{"id":"https://openalex.org/W4292055030","doi":"https://doi.org/10.1142/s0218213022500348","title":"Improving Hierarchical Short Text Clustering through Dominant Feature Learning","display_name":"Improving Hierarchical Short Text Clustering through Dominant Feature Learning","publication_year":2022,"publication_date":"2022-08-01","ids":{"openalex":"https://openalex.org/W4292055030","doi":"https://doi.org/10.1142/s0218213022500348"},"language":"en","primary_location":{"id":"doi:10.1142/s0218213022500348","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s0218213022500348","pdf_url":null,"source":{"id":"https://openalex.org/S178780388","display_name":"International Journal of Artificial Intelligence Tools","issn_l":"0218-2130","issn":["0218-2130","1793-6349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319815","host_organization_name":"World Scientific","host_organization_lineage":["https://openalex.org/P4310319815"],"host_organization_lineage_names":["World Scientific"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal on Artificial Intelligence Tools","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/A5011200753","display_name":"Leonidas Akritidis","orcid":"https://orcid.org/0000-0001-6602-0723"},"institutions":[{"id":"https://openalex.org/I183898223","display_name":"International Hellenic University","ror":"https://ror.org/00708jp83","country_code":"GR","type":"education","lineage":["https://openalex.org/I183898223"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Leonidas Akritidis","raw_affiliation_strings":["Department of Science and Technology, International Hellenic University, Thessaloniki, Greece"],"raw_orcid":"https://orcid.org/0000-0001-6602-0723","affiliations":[{"raw_affiliation_string":"Department of Science and Technology, International Hellenic University, Thessaloniki, Greece","institution_ids":["https://openalex.org/I183898223"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074118906","display_name":"Miltiadis Alamaniotis","orcid":"https://orcid.org/0000-0003-0787-5013"},"institutions":[{"id":"https://openalex.org/I45438204","display_name":"The University of Texas at San Antonio","ror":"https://ror.org/01kd65564","country_code":"US","type":"education","lineage":["https://openalex.org/I45438204"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Miltiadis Alamaniotis","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of Texas at San Antonio, San Antonio, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Texas at San Antonio, San Antonio, USA","institution_ids":["https://openalex.org/I45438204"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006905736","display_name":"Athanasios Fevgas","orcid":"https://orcid.org/0000-0003-0154-175X"},"institutions":[{"id":"https://openalex.org/I145722265","display_name":"University of Thessaly","ror":"https://ror.org/04v4g9h31","country_code":"GR","type":"education","lineage":["https://openalex.org/I145722265"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Athanasios Fevgas","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of Thessaly, Volos, Greece"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Thessaly, Volos, Greece","institution_ids":["https://openalex.org/I145722265"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111610947","display_name":"Panagiota Tsompanopoulou","orcid":null},"institutions":[{"id":"https://openalex.org/I145722265","display_name":"University of Thessaly","ror":"https://ror.org/04v4g9h31","country_code":"GR","type":"education","lineage":["https://openalex.org/I145722265"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Panagiota Tsompanopoulou","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of Thessaly, Volos, Greece"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Thessaly, Volos, Greece","institution_ids":["https://openalex.org/I145722265"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5011619520","display_name":"Panayiotis Bozanis","orcid":"https://orcid.org/0000-0001-9435-1829"},"institutions":[{"id":"https://openalex.org/I183898223","display_name":"International Hellenic University","ror":"https://ror.org/00708jp83","country_code":"GR","type":"education","lineage":["https://openalex.org/I183898223"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Panayiotis Bozanis","raw_affiliation_strings":["Department of Science and Technology, International Hellenic University, Thessaloniki, Greece"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Science and Technology, International Hellenic University, Thessaloniki, Greece","institution_ids":["https://openalex.org/I183898223"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.8324,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.77684029,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"31","issue":"05","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":0.995199978351593,"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":0.995199978351593,"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":0.9835000038146973,"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/T10057","display_name":"Face and Expression Recognition","score":0.9797999858856201,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.8386738300323486},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.7886492013931274},{"id":"https://openalex.org/keywords/hierarchical-clustering","display_name":"Hierarchical clustering","score":0.6105441451072693},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5290157794952393},{"id":"https://openalex.org/keywords/document-clustering","display_name":"Document clustering","score":0.5136703848838806},{"id":"https://openalex.org/keywords/curse-of-dimensionality","display_name":"Curse of dimensionality","score":0.5050662159919739},{"id":"https://openalex.org/keywords/completeness","display_name":"Completeness (order theory)","score":0.5047560930252075},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5008594989776611},{"id":"https://openalex.org/keywords/feature-vector","display_name":"Feature vector","score":0.48761358857154846},{"id":"https://openalex.org/keywords/brown-clustering","display_name":"Brown clustering","score":0.44904765486717224},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4289079010486603},{"id":"https://openalex.org/keywords/cluster","display_name":"Cluster (spacecraft)","score":0.42708122730255127},{"id":"https://openalex.org/keywords/single-linkage-clustering","display_name":"Single-linkage clustering","score":0.4129621982574463},{"id":"https://openalex.org/keywords/correlation-clustering","display_name":"Correlation clustering","score":0.3199678659439087},{"id":"https://openalex.org/keywords/cure-data-clustering-algorithm","display_name":"CURE data clustering algorithm","score":0.2647578716278076},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10238698124885559}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8386738300323486},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.7886492013931274},{"id":"https://openalex.org/C92835128","wikidata":"https://www.wikidata.org/wiki/Q1277447","display_name":"Hierarchical clustering","level":3,"score":0.6105441451072693},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5290157794952393},{"id":"https://openalex.org/C177937566","wikidata":"https://www.wikidata.org/wiki/Q4223102","display_name":"Document clustering","level":3,"score":0.5136703848838806},{"id":"https://openalex.org/C111030470","wikidata":"https://www.wikidata.org/wiki/Q1430460","display_name":"Curse of dimensionality","level":2,"score":0.5050662159919739},{"id":"https://openalex.org/C17231256","wikidata":"https://www.wikidata.org/wiki/Q5156540","display_name":"Completeness (order theory)","level":2,"score":0.5047560930252075},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5008594989776611},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.48761358857154846},{"id":"https://openalex.org/C167984511","wikidata":"https://www.wikidata.org/wiki/Q17003931","display_name":"Brown clustering","level":5,"score":0.44904765486717224},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4289079010486603},{"id":"https://openalex.org/C164866538","wikidata":"https://www.wikidata.org/wiki/Q367351","display_name":"Cluster (spacecraft)","level":2,"score":0.42708122730255127},{"id":"https://openalex.org/C22648726","wikidata":"https://www.wikidata.org/wiki/Q7523744","display_name":"Single-linkage clustering","level":5,"score":0.4129621982574463},{"id":"https://openalex.org/C94641424","wikidata":"https://www.wikidata.org/wiki/Q5172845","display_name":"Correlation clustering","level":3,"score":0.3199678659439087},{"id":"https://openalex.org/C33704608","wikidata":"https://www.wikidata.org/wiki/Q5014717","display_name":"CURE data clustering algorithm","level":4,"score":0.2647578716278076},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10238698124885559},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1142/s0218213022500348","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s0218213022500348","pdf_url":null,"source":{"id":"https://openalex.org/S178780388","display_name":"International Journal of Artificial Intelligence Tools","issn_l":"0218-2130","issn":["0218-2130","1793-6349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319815","host_organization_name":"World Scientific","host_organization_lineage":["https://openalex.org/P4310319815"],"host_organization_lineage_names":["World Scientific"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal on Artificial Intelligence Tools","raw_type":"journal-article"},{"id":"pmh:oai:ir.lib.uth.gr:11615/70351","is_oa":false,"landing_page_url":"http://hdl.handle.net/11615/70351","pdf_url":null,"source":{"id":"https://openalex.org/S4306400243","display_name":"University of Thessaly Institutional Repository (University of Thessaly)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I145722265","host_organization_name":"University of Thessaly","host_organization_lineage":["https://openalex.org/I145722265"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"International Journal on Artificial Intelligence Tools","raw_type":"journalArticle"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.41999998688697815,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2130194910","https://openalex.org/W2087424554","https://openalex.org/W2384052049","https://openalex.org/W2189374779","https://openalex.org/W1981213098","https://openalex.org/W4231226332","https://openalex.org/W2161927371","https://openalex.org/W2367205823","https://openalex.org/W2379907417","https://openalex.org/W2605148547"],"abstract_inverted_index":{"This":[0],"paper":[1],"focuses":[2],"on":[3,46,77,89],"the":[4,12,25,35,55,68,71,83,90,97,111,114,120,138,149,161,199],"popular":[5],"problem":[6,26],"of":[7,20,57,113,125,143,178,198],"short":[8,13,60],"text":[9,14,61,73],"clustering.":[10],"Since":[11],"documents":[15,84],"typically":[16],"exhibit":[17],"high":[18],"degrees":[19],"data":[21],"sparseness":[22],"and":[23,82,133,135,156,180],"dimensionality,":[24],"in":[27,96,164,176],"question":[28],"is":[29,44,103,128],"generally":[30],"considered":[31],"more":[32],"challenging":[33],"than":[34],"traditional":[36],"clustering":[37,59],"scenarios.":[38],"Our":[39],"proposed":[40,170],"solution,":[41],"named":[42],"VEPH,":[43],"based":[45],"a":[47,78,104,126,165],"novel":[48],"algorithm":[49,171],"that":[50,116],"was":[51],"published":[52],"recently":[53],"with":[54,85,186],"aim":[56],"optimally":[58],"documents.":[62],"VEPH":[63,147],"includes":[64],"two":[65,139],"stages:":[66],"During":[67],"first":[69],"stage,":[70],"original":[72],"vectors":[74,87],"are":[75,94,137],"projected":[76],"lower":[79],"dimensional":[80,92],"space":[81,93],"projection":[86],"lying":[88],"same":[91,98],"grouped":[95],"cluster.":[99],"The":[100,123,169,189],"second":[101],"stage":[102],"refinement":[105],"process":[106],"which":[107],"attempts":[108],"to":[109],"improve":[110],"quality":[112,124],"clusters":[115,150,163],"were":[117],"generated":[118],"during":[119],"previous":[121],"stage.":[122,145],"cluster":[127],"determined":[129],"by":[130,151,182],"its":[131,192],"homogeneity":[132],"completeness":[134],"these":[136],"primary":[140],"design":[141],"criteria":[142],"this":[144],"Initially":[146],"cleanses":[148],"removing":[152],"all":[153],"dissimilar":[154],"elements,":[155],"then,":[157],"it":[158],"iteratively":[159],"merges":[160],"similar":[162],"hierarchical":[166],"agglomerative":[167],"manner.":[168],"has":[172],"been":[173],"experimentally":[174],"evaluated":[175],"terms":[177],"F1":[179],"NMI,":[181],"employing":[183],"three":[184],"datasets":[185],"diverse":[187],"attributes.":[188],"results":[190],"demonstrated":[191],"superiority":[193],"over":[194],"other":[195],"state-of-the-art":[196],"works":[197],"relevant":[200],"literature.":[201]},"counts_by_year":[{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}