{"id":"https://openalex.org/W2046934872","doi":"https://doi.org/10.5539/cis.v3n2p268","title":"The Comparison of SOM and K-means for Text Clustering","display_name":"The Comparison of SOM and K-means for Text Clustering","publication_year":2010,"publication_date":"2010-04-18","ids":{"openalex":"https://openalex.org/W2046934872","doi":"https://doi.org/10.5539/cis.v3n2p268","mag":"2046934872"},"language":"en","primary_location":{"id":"doi:10.5539/cis.v3n2p268","is_oa":true,"landing_page_url":"https://doi.org/10.5539/cis.v3n2p268","pdf_url":"https://ccsenet.org/journal/index.php/cis/article/download/6010/4836","source":{"id":"https://openalex.org/S2764452479","display_name":"Computer and Information Science","issn_l":"1913-8989","issn":["1913-8989","1913-8997"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310322531","host_organization_name":"Canadian Center of Science and Education","host_organization_lineage":["https://openalex.org/P4310322531"],"host_organization_lineage_names":["Canadian Center of Science and Education"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computer and Information Science","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://ccsenet.org/journal/index.php/cis/article/download/6010/4836","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5082435778","display_name":"Yiheng Chen","orcid":"https://orcid.org/0009-0009-8726-4589"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yiheng Chen","raw_affiliation_strings":["School of Computer Science and Technology, Harbin Institute of Technology PO box 321, Harbin, 150001, China","[Sch. of Comput. Sci. & Technol., Harbin Inst. of Technol.]"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Harbin Institute of Technology PO box 321, Harbin, 150001, China","institution_ids":["https://openalex.org/I204983213"]},{"raw_affiliation_string":"[Sch. of Comput. Sci. & Technol., Harbin Inst. of Technol.]","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029198852","display_name":"Bing Qin","orcid":"https://orcid.org/0000-0003-2842-9637"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bing Qin","raw_affiliation_strings":["School of Computer Science and Technology, Harbin Institute of Technology PO box 321, Harbin, 150001, China","[Sch. of Comput. Sci. & Technol., Harbin Inst. of Technol.]"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Harbin Institute of Technology PO box 321, Harbin, 150001, China","institution_ids":["https://openalex.org/I204983213"]},{"raw_affiliation_string":"[Sch. of Comput. Sci. & Technol., Harbin Inst. of Technol.]","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100418165","display_name":"Ting Liu","orcid":"https://orcid.org/0000-0003-3489-4578"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ting Liu","raw_affiliation_strings":["School of Computer Science and Technology, Harbin Institute of Technology PO box 321, Harbin, 150001, China","[Sch. of Comput. Sci. & Technol., Harbin Inst. of Technol.]"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Harbin Institute of Technology PO box 321, Harbin, 150001, China","institution_ids":["https://openalex.org/I204983213"]},{"raw_affiliation_string":"[Sch. of Comput. Sci. & Technol., Harbin Inst. of Technol.]","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101881571","display_name":"Yuanchao Liu","orcid":"https://orcid.org/0009-0007-0430-7658"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuanchao Liu","raw_affiliation_strings":["School of Computer Science and Technology, Harbin Institute of Technology Harbin, 150001, China","[Sch. of Comput. Sci. & Technol., Harbin Inst. of Technol.]"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Harbin Institute of Technology Harbin, 150001, China","institution_ids":["https://openalex.org/I204983213"]},{"raw_affiliation_string":"[Sch. of Comput. Sci. & Technol., Harbin Inst. of Technol.]","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100359839","display_name":"Sheng Li","orcid":"https://orcid.org/0000-0003-1205-8632"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Sheng Li","raw_affiliation_strings":["School of Computer Science and Technology, Harbin Institute of Technology PO box 321, Harbin, 150001, China","[Sch. of Comput. Sci. & Technol., Harbin Inst. of Technol.]"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Harbin Institute of Technology PO box 321, Harbin, 150001, China","institution_ids":["https://openalex.org/I204983213"]},{"raw_affiliation_string":"[Sch. of Comput. Sci. & Technol., Harbin Inst. of Technol.]","institution_ids":["https://openalex.org/I204983213"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5082435778"],"corresponding_institution_ids":["https://openalex.org/I204983213"],"apc_list":null,"apc_paid":null,"fwci":2.2552,"has_fulltext":true,"cited_by_count":31,"citation_normalized_percentile":{"value":0.89175641,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"3","issue":"2","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13734","display_name":"Advanced Computational Techniques and Applications","score":0.9878000020980835,"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/T13734","display_name":"Advanced Computational Techniques and Applications","score":0.9878000020980835,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9858999848365784,"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/T10538","display_name":"Data Mining Algorithms and Applications","score":0.983299970626831,"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":0.8846415281295776},{"id":"https://openalex.org/keywords/automatic-summarization","display_name":"Automatic summarization","score":0.8820247650146484},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.8185906410217285},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5616649389266968},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.528995156288147},{"id":"https://openalex.org/keywords/document-clustering","display_name":"Document clustering","score":0.4316740334033966},{"id":"https://openalex.org/keywords/layer","display_name":"Layer (electronics)","score":0.4141702353954315},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.38643237948417664},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3673117160797119},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3409474790096283},{"id":"https://openalex.org/keywords/topology","display_name":"Topology (electrical circuits)","score":0.32146626710891724},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.06556817889213562}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8846415281295776},{"id":"https://openalex.org/C170858558","wikidata":"https://www.wikidata.org/wiki/Q1394144","display_name":"Automatic summarization","level":2,"score":0.8820247650146484},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.8185906410217285},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5616649389266968},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.528995156288147},{"id":"https://openalex.org/C177937566","wikidata":"https://www.wikidata.org/wiki/Q4223102","display_name":"Document clustering","level":3,"score":0.4316740334033966},{"id":"https://openalex.org/C2779227376","wikidata":"https://www.wikidata.org/wiki/Q6505497","display_name":"Layer (electronics)","level":2,"score":0.4141702353954315},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.38643237948417664},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3673117160797119},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3409474790096283},{"id":"https://openalex.org/C184720557","wikidata":"https://www.wikidata.org/wiki/Q7825049","display_name":"Topology (electrical circuits)","level":2,"score":0.32146626710891724},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.06556817889213562},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.5539/cis.v3n2p268","is_oa":true,"landing_page_url":"https://doi.org/10.5539/cis.v3n2p268","pdf_url":"https://ccsenet.org/journal/index.php/cis/article/download/6010/4836","source":{"id":"https://openalex.org/S2764452479","display_name":"Computer and Information Science","issn_l":"1913-8989","issn":["1913-8989","1913-8997"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310322531","host_organization_name":"Canadian Center of Science and Education","host_organization_lineage":["https://openalex.org/P4310322531"],"host_organization_lineage_names":["Canadian Center of Science and Education"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computer and Information Science","raw_type":"journal-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.668.5185","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.668.5185","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://ccsenet.org/journal/index.php/cis/article/download/6010/4836/","raw_type":"text"}],"best_oa_location":{"id":"doi:10.5539/cis.v3n2p268","is_oa":true,"landing_page_url":"https://doi.org/10.5539/cis.v3n2p268","pdf_url":"https://ccsenet.org/journal/index.php/cis/article/download/6010/4836","source":{"id":"https://openalex.org/S2764452479","display_name":"Computer and Information Science","issn_l":"1913-8989","issn":["1913-8989","1913-8997"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310322531","host_organization_name":"Canadian Center of Science and Education","host_organization_lineage":["https://openalex.org/P4310322531"],"host_organization_lineage_names":["Canadian Center of Science and Education"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computer and Information Science","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2046934872.pdf","grobid_xml":"https://content.openalex.org/works/W2046934872.grobid-xml"},"referenced_works_count":21,"referenced_works":["https://openalex.org/W65738273","https://openalex.org/W1485231155","https://openalex.org/W1490573914","https://openalex.org/W1492327544","https://openalex.org/W1518342559","https://openalex.org/W1566139570","https://openalex.org/W1575476631","https://openalex.org/W1651093245","https://openalex.org/W1973867972","https://openalex.org/W1996764654","https://openalex.org/W2041565863","https://openalex.org/W2138745909","https://openalex.org/W2156985538","https://openalex.org/W2367654372","https://openalex.org/W2393742565","https://openalex.org/W2407272972","https://openalex.org/W2977003282","https://openalex.org/W4241122026","https://openalex.org/W6637231022","https://openalex.org/W6643677473","https://openalex.org/W6806421124"],"related_works":["https://openalex.org/W2366403280","https://openalex.org/W1495108544","https://openalex.org/W1795405792","https://openalex.org/W2899601636","https://openalex.org/W4254379378","https://openalex.org/W4206655101","https://openalex.org/W52853789","https://openalex.org/W4237592971","https://openalex.org/W2387982377","https://openalex.org/W4322720815"],"abstract_inverted_index":{"SOM":[0,45,78,121],"and":[1,38,56,85,95,114],"k-means":[2,66],"are":[3,53],"two":[4],"classical":[5],"methods":[6],"for":[7,90,103],"text":[8],"clustering.":[9],"In":[10],"this":[11],"paper":[12],"some":[13,104],"experiments":[14],"have":[15],"been":[16],"done":[17],"to":[18,40,58,69,124],"compare":[19],"their":[20],"performances.":[21],"The":[22,60],"sample":[23],"data":[24],"used":[25],"is":[26,36,46,67,79,122],"420":[27],"articles":[28],"which":[29],"come":[30],"from":[31],"different":[32],"topics.":[33],"K-means":[34],"method":[35],"simple":[37],"easy":[39,57],"implement;":[41],"the":[42,50,73,117],"structure":[43],"of":[44,77,83,92,109,120],"relatively":[47],"complex,":[48],"but":[49],"clustering":[51,75,118],"results":[52,62,119],"more":[54,101],"visual":[55],"comprehend.":[59],"comparison":[61],"also":[63,87],"show":[64],"that":[65,82],"sensitive":[68,123],"initiative":[70],"distribution,":[71],"whereas":[72,116],"overall":[74],"performance":[76],"better":[80],"than":[81],"k-means,":[84],"it":[86,100],"performs":[88],"well":[89],"detection":[91],"noisy":[93],"documents":[94],"topology":[96],"preservation,":[97],"thus":[98],"make":[99],"suitable":[102],"applications":[105],"such":[106],"as":[107],"navigation":[108],"document":[110],"collection,":[111],"multi-document":[112],"summarization":[113],"etc.":[115],"output":[125],"layer":[126],"topology.":[127]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":6},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":4},{"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"}
