{"id":"https://openalex.org/W3027910261","doi":"https://doi.org/10.1109/access.2020.2995516","title":"Improving Online Clustering of Chinese Technology Web News With Bag-of-Near-Synonyms","display_name":"Improving Online Clustering of Chinese Technology Web News With Bag-of-Near-Synonyms","publication_year":2020,"publication_date":"2020-01-01","ids":{"openalex":"https://openalex.org/W3027910261","doi":"https://doi.org/10.1109/access.2020.2995516","mag":"3027910261"},"language":"en","primary_location":{"id":"doi:10.1109/access.2020.2995516","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2020.2995516","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/8948470/09095310.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://ieeexplore.ieee.org/ielx7/6287639/8948470/09095310.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100442958","display_name":"Zhe Zhang","orcid":"https://orcid.org/0000-0001-9292-1162"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zhe Zhang","raw_affiliation_strings":["Science and Technology on Information Systems Engineering Laboratory, College of Systems Engineering, National University of Defense Technology, Changsha, China"],"raw_orcid":"https://orcid.org/0000-0001-9292-1162","affiliations":[{"raw_affiliation_string":"Science and Technology on Information Systems Engineering Laboratory, College of Systems Engineering, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100420755","display_name":"Le Chen","orcid":"https://orcid.org/0000-0003-3789-2578"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Le Chen","raw_affiliation_strings":["Institute of Systems Engineering, Academy of Military Science, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-3789-2578","affiliations":[{"raw_affiliation_string":"Institute of Systems Engineering, Academy of Military Science, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100651696","display_name":"Fengjing Yin","orcid":"https://orcid.org/0000-0002-6045-0236"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fengjing Yin","raw_affiliation_strings":["Science and Technology on Information Systems Engineering Laboratory, College of Systems Engineering, National University of Defense Technology, Changsha, China"],"raw_orcid":"https://orcid.org/0000-0002-6045-0236","affiliations":[{"raw_affiliation_string":"Science and Technology on Information Systems Engineering Laboratory, College of Systems Engineering, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100327595","display_name":"Xin Zhang","orcid":"https://orcid.org/0000-0003-2954-2076"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xin Zhang","raw_affiliation_strings":["Science and Technology on Information Systems Engineering Laboratory, College of Systems Engineering, National University of Defense Technology, Changsha, China"],"raw_orcid":"https://orcid.org/0000-0003-2954-2076","affiliations":[{"raw_affiliation_string":"Science and Technology on Information Systems Engineering Laboratory, College of Systems Engineering, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5055715993","display_name":"Lixiang Guo","orcid":"https://orcid.org/0000-0003-0276-5077"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lixiang Guo","raw_affiliation_strings":["Science and Technology on Information Systems Engineering Laboratory, College of Systems Engineering, National University of Defense Technology, Changsha, China"],"raw_orcid":"https://orcid.org/0000-0003-0276-5077","affiliations":[{"raw_affiliation_string":"Science and Technology on Information Systems Engineering Laboratory, College of Systems Engineering, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5100442958"],"corresponding_institution_ids":["https://openalex.org/I170215575"],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":0.8352,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.8039882,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":"8","issue":null,"first_page":"94245","last_page":"94257"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","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/T12016","display_name":"Web Data Mining and Analysis","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":0.9980000257492065,"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/T10064","display_name":"Complex Network Analysis Techniques","score":0.9970999956130981,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8163683414459229},{"id":"https://openalex.org/keywords/tf\u2013idf","display_name":"tf\u2013idf","score":0.7594407796859741},{"id":"https://openalex.org/keywords/latent-dirichlet-allocation","display_name":"Latent Dirichlet allocation","score":0.6356132626533508},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.6291055083274841},{"id":"https://openalex.org/keywords/synonym","display_name":"Synonym (taxonomy)","score":0.590275764465332},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.556179940700531},{"id":"https://openalex.org/keywords/word2vec","display_name":"Word2vec","score":0.5441327095031738},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4714689552783966},{"id":"https://openalex.org/keywords/document-clustering","display_name":"Document clustering","score":0.4604080617427826},{"id":"https://openalex.org/keywords/topic-model","display_name":"Topic model","score":0.4526814818382263},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.42690715193748474},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41974830627441406},{"id":"https://openalex.org/keywords/dimension","display_name":"Dimension (graph theory)","score":0.4124666154384613},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.35556113719940186},{"id":"https://openalex.org/keywords/term","display_name":"Term (time)","score":0.290514200925827},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10881781578063965}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8163683414459229},{"id":"https://openalex.org/C81758059","wikidata":"https://www.wikidata.org/wiki/Q796584","display_name":"tf\u2013idf","level":3,"score":0.7594407796859741},{"id":"https://openalex.org/C500882744","wikidata":"https://www.wikidata.org/wiki/Q269236","display_name":"Latent Dirichlet allocation","level":3,"score":0.6356132626533508},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6291055083274841},{"id":"https://openalex.org/C173483453","wikidata":"https://www.wikidata.org/wiki/Q1040689","display_name":"Synonym (taxonomy)","level":3,"score":0.590275764465332},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.556179940700531},{"id":"https://openalex.org/C2776461190","wikidata":"https://www.wikidata.org/wiki/Q22673982","display_name":"Word2vec","level":3,"score":0.5441327095031738},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4714689552783966},{"id":"https://openalex.org/C177937566","wikidata":"https://www.wikidata.org/wiki/Q4223102","display_name":"Document clustering","level":3,"score":0.4604080617427826},{"id":"https://openalex.org/C171686336","wikidata":"https://www.wikidata.org/wiki/Q3532085","display_name":"Topic model","level":2,"score":0.4526814818382263},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.42690715193748474},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41974830627441406},{"id":"https://openalex.org/C33676613","wikidata":"https://www.wikidata.org/wiki/Q13415176","display_name":"Dimension (graph theory)","level":2,"score":0.4124666154384613},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.35556113719940186},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.290514200925827},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10881781578063965},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C157369684","wikidata":"https://www.wikidata.org/wiki/Q34740","display_name":"Genus","level":2,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"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/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2020.2995516","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2020.2995516","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/8948470/09095310.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:36689a5d2cf348f3b0e490739860b37e","is_oa":true,"landing_page_url":"https://doaj.org/article/36689a5d2cf348f3b0e490739860b37e","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 8, Pp 94245-94257 (2020)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2020.2995516","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2020.2995516","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/8948470/09095310.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Climate action","id":"https://metadata.un.org/sdg/13","score":0.6399999856948853}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3027910261.pdf","grobid_xml":"https://content.openalex.org/works/W3027910261.grobid-xml"},"referenced_works_count":52,"referenced_works":["https://openalex.org/W21361513","https://openalex.org/W125546202","https://openalex.org/W1594112393","https://openalex.org/W1612003148","https://openalex.org/W1880262756","https://openalex.org/W1965456679","https://openalex.org/W1989993068","https://openalex.org/W1998224037","https://openalex.org/W2037001658","https://openalex.org/W2056167975","https://openalex.org/W2064988570","https://openalex.org/W2094043862","https://openalex.org/W2110642088","https://openalex.org/W2114431967","https://openalex.org/W2131744502","https://openalex.org/W2135909747","https://openalex.org/W2138107145","https://openalex.org/W2141585940","https://openalex.org/W2147152072","https://openalex.org/W2165236847","https://openalex.org/W2165599843","https://openalex.org/W2174706414","https://openalex.org/W2350919801","https://openalex.org/W2378886430","https://openalex.org/W2528222195","https://openalex.org/W2540832166","https://openalex.org/W2618694545","https://openalex.org/W2743024853","https://openalex.org/W2896457183","https://openalex.org/W2942765639","https://openalex.org/W2949547296","https://openalex.org/W2954075271","https://openalex.org/W2963341956","https://openalex.org/W2974273066","https://openalex.org/W2998704965","https://openalex.org/W3012193977","https://openalex.org/W3210120707","https://openalex.org/W4234917632","https://openalex.org/W4294170691","https://openalex.org/W6636440780","https://openalex.org/W6639619044","https://openalex.org/W6679775712","https://openalex.org/W6680392773","https://openalex.org/W6680532216","https://openalex.org/W6682691769","https://openalex.org/W6684489972","https://openalex.org/W6729009247","https://openalex.org/W6755207826","https://openalex.org/W6759216221","https://openalex.org/W6767913650","https://openalex.org/W6802852670","https://openalex.org/W7024322102"],"related_works":["https://openalex.org/W2769501189","https://openalex.org/W4315588616","https://openalex.org/W4312773271","https://openalex.org/W2888805565","https://openalex.org/W2962686197","https://openalex.org/W2207653751","https://openalex.org/W2594674086","https://openalex.org/W4309228610","https://openalex.org/W3204681432","https://openalex.org/W4294597112"],"abstract_inverted_index":{"In":[0,150],"the":[1,23,61,67,114,138,143],"Internet":[2],"era,":[3],"online":[4,156],"clustering":[5,157],"of":[6,117,145,158,192,205],"technology":[7,17,160],"web":[8,161],"news":[9,24,162],"can":[10],"help":[11],"discover":[12],"scientific":[13],"breakthroughs":[14],"and":[15,49,76,79,119,140,163,201,208],"grasp":[16],"trends.":[18],"To":[19,54,107],"do":[20],"that":[21,181],"automatically,":[22],"documents":[25],"to":[26,69,81,98,128,133,147,155],"be":[27,30],"clustered":[28],"must":[29],"represented":[31],"appropriately":[32],"with":[33,85],"numerical":[34],"vectors.":[35],"However,":[36],"traditional":[37],"representations":[38],"such":[39],"as":[40,137],"Term":[41],"Frequency-Inverse":[42,88],"Document":[43,89],"Frequency":[44,90],"(TF-IDF)":[45],"cannot":[46],"distinguish":[47],"near-synonyms":[48],"may":[50],"cause":[51],"\u201cdimension":[52],"disaster.\u201d":[53],"overcome":[55],"these":[56],"problems,":[57],"this":[58],"article":[59],"proposes":[60],"Bag-of-Near-Synonyms":[62],"(BoNS)":[63],"model":[64,183],"based":[65],"on":[66,174],"idea":[68],"construct":[70],"near-synonym":[71,100,131],"sets":[72],"using":[73],"word":[74,193],"embeddings":[75],"agglomerative":[77],"clustering,":[78],"then":[80],"represent":[82],"a":[83,86,99,104,125,134,175],"document":[84],"Set":[87],"(SF-IDF)":[91],"vector":[92],"in":[93,203],"which":[94,123],"each":[95,130],"dimension":[96],"corresponds":[97],"set":[101,132],"rather":[102],"than":[103],"single":[105],"word.":[106],"speed":[108],"up":[109],"computation,":[110],"we":[111,152],"further":[112],"propose":[113,164],"hashed":[115],"version":[116],"SF-IDF":[118],"name":[120],"it":[121],"hSF-IDF,":[122],"employs":[124],"hash":[126],"function":[127],"map":[129],"unique":[135],"number":[136],"key":[139],"hence":[141],"reduces":[142],"computation":[144],"SF":[146],"linear":[148],"time.":[149],"addition,":[151],"apply":[153],"hSF-IDF":[154],"Chinese":[159],"an":[165],"improved":[166],"batch-based":[167],"method.":[168],"Extensive":[169],"experiments":[170],"have":[171],"been":[172],"conducted":[173],"real-world":[176],"dataset.":[177],"The":[178],"results":[179],"show":[180],"our":[182],"outperforms":[184],"some":[185],"strong":[186],"baselines":[187],"including":[188],"TF-IDF,":[189],"average":[190],"pooling":[191],"or":[194],"character":[195],"embeddings,":[196],"Latent":[197],"Dirichlet":[198],"Allocation":[199],"(LDA),":[200],"bag-of-concepts":[202],"terms":[204],"both":[206],"accuracy":[207],"efficiency.":[209]},"counts_by_year":[{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1}],"updated_date":"2026-05-06T08:25:59.206177","created_date":"2025-10-10T00:00:00"}