{"id":"https://openalex.org/W1987796963","doi":"https://doi.org/10.1631/jzus.c1100373","title":"Short text classification based on strong feature thesaurus","display_name":"Short text classification based on strong feature thesaurus","publication_year":2012,"publication_date":"2012-09-01","ids":{"openalex":"https://openalex.org/W1987796963","doi":"https://doi.org/10.1631/jzus.c1100373","mag":"1987796963"},"language":"en","primary_location":{"id":"doi:10.1631/jzus.c1100373","is_oa":false,"landing_page_url":"https://doi.org/10.1631/jzus.c1100373","pdf_url":null,"source":{"id":"https://openalex.org/S199067057","display_name":"Journal of Zhejiang University SCIENCE C","issn_l":"1869-1951","issn":["1869-1951","1869-196X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311937","host_organization_name":"Zhejiang University Press","host_organization_lineage":["https://openalex.org/P4310311937"],"host_organization_lineage_names":["Zhejiang University Press"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Zhejiang University SCIENCE C","raw_type":"journal-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/A5061687395","display_name":"Bing-kun Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Bing-kun Wang","raw_affiliation_strings":["Information Cognitive and Intelligent System Research Institute, Department of Electronic and Engineering, Tsinghua University, Beijing, 100084, China","Information Technology National Laboratory, Tsinghua University, Beijing, 100084, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Information Cognitive and Intelligent System Research Institute, Department of Electronic and Engineering, Tsinghua University, Beijing, 100084, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Information Technology National Laboratory, Tsinghua University, Beijing, 100084, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100768896","display_name":"Yongfeng Huang","orcid":"https://orcid.org/0000-0003-3825-2230"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yong-feng Huang","raw_affiliation_strings":["Information Cognitive and Intelligent System Research Institute, Department of Electronic and Engineering, Tsinghua University, Beijing, 100084, China","Information Technology National Laboratory, Tsinghua University, Beijing, 100084, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Information Cognitive and Intelligent System Research Institute, Department of Electronic and Engineering, Tsinghua University, Beijing, 100084, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Information Technology National Laboratory, Tsinghua University, Beijing, 100084, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076722675","display_name":"Wanxia Yang","orcid":"https://orcid.org/0000-0001-8175-7045"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wan-xia Yang","raw_affiliation_strings":["Information Cognitive and Intelligent System Research Institute, Department of Electronic and Engineering, Tsinghua University, Beijing, 100084, China","Information Technology National Laboratory, Tsinghua University, Beijing, 100084, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Information Cognitive and Intelligent System Research Institute, Department of Electronic and Engineering, Tsinghua University, Beijing, 100084, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Information Technology National Laboratory, Tsinghua University, Beijing, 100084, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100600286","display_name":"Xing Li","orcid":"https://orcid.org/0000-0002-5306-1742"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xing Li","raw_affiliation_strings":["Information Cognitive and Intelligent System Research Institute, Department of Electronic and Engineering, Tsinghua University, Beijing, 100084, China","Information Technology National Laboratory, Tsinghua University, Beijing, 100084, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Information Cognitive and Intelligent System Research Institute, Department of Electronic and Engineering, Tsinghua University, Beijing, 100084, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Information Technology National Laboratory, Tsinghua University, Beijing, 100084, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5061687395"],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":4.7843,"has_fulltext":false,"cited_by_count":38,"citation_normalized_percentile":{"value":0.94719009,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"13","issue":"9","first_page":"649","last_page":"659"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9940000176429749,"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":0.9940000176429749,"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":0.9894000291824341,"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/T10028","display_name":"Topic Modeling","score":0.9829999804496765,"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/thesaurus","display_name":"Thesaurus","score":0.8570772409439087},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7368332147598267},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6061824560165405},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5970770716667175},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.47639670968055725},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.43343642354011536},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40653958916664124},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.08058446645736694},{"id":"https://openalex.org/keywords/philosophy","display_name":"Philosophy","score":0.04947122931480408}],"concepts":[{"id":"https://openalex.org/C2778698081","wikidata":"https://www.wikidata.org/wiki/Q179797","display_name":"Thesaurus","level":2,"score":0.8570772409439087},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7368332147598267},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6061824560165405},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5970770716667175},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.47639670968055725},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.43343642354011536},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40653958916664124},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.08058446645736694},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.04947122931480408}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1631/jzus.c1100373","is_oa":false,"landing_page_url":"https://doi.org/10.1631/jzus.c1100373","pdf_url":null,"source":{"id":"https://openalex.org/S199067057","display_name":"Journal of Zhejiang University SCIENCE C","issn_l":"1869-1951","issn":["1869-1951","1869-196X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311937","host_organization_name":"Zhejiang University Press","host_organization_lineage":["https://openalex.org/P4310311937"],"host_organization_lineage_names":["Zhejiang University Press"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Zhejiang University SCIENCE C","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8399999737739563,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W103965747","https://openalex.org/W1511986666","https://openalex.org/W1532325895","https://openalex.org/W1570448133","https://openalex.org/W1573190978","https://openalex.org/W1646006088","https://openalex.org/W1880262756","https://openalex.org/W1993972863","https://openalex.org/W2001082470","https://openalex.org/W2015136191","https://openalex.org/W2030129670","https://openalex.org/W2055400882","https://openalex.org/W2100335205","https://openalex.org/W2110591510","https://openalex.org/W2121184547","https://openalex.org/W2123160630","https://openalex.org/W2149393279","https://openalex.org/W2161443453","https://openalex.org/W2169821025","https://openalex.org/W2171836785","https://openalex.org/W2747986893","https://openalex.org/W3147705998","https://openalex.org/W4213009331","https://openalex.org/W4254542057","https://openalex.org/W6634191187","https://openalex.org/W6639619044","https://openalex.org/W6676781583"],"related_works":["https://openalex.org/W2046824966","https://openalex.org/W2358573687","https://openalex.org/W2100136642","https://openalex.org/W186704260","https://openalex.org/W1496588992","https://openalex.org/W266409346","https://openalex.org/W2075838610","https://openalex.org/W2184026322","https://openalex.org/W4386159726","https://openalex.org/W4213277595"],"abstract_inverted_index":{"Data":[0],"sparseness,":[1],"the":[2,13,17,21,38,49,73,102,134],"evident":[3],"characteristic":[4],"of":[5,16,23,52],"short":[6,24,123],"text,":[7],"has":[8,31],"always":[9],"been":[10,32],"regarded":[11],"as":[12],"main":[14],"cause":[15],"low":[18,60],"accuracy":[19,104],"in":[20,34,100,121],"classification":[22,61,103],"texts":[25],"using":[26],"statistical":[27],"methods.":[28],"Intensive":[29],"research":[30],"conducted":[33],"this":[35,64],"area":[36],"during":[37],"past":[39],"decade.":[40],"However,":[41],"most":[42],"researchers":[43],"failed":[44],"to":[45,59,71,97,112],"notice":[46],"that":[47,127],"ignoring":[48],"semantic":[50],"importance":[51],"certain":[53],"feature":[54,79,98],"terms":[55,99],"might":[56],"also":[57],"contribute":[58],"accuracy.":[62],"In":[63],"paper":[65],"we":[66],"present":[67],"a":[68,77],"new":[69],"method":[70,110],"tackle":[72],"problem":[74],"by":[75],"building":[76],"strong":[78],"thesaurus":[80],"(SFT)":[81],"based":[82],"on":[83],"latent":[84],"Dirichlet":[85],"allocation":[86],"(LDA)":[87],"and":[88,142],"information":[89],"gain":[90],"(IG)":[91],"models.":[92],"By":[93],"giving":[94],"larger":[95],"weights":[96],"SFT,":[101],"can":[105],"be":[106,113],"improved.":[107],"Specifically,":[108],"our":[109,128],"appeared":[111],"more":[114,117],"effective":[115],"with":[116,133],"detailed":[118],"classification.":[119],"Experiments":[120],"two":[122],"text":[124],"datasets":[125],"demonstrate":[126],"approach":[129],"achieved":[130],"improvement":[131],"compared":[132],"state-of-the-art":[135],"methods":[136],"including":[137],"support":[138],"vector":[139],"machine":[140],"(SVM)":[141],"Na\u00efve":[143],"Bayes":[144],"Multinomial.":[145]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":2},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":6},{"year":2017,"cited_by_count":9},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":4},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
