{"id":"https://openalex.org/W3117229956","doi":"https://doi.org/10.1109/uemcon51285.2020.9298131","title":"A Feasible Chinese Text Data Preprocessing Strategy","display_name":"A Feasible Chinese Text Data Preprocessing Strategy","publication_year":2020,"publication_date":"2020-10-28","ids":{"openalex":"https://openalex.org/W3117229956","doi":"https://doi.org/10.1109/uemcon51285.2020.9298131","mag":"3117229956"},"language":"en","primary_location":{"id":"doi:10.1109/uemcon51285.2020.9298131","is_oa":false,"landing_page_url":"https://doi.org/10.1109/uemcon51285.2020.9298131","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 11th IEEE Annual Ubiquitous Computing, Electronics & Mobile Communication Conference (UEMCON)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5100739647","display_name":"Jingang Liu","orcid":"https://orcid.org/0000-0001-9277-6428"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingang Liu","raw_affiliation_strings":["School of Computer Science and Engineering Beihang University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035296513","display_name":"Chunhe Xia","orcid":"https://orcid.org/0000-0003-4424-8449"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chunhe Xia","raw_affiliation_strings":["School of Computer Science and Engineering Beihang University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057240245","display_name":"Haihua Yan","orcid":null},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haihua Yan","raw_affiliation_strings":["School of Computer Science and Engineering Beihang University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034843347","display_name":"Jie Sun","orcid":"https://orcid.org/0000-0002-5125-9149"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jie Sun","raw_affiliation_strings":["School of Computer Science and Engineering Beihang University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I82880672"],"apc_list":null,"apc_paid":null,"fwci":0.5848,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.68194267,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"0234","last_page":"0239"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9983999729156494,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9983999729156494,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9930999875068665,"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/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9908000230789185,"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":0.8030163645744324},{"id":"https://openalex.org/keywords/data-pre-processing","display_name":"Data pre-processing","score":0.7781258821487427},{"id":"https://openalex.org/keywords/raw-data","display_name":"Raw data","score":0.7731964588165283},{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.7722316980361938},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.6363359093666077},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5976608395576477},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5085042715072632},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.46421077847480774},{"id":"https://openalex.org/keywords/expression","display_name":"Expression (computer science)","score":0.45349371433258057},{"id":"https://openalex.org/keywords/data-processing","display_name":"Data processing","score":0.44472798705101013},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.09562951326370239}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8030163645744324},{"id":"https://openalex.org/C10551718","wikidata":"https://www.wikidata.org/wiki/Q5227332","display_name":"Data pre-processing","level":2,"score":0.7781258821487427},{"id":"https://openalex.org/C132964779","wikidata":"https://www.wikidata.org/wiki/Q2110223","display_name":"Raw data","level":2,"score":0.7731964588165283},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.7722316980361938},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.6363359093666077},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5976608395576477},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5085042715072632},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.46421077847480774},{"id":"https://openalex.org/C90559484","wikidata":"https://www.wikidata.org/wiki/Q778379","display_name":"Expression (computer science)","level":2,"score":0.45349371433258057},{"id":"https://openalex.org/C138827492","wikidata":"https://www.wikidata.org/wiki/Q6661985","display_name":"Data processing","level":2,"score":0.44472798705101013},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.09562951326370239},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/uemcon51285.2020.9298131","is_oa":false,"landing_page_url":"https://doi.org/10.1109/uemcon51285.2020.9298131","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 11th IEEE Annual Ubiquitous Computing, Electronics & Mobile Communication Conference (UEMCON)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6200000047683716,"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320326978","display_name":"State Key Laboratory of Software Development Environment","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W1969403436","https://openalex.org/W1970888939","https://openalex.org/W1982277130","https://openalex.org/W1992399912","https://openalex.org/W1999719662","https://openalex.org/W2002310016","https://openalex.org/W2020791078","https://openalex.org/W2058181105","https://openalex.org/W2116984840","https://openalex.org/W2123409753","https://openalex.org/W2124316743","https://openalex.org/W2152775624","https://openalex.org/W2249511864","https://openalex.org/W2250221183","https://openalex.org/W2359934671","https://openalex.org/W2537388533","https://openalex.org/W2539006980","https://openalex.org/W2785286326","https://openalex.org/W2793148796","https://openalex.org/W2888124146","https://openalex.org/W2918629080","https://openalex.org/W2993259699","https://openalex.org/W3103352455","https://openalex.org/W6691339522"],"related_works":["https://openalex.org/W2989490741","https://openalex.org/W2367545121","https://openalex.org/W4248881655","https://openalex.org/W2482165163","https://openalex.org/W3092506759","https://openalex.org/W138569904","https://openalex.org/W2390914021","https://openalex.org/W3010890513","https://openalex.org/W3138271675","https://openalex.org/W4220726286"],"abstract_inverted_index":{"With":[0],"the":[1,13,17,28,34,47,56,70,95,105,122,144],"rapid":[2,14],"rise":[3],"of":[4,16,30,97,108],"artificial":[5],"intelligence":[6],"technologies":[7],"such":[8],"as":[9],"machine":[10],"learning":[11],"and":[12,22,44,85,101,115,152],"development":[15],"big":[18],"data":[19,31,60,75,81,99,124,139],"industry,":[20],"more":[21,23,40],"attention":[24],"is":[25,39,50,63],"paid":[26],"to":[27,54,78,92,104,134],"use":[29],"itself,":[32],"especially":[33],"Chinese":[35,58,98,109,117,137,159],"text":[36,59,118,138,160],"data,":[37,110],"which":[38],"complex":[41],"in":[42,46,82],"expression":[43],"richer":[45],"information.":[48],"It":[49],"a":[51,113,154],"necessary":[52],"step":[53],"process":[55,135],"raw":[57,136],"before":[61],"it":[62],"used":[64],"for":[65,73,157],"specific":[66,86],"application":[67,87,106],"tasks.":[68,88],"However,":[69],"current":[71],"strategies":[72],"processing":[74,100],"are":[76],"generally":[77],"deal":[79],"with":[80],"different":[83],"fields":[84],"In":[89],"this":[90],"paper,":[91],"further":[93],"improve":[94],"quality":[96],"give":[102],"play":[103],"value":[107],"we":[111],"propose":[112],"general":[114],"feasible":[116],"preprocessing":[119,125,158],"strategy,":[120],"named":[121],"multi-level":[123],"strategy":[126,129],"(MLDPS).":[127],"This":[128],"uses":[130],"four":[131],"effective":[132],"links":[133],"systematically.":[140],"We":[141],"believe":[142],"that":[143],"proposed":[145],"MLDPS":[146],"has":[147],"relatively":[148],"strong":[149],"practical":[150],"significance,":[151],"provides":[153],"better":[155],"idea":[156],"data.":[161]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}