ids":["https://openalex.org/I177725633"]},{"raw_affiliation_string":"The Chinese University of Hong Kong, Shatin, N. T. Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5042251906","display_name":"Irwin King","orcid":"https://orcid.org/0000-0001-8106-6447"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Irwin King","raw_affiliation_strings":["The Chinese University of Hong Kong, Shatin, N.T., Hong Kong","The Chinese University of Hong Kong, Shatin, N. T. Hong Kong"],"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong, Shatin, N.T., Hong Kong","institution_ids":["https://openalex.org/I177725633"]},{"raw_affiliation_string":"The Chinese University of Hong Kong, Shatin, N. T. Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5051227924"],"corresponding_institution_ids":["https://openalex.org/I177725633"],"apc_list":null,"apc_paid":null,"fwci":2.2882,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":{"value":0.8927696,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1517","last_page":"1518"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9995999932289124,"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"}},"topics":[{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9995999932289124,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9864000082015991,"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/T11644","display_name":"Spam and Phishing Detection","score":0.9860000014305115,"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/categorization","display_name":"Categorization","score":0.8546959161758423},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8114079236984253},{"id":"https://openalex.org/keywords/text-categorization","display_name":"Text categorization","score":0.7289528250694275},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.6910925507545471},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6005477905273438},{"id":"https://openalex.org/keywords/search-engine","display_name":"Search engine","score":0.5393604636192322},{"id":"https://openalex.org/keywords/supervised-learning","display_name":"Supervised learning","score":0.49386197328567505},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43553340435028076},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3267921805381775}],"concepts":[{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.8546959161758423},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8114079236984253},{"id":"https://openalex.org/C2986744138","wikidata":"https://www.wikidata.org/wiki/Q302088","display_name":"Text categorization","level":3,"score":0.7289528250694275},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.6910925507545471},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6005477905273438},{"id":"https://openalex.org/C97854310","wikidata":"https://www.wikidata.org/wiki/Q19541","display_name":"Search engine","level":2,"score":0.5393604636192322},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.49386197328567505},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43553340435028076},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3267921805381775},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1458082.1458364","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1458082.1458364","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 ACM conference on Information and knowledge management","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.5699999928474426,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":5,"referenced_works":["https://openalex.org/W1479807131","https://openalex.org/W2142114717","https://openalex.org/W2148603752","https://openalex.org/W6681325634","https://openalex.org/W7071374342"],"related_works":["https://openalex.org/W2360898036","https://openalex.org/W2390857744","https://openalex.org/W2133651098","https://openalex.org/W2390698788","https://openalex.org/W2383063829","https://openalex.org/W2138922887","https://openalex.org/W2082678934","https://openalex.org/W2035261173","https://openalex.org/W2106892947","https://openalex.org/W2237299843"],"abstract_inverted_index":{"In":[0],"automated":[1],"text":[2,38,107,135],"categorization,":[3],"given":[4],"a":[5,20,35,71,81],"small":[6],"number":[7],"of":[8,73,94,104],"labeled":[9,55],"documents,":[10,75],"it":[11],"is":[12,24,41,90,120],"very":[13],"challenging,":[14],"if":[15],"not":[16],"impossible,":[17],"to":[18,26,57,66,122],"build":[19],"reliable":[21],"classifier":[22],"that":[23],"able":[25,121],"achieve":[27],"high":[28],"classification":[29,125],"accuracy.":[30],"To":[31,84],"address":[32],"this":[33,44,88,95],"problem,":[34],"novel":[36],"web-assisted":[37],"categorization":[39,108,136],"framework":[40,119],"proposed":[42,106,118],"in":[43],"paper.":[45],"Important":[46],"keywords":[47],"are":[48,63,77],"first":[49,92],"automatically":[50],"identified":[51],"from":[52,68],"the":[53,59,69,91,101,105,113,117,124,132],"available":[54],"documents":[56],"form":[58],"queries.":[60],"Search":[61],"engines":[62],"then":[64,78],"utilized":[65],"retrieve":[67],"Web":[70],"multitude":[72],"relevant":[74],"which":[76],"exploited":[79],"by":[80,127],"semi-supervised":[82],"framework.":[83],"our":[85],"best":[86],"knowledge,":[87],"work":[89],"study":[93,99],"kind.":[96],"Extensive":[97],"experimental":[98],"shows":[100],"encouraging":[102],"results":[103],"framework:":[109],"using":[110],"Google":[111],"as":[112],"web":[114],"search":[115],"engine,":[116],"reduce":[123],"error":[126],"30%":[128],"when":[129],"compared":[130],"with":[131],"state-of-the-art":[133],"supervised":[134],"method.":[137]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}