{"id":"https://openalex.org/W1852132449","doi":"https://doi.org/10.3233/kes-130267","title":"Enhanced cross-domain document clustering with a semantically enhanced text stemmer (SETS)","display_name":"Enhanced cross-domain document clustering with a semantically enhanced text stemmer (SETS)","publication_year":2013,"publication_date":"2013-05-13","ids":{"openalex":"https://openalex.org/W1852132449","doi":"https://doi.org/10.3233/kes-130267","mag":"1852132449"},"language":"en","primary_location":{"is_oa":false,"landing_page_url":"https://doi.org/10.3233/kes-130267","pdf_url":null,"source":{"id":"https://openalex.org/S133764092","display_name":"International Journal of Knowledge-based and Intelligent Engineering Systems","issn_l":"1327-2314","issn":["1327-2314","1875-8827"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310318577","host_organization_name":"IOS Press","host_organization_lineage":["https://openalex.org/P4310318577"],"host_organization_lineage_names":["IOS Press"],"type":"journal"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false},"type":"article","type_crossref":"journal-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/A5077102811","display_name":"Ivan Stankov","orcid":null},"institutions":[{"id":"https://openalex.org/I79510175","display_name":"Cardiff University","ror":"https://ror.org/03kk7td41","country_code":"GB","type":"education","lineage":["https://openalex.org/I79510175"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Ivan Stankov","raw_affiliation_strings":["Knowledge Engineering Systems Group, School of Engineering, Cardiff University, Cardiff, UK"],"affiliations":[{"raw_affiliation_string":"Knowledge Engineering Systems Group, School of Engineering, Cardiff University, Cardiff, UK","institution_ids":["https://openalex.org/I79510175"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080604453","display_name":"Diman Todorov","orcid":null},"institutions":[{"id":"https://openalex.org/I79510175","display_name":"Cardiff University","ror":"https://ror.org/03kk7td41","country_code":"GB","type":"education","lineage":["https://openalex.org/I79510175"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Diman Todorov","raw_affiliation_strings":["Knowledge Engineering Systems Group, School of Engineering, Cardiff University, Cardiff, UK"],"affiliations":[{"raw_affiliation_string":"Knowledge Engineering Systems Group, School of Engineering, Cardiff University, Cardiff, UK","institution_ids":["https://openalex.org/I79510175"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5006534137","display_name":"Rossitza Setchi","orcid":"https://orcid.org/0000-0002-7207-6544"},"institutions":[{"id":"https://openalex.org/I79510175","display_name":"Cardiff University","ror":"https://ror.org/03kk7td41","country_code":"GB","type":"education","lineage":["https://openalex.org/I79510175"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Rossitza Setchi","raw_affiliation_strings":["Knowledge Engineering Systems Group, School of Engineering, Cardiff University, Cardiff, UK"],"affiliations":[{"raw_affiliation_string":"Knowledge Engineering Systems Group, School of Engineering, Cardiff University, Cardiff, UK","institution_ids":["https://openalex.org/I79510175"]}]}],"institution_assertions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.38,"has_fulltext":true,"fulltext_origin":"ngrams","cited_by_count":3,"citation_normalized_percentile":{"value":0.67286,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":76,"max":78},"biblio":{"volume":"17","issue":"2","first_page":"113","last_page":"126"},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T10637","display_name":"Advanced Clustering Algorithms Research","score":0.9984,"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/T10637","display_name":"Advanced Clustering Algorithms Research","score":0.9984,"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":0.9974,"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":0.9967,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/document-clustering","display_name":"Document Clustering","score":0.85291326}],"concepts":[{"id":"https://openalex.org/C177937566","wikidata":"https://www.wikidata.org/wiki/Q4223102","display_name":"Document clustering","level":3,"score":0.85291326},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8249098},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.81365204},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.57345635},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5668458},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.537503},{"id":"https://openalex.org/C2781181686","wikidata":"https://www.wikidata.org/wiki/Q4226068","display_name":"Coherence (philosophical gambling strategy)","level":2,"score":0.52605796},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.47412634},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07619393},{"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/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"is_oa":false,"landing_page_url":"https://doi.org/10.3233/kes-130267","pdf_url":null,"source":{"id":"https://openalex.org/S133764092","display_name":"International Journal of Knowledge-based and Intelligent Engineering Systems","issn_l":"1327-2314","issn":["1327-2314","1875-8827"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310318577","host_organization_name":"IOS Press","host_organization_lineage":["https://openalex.org/P4310318577"],"host_organization_lineage_names":["IOS Press"],"type":"journal"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false}],"best_oa_location":null,"sustainable_development_goals":[],"grants":[],"datasets":[],"versions":[],"referenced_works_count":30,"referenced_works":["https://openalex.org/W1536697368","https://openalex.org/W1541825180","https://openalex.org/W179579220","https://openalex.org/W1956559956","https://openalex.org/W1969158886","https://openalex.org/W1987971958","https://openalex.org/W1992419399","https://openalex.org/W1995639191","https://openalex.org/W1996764654","https://openalex.org/W2008495066","https://openalex.org/W2010178645","https://openalex.org/W2024932032","https://openalex.org/W2058200372","https://openalex.org/W2081980673","https://openalex.org/W2095478124","https://openalex.org/W2098162425","https://openalex.org/W2102381086","https://openalex.org/W2120084270","https://openalex.org/W2121853761","https://openalex.org/W2122600670","https://openalex.org/W2131970106","https://openalex.org/W2132549764","https://openalex.org/W2133517430","https://openalex.org/W2141457256","https://openalex.org/W2141585940","https://openalex.org/W2150874198","https://openalex.org/W2153233077","https://openalex.org/W2166843810","https://openalex.org/W4285719527","https://openalex.org/W78181647"],"related_works":["https://openalex.org/W52853789","https://openalex.org/W4298130764","https://openalex.org/W4254379378","https://openalex.org/W4237592971","https://openalex.org/W4206655101","https://openalex.org/W2899601636","https://openalex.org/W2804364458","https://openalex.org/W2387982377","https://openalex.org/W2019737068","https://openalex.org/W1795405792"],"abstract_inverted_index":{"The":[0,76,96],"aim":[1],"of":[2,10,56,85,106],"document":[3,27,74],"clustering":[4,28,59],"is":[5,41,78,133,141],"to":[6,20,48,119,135,138,154],"produce":[7],"coherent":[8],"clusters":[9,107],"similar":[11],"documents.":[12,24,156],"Clustering":[13],"algorithms":[14,29],"rely":[15],"on":[16,80],"text":[17,114,121,131],"normalisation":[18,122,132],"techniques":[19],"represent":[21,155],"and":[22,71],"cluster":[23,66],"Although":[25],"most":[26],"perform":[30],"well":[31],"in":[32,144],"specific":[33],"knowledge":[34],"domains,":[35,62],"processing":[36],"cross-domain":[37],"docum":[38],"ent":[39],"repositories":[40],"still":[42],"a":[43,86,111,149],"challenge.":[44,51],"This":[45],"paper":[46],"attempts":[47],"address":[49],"this":[50],"It":[52],"investigates":[53],"the":[54,57,65,93,101,120,125,145],"performance":[55],"sk-means":[58],"algorithm":[60],"across":[61],"by":[63,109],"comparing":[64],"coherence":[67,105],"produced":[68,108],"with":[69,124],"semantic-based":[70,130],"traditional":[72],"(TF-IDF-based)":[73],"representations.":[75],"evaluation":[77,102],"conducted":[79],"20":[81],"different":[82],"generic":[83],"sub-domains":[84],"thousand":[87],"documents,":[88],"each":[89],"randomly":[90],"selected":[91],"from":[92,100],"Reuters21578":[94],"corpus.":[95],"experimental":[97],"results":[98],"obtained":[99,123],"demonstrate":[103],"improved":[104],"using":[110],"semantically":[112],"enhanced":[113],"stemmer":[115],"(SETS),":[116],"when":[117],"compared":[118],"Porter":[126],"stemmer.":[127],"In":[128],"addition,":[129],"shown":[134],"be":[136],"resistant":[137],"noise,":[139],"which":[140],"often":[142],"introduced":[143],"index":[146],"aggregation":[147],"stage,":[148],"stage":[150],"that":[151],"acquires":[152],"features":[153]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W1852132449","counts_by_year":[{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":1}],"updated_date":"2024-12-06T21:55:12.089271","created_date":"2016-06-24"}
