{"id":"https://openalex.org/W4415114209","doi":"https://doi.org/10.1007/s42979-025-04411-5","title":"Enhancing Segment-Based Bag of Clusters with Mixture Models and Late Chunking for Document Clustering","display_name":"Enhancing Segment-Based Bag of Clusters with Mixture Models and Late Chunking for Document Clustering","publication_year":2025,"publication_date":"2025-10-13","ids":{"openalex":"https://openalex.org/W4415114209","doi":"https://doi.org/10.1007/s42979-025-04411-5"},"language":"en","primary_location":{"id":"doi:10.1007/s42979-025-04411-5","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s42979-025-04411-5","pdf_url":null,"source":{"id":"https://openalex.org/S4210174798","display_name":"SN Computer Science","issn_l":"2661-8907","issn":["2661-8907","2662-995X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"SN Computer Science","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/A5114094720","display_name":"Quoc-Khang Tran","orcid":"https://orcid.org/0009-0000-2715-7647"},"institutions":[{"id":"https://openalex.org/I177733328","display_name":"Can Tho University","ror":"https://ror.org/0071qz696","country_code":"VN","type":"education","lineage":["https://openalex.org/I177733328"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Quoc-Khang Tran","raw_affiliation_strings":["College of Information and Communication Technology, Can Tho University, 94000, Can Tho, Vietnam"],"raw_orcid":"https://orcid.org/0009-0000-2715-7647","affiliations":[{"raw_affiliation_string":"College of Information and Communication Technology, Can Tho University, 94000, Can Tho, Vietnam","institution_ids":["https://openalex.org/I177733328"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5113776210","display_name":"Nguyen-Khang Pham","orcid":"https://orcid.org/0009-0005-6761-1636"},"institutions":[{"id":"https://openalex.org/I177733328","display_name":"Can Tho University","ror":"https://ror.org/0071qz696","country_code":"VN","type":"education","lineage":["https://openalex.org/I177733328"]}],"countries":["VN"],"is_corresponding":true,"raw_author_name":"Nguyen-Khang Pham","raw_affiliation_strings":["Graduate School, Can Tho University, 94000, Can Tho, Vietnam"],"raw_orcid":"https://orcid.org/0009-0005-6761-1636","affiliations":[{"raw_affiliation_string":"Graduate School, Can Tho University, 94000, Can Tho, Vietnam","institution_ids":["https://openalex.org/I177733328"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5113776210"],"corresponding_institution_ids":["https://openalex.org/I177733328"],"apc_list":{"value":2890,"currency":"USD","value_usd":2890},"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.10776135,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"6","issue":"7","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9991000294685364,"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":0.9991000294685364,"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/T10637","display_name":"Advanced Clustering Algorithms Research","score":0.9987999796867371,"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/T10203","display_name":"Recommender Systems and Techniques","score":0.9952999949455261,"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/cluster-analysis","display_name":"Cluster analysis","score":0.7732999920845032},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.6021000146865845},{"id":"https://openalex.org/keywords/hierarchical-clustering","display_name":"Hierarchical clustering","score":0.4632999897003174},{"id":"https://openalex.org/keywords/document-clustering","display_name":"Document clustering","score":0.454800009727478},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.450300008058548},{"id":"https://openalex.org/keywords/single-linkage-clustering","display_name":"Single-linkage clustering","score":0.4203000068664551},{"id":"https://openalex.org/keywords/brown-clustering","display_name":"Brown clustering","score":0.4147999882698059},{"id":"https://openalex.org/keywords/rand-index","display_name":"Rand index","score":0.41449999809265137},{"id":"https://openalex.org/keywords/granularity","display_name":"Granularity","score":0.4075999855995178}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.7732999920845032},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7332000136375427},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.6021000146865845},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5925999879837036},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.492900013923645},{"id":"https://openalex.org/C92835128","wikidata":"https://www.wikidata.org/wiki/Q1277447","display_name":"Hierarchical clustering","level":3,"score":0.4632999897003174},{"id":"https://openalex.org/C177937566","wikidata":"https://www.wikidata.org/wiki/Q4223102","display_name":"Document clustering","level":3,"score":0.454800009727478},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.450300008058548},{"id":"https://openalex.org/C22648726","wikidata":"https://www.wikidata.org/wiki/Q7523744","display_name":"Single-linkage clustering","level":5,"score":0.4203000068664551},{"id":"https://openalex.org/C167984511","wikidata":"https://www.wikidata.org/wiki/Q17003931","display_name":"Brown clustering","level":5,"score":0.4147999882698059},{"id":"https://openalex.org/C111442797","wikidata":"https://www.wikidata.org/wiki/Q7291446","display_name":"Rand index","level":3,"score":0.41449999809265137},{"id":"https://openalex.org/C177774035","wikidata":"https://www.wikidata.org/wiki/Q1246948","display_name":"Granularity","level":2,"score":0.4075999855995178},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3984000086784363},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.3937999904155731},{"id":"https://openalex.org/C94641424","wikidata":"https://www.wikidata.org/wiki/Q5172845","display_name":"Correlation clustering","level":3,"score":0.38920000195503235},{"id":"https://openalex.org/C152565575","wikidata":"https://www.wikidata.org/wiki/Q1124538","display_name":"Conditional random field","level":2,"score":0.3783999979496002},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.373199999332428},{"id":"https://openalex.org/C203357204","wikidata":"https://www.wikidata.org/wiki/Q1089605","display_name":"Chunking (psychology)","level":2,"score":0.3418000042438507},{"id":"https://openalex.org/C17212007","wikidata":"https://www.wikidata.org/wiki/Q5511111","display_name":"Fuzzy clustering","level":3,"score":0.3361000120639801},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.32989999651908875},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.30070000886917114},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.2881999909877777},{"id":"https://openalex.org/C186767784","wikidata":"https://www.wikidata.org/wiki/Q5162841","display_name":"Consensus clustering","level":5,"score":0.2784999907016754},{"id":"https://openalex.org/C148524875","wikidata":"https://www.wikidata.org/wiki/Q6975395","display_name":"F1 score","level":2,"score":0.27379998564720154},{"id":"https://openalex.org/C164866538","wikidata":"https://www.wikidata.org/wiki/Q367351","display_name":"Cluster (spacecraft)","level":2,"score":0.251800000667572},{"id":"https://openalex.org/C2775953691","wikidata":"https://www.wikidata.org/wiki/Q5013874","display_name":"CRFS","level":3,"score":0.2517000138759613}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s42979-025-04411-5","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s42979-025-04411-5","pdf_url":null,"source":{"id":"https://openalex.org/S4210174798","display_name":"SN Computer Science","issn_l":"2661-8907","issn":["2661-8907","2662-995X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"SN Computer Science","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W1506806321","https://openalex.org/W2013029404","https://openalex.org/W2129250947","https://openalex.org/W2222512263","https://openalex.org/W2558405088","https://openalex.org/W2889326414","https://openalex.org/W2970641574","https://openalex.org/W3000274722","https://openalex.org/W3035324702","https://openalex.org/W4235169531","https://openalex.org/W4243794628","https://openalex.org/W4246183800","https://openalex.org/W4300672471","https://openalex.org/W4301229630","https://openalex.org/W4404146743","https://openalex.org/W6888962268"],"related_works":[],"abstract_inverted_index":null,"counts_by_year":[],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2025-10-14T00:00:00"}