{"id":"https://openalex.org/W3097109473","doi":"https://doi.org/10.3390/info11110518","title":"Urdu Documents Clustering with Unsupervised and Semi-Supervised Probabilistic Topic Modeling","display_name":"Urdu Documents Clustering with Unsupervised and Semi-Supervised Probabilistic Topic Modeling","publication_year":2020,"publication_date":"2020-11-05","ids":{"openalex":"https://openalex.org/W3097109473","doi":"https://doi.org/10.3390/info11110518","mag":"3097109473"},"language":"en","primary_location":{"id":"doi:10.3390/info11110518","is_oa":true,"landing_page_url":"https://doi.org/10.3390/info11110518","pdf_url":"https://www.mdpi.com/2078-2489/11/11/518/pdf?version=1604563674","source":{"id":"https://openalex.org/S4210219776","display_name":"Information","issn_l":"2078-2489","issn":["2078-2489"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Information","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.mdpi.com/2078-2489/11/11/518/pdf?version=1604563674","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5090122271","display_name":"Mubashar Mustafa","orcid":null},"institutions":[{"id":"https://openalex.org/I139660479","display_name":"Central South University","ror":"https://ror.org/00f1zfq44","country_code":"CN","type":"education","lineage":["https://openalex.org/I139660479"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mubashar Mustafa","raw_affiliation_strings":["School of Computer Science and Engineering, Central South University, 410083 Changsha, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Central South University, 410083 Changsha, China","institution_ids":["https://openalex.org/I139660479"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061939148","display_name":"Feng Zeng","orcid":"https://orcid.org/0000-0002-1541-1326"},"institutions":[{"id":"https://openalex.org/I139660479","display_name":"Central South University","ror":"https://ror.org/00f1zfq44","country_code":"CN","type":"education","lineage":["https://openalex.org/I139660479"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Feng Zeng","raw_affiliation_strings":["School of Computer Science and Engineering, Central South University, 410083 Changsha, China"],"raw_orcid":"https://orcid.org/0000-0002-1541-1326","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Central South University, 410083 Changsha, China","institution_ids":["https://openalex.org/I139660479"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Hussain Ghulam","orcid":null},"institutions":[{"id":"https://openalex.org/I139660479","display_name":"Central South University","ror":"https://ror.org/00f1zfq44","country_code":"CN","type":"education","lineage":["https://openalex.org/I139660479"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hussain Ghulam","raw_affiliation_strings":["School of Computer Science and Engineering, Central South University, 410083 Changsha, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Central South University, 410083 Changsha, China","institution_ids":["https://openalex.org/I139660479"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5003209770","display_name":"Hafiz Muhammad Arslan","orcid":"https://orcid.org/0000-0001-9346-0687"},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hafiz Muhammad Arslan","raw_affiliation_strings":["School of Software Engineering, Northeastern University, 110819 Shenyang, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Software Engineering, Northeastern University, 110819 Shenyang, China","institution_ids":["https://openalex.org/I9224756"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5061939148"],"corresponding_institution_ids":["https://openalex.org/I139660479"],"apc_list":{"value":1400,"currency":"CHF","value_usd":1515},"apc_paid":{"value":1400,"currency":"CHF","value_usd":1515},"fwci":1.0881,"has_fulltext":true,"cited_by_count":11,"citation_normalized_percentile":{"value":0.83164666,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"11","issue":"11","first_page":"518","last_page":"518"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9965000152587891,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9965000152587891,"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":0.9954000115394592,"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/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.982200026512146,"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/latent-dirichlet-allocation","display_name":"Latent Dirichlet allocation","score":0.8561110496520996},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8147012591362},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.7196359634399414},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7023047804832458},{"id":"https://openalex.org/keywords/topic-model","display_name":"Topic model","score":0.690220296382904},{"id":"https://openalex.org/keywords/document-clustering","display_name":"Document clustering","score":0.5528804063796997},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5516605377197266},{"id":"https://openalex.org/keywords/urdu","display_name":"Urdu","score":0.5423023104667664},{"id":"https://openalex.org/keywords/gibbs-sampling","display_name":"Gibbs sampling","score":0.47209256887435913},{"id":"https://openalex.org/keywords/syntax","display_name":"Syntax","score":0.43809324502944946},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.4329819083213806},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.4182170033454895},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.34866809844970703},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.1538277566432953}],"concepts":[{"id":"https://openalex.org/C500882744","wikidata":"https://www.wikidata.org/wiki/Q269236","display_name":"Latent Dirichlet allocation","level":3,"score":0.8561110496520996},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8147012591362},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.7196359634399414},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7023047804832458},{"id":"https://openalex.org/C171686336","wikidata":"https://www.wikidata.org/wiki/Q3532085","display_name":"Topic model","level":2,"score":0.690220296382904},{"id":"https://openalex.org/C177937566","wikidata":"https://www.wikidata.org/wiki/Q4223102","display_name":"Document clustering","level":3,"score":0.5528804063796997},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5516605377197266},{"id":"https://openalex.org/C2777350258","wikidata":"https://www.wikidata.org/wiki/Q1617","display_name":"Urdu","level":2,"score":0.5423023104667664},{"id":"https://openalex.org/C158424031","wikidata":"https://www.wikidata.org/wiki/Q1191905","display_name":"Gibbs sampling","level":3,"score":0.47209256887435913},{"id":"https://openalex.org/C60048249","wikidata":"https://www.wikidata.org/wiki/Q37437","display_name":"Syntax","level":2,"score":0.43809324502944946},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.4329819083213806},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.4182170033454895},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.34866809844970703},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.1538277566432953},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.3390/info11110518","is_oa":true,"landing_page_url":"https://doi.org/10.3390/info11110518","pdf_url":"https://www.mdpi.com/2078-2489/11/11/518/pdf?version=1604563674","source":{"id":"https://openalex.org/S4210219776","display_name":"Information","issn_l":"2078-2489","issn":["2078-2489"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Information","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:a9a930230e9748a384a9e46f89f899d5","is_oa":true,"landing_page_url":"https://doaj.org/article/a9a930230e9748a384a9e46f89f899d5","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":"Information, Vol 11, Iss 11, p 518 (2020)","raw_type":"article"},{"id":"pmh:oai:mdpi.com:/2078-2489/11/11/518/","is_oa":true,"landing_page_url":"https://dx.doi.org/10.3390/info11110518","pdf_url":null,"source":{"id":"https://openalex.org/S4306400947","display_name":"MDPI (MDPI AG)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210097602","host_organization_name":"Multidisciplinary Digital Publishing Institute (Switzerland)","host_organization_lineage":["https://openalex.org/I4210097602"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Information; Volume 11; Issue 11; Pages: 518","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.3390/info11110518","is_oa":true,"landing_page_url":"https://doi.org/10.3390/info11110518","pdf_url":"https://www.mdpi.com/2078-2489/11/11/518/pdf?version=1604563674","source":{"id":"https://openalex.org/S4210219776","display_name":"Information","issn_l":"2078-2489","issn":["2078-2489"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Information","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"No poverty","id":"https://metadata.un.org/sdg/1","score":0.5099999904632568}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3097109473.pdf","grobid_xml":"https://content.openalex.org/works/W3097109473.grobid-xml"},"referenced_works_count":43,"referenced_works":["https://openalex.org/W40976687","https://openalex.org/W81280874","https://openalex.org/W140539934","https://openalex.org/W1506246224","https://openalex.org/W1516946508","https://openalex.org/W1523209510","https://openalex.org/W1761993226","https://openalex.org/W1880262756","https://openalex.org/W1902027874","https://openalex.org/W2001082470","https://openalex.org/W2005539035","https://openalex.org/W2011430131","https://openalex.org/W2033403400","https://openalex.org/W2054460891","https://openalex.org/W2059745395","https://openalex.org/W2067861964","https://openalex.org/W2070412788","https://openalex.org/W2087743880","https://openalex.org/W2098126593","https://openalex.org/W2159426623","https://openalex.org/W2174706414","https://openalex.org/W2264409600","https://openalex.org/W2409439155","https://openalex.org/W2486037960","https://openalex.org/W2538688051","https://openalex.org/W2620351450","https://openalex.org/W2787463955","https://openalex.org/W2798001063","https://openalex.org/W2801591764","https://openalex.org/W2841402245","https://openalex.org/W2899794986","https://openalex.org/W2904431123","https://openalex.org/W2978399804","https://openalex.org/W3026111380","https://openalex.org/W3081332416","https://openalex.org/W3087824800","https://openalex.org/W3105265400","https://openalex.org/W4231510805","https://openalex.org/W4236122429","https://openalex.org/W6639619044","https://openalex.org/W6667444056","https://openalex.org/W6755606341","https://openalex.org/W6782325081"],"related_works":["https://openalex.org/W2888805565","https://openalex.org/W4312773271","https://openalex.org/W4315588616","https://openalex.org/W2769501189","https://openalex.org/W2962686197","https://openalex.org/W2207653751","https://openalex.org/W4293863151","https://openalex.org/W4309228610","https://openalex.org/W2352674739","https://openalex.org/W4294597112"],"abstract_inverted_index":{"Document":[0],"clustering":[1,72,100],"is":[2,31,63,111,155,168,191,267,282],"to":[3,7,24,41,101,138,183,271,275,297],"group":[4],"documents":[5,35,99],"according":[6],"certain":[8],"semantic":[9,16],"features.":[10],"Topic":[11],"model":[12,110,118,134,257,266],"has":[13,73,82],"a":[14,75,94,112],"richer":[15],"structure":[17],"and":[18,87,119,135,178,207,269],"considerable":[19],"potential":[20,30],"for":[21,56,65,97,142,151],"helping":[22],"users":[23],"know":[25],"document":[26,71,152],"corpora.":[27],"Unfortunately,":[28],"this":[29,48,90,189,236,265,285],"stymied":[32],"on":[33,213,229,235,261],"text":[34],"which":[36,81,160,173],"have":[37,53,163],"overlapping":[38,177],"nature,":[39],"due":[40],"their":[42],"purely":[43],"unsupervised":[44,197,223,298],"nature.":[45,165],"To":[46],"solve":[47],"problem,":[49],"some":[50,241],"semi-supervised":[51,95,256,289],"models":[52,198,224,274],"been":[54],"proposed":[55,93,109,133,255],"English":[57],"language.":[58],"However,":[59],"no":[60],"such":[61],"work":[62],"available":[64],"poor":[66],"resource":[67],"language":[68],"Urdu.":[69],"Therefore,":[70],"become":[74],"challenging":[76],"task":[77],"in":[78,159,172,250,284],"Urdu":[79,98,105,139],"language,":[80],"its":[83],"own":[84],"morphology,":[85],"syntax":[86],"semantics.":[88],"In":[89],"study,":[91],"we":[92,122],"framework":[96],"deal":[102],"with":[103,170,232],"the":[104,132,145,174,179,214,230,288],"morphology":[106],"challenges.":[107],"The":[108,166,186],"combination":[113],"of":[114,188,278],"pre-processing":[115],"techniques,":[116],"seeded-LDA":[117],"Gibbs":[120],"sampling,":[121],"named":[123],"it":[124,193,219],"seeded-Urdu":[125],"Latent":[126],"Dirichlet":[127,200],"Allocation":[128,201],"(seeded-ULDA).":[129],"We":[130],"apply":[131],"other":[136,167],"methods":[137],"news":[140],"datasets":[141,263],"categorizing.":[143],"For":[144],"datasets,":[146],"two":[147],"conditions":[148],"are":[149,176,181,209,225,244],"considered":[150],"clustering,":[153],"one":[154],"\u201cDataset":[156,169],"without":[157,216],"overlapping\u201d":[158,171],"all":[161],"classes":[162,180],"distinct":[164],"categories":[175],"connected":[182],"each":[184],"other.":[185],"aim":[187],"study":[190],"threefold:":[192],"first":[194],"shows":[195,220],"that":[196,221,243,287],"(Latent":[199],"(LDA),":[202],"Non-negative":[203],"matrix":[204],"factorization":[205],"(NMF)":[206],"K-means)":[208],"giving":[210],"satisfying":[211],"results":[212,294],"dataset":[215,231],"overlapping.":[217],"Second,":[218],"these":[222,238],"not":[226],"performing":[227],"well":[228,260],"overlapping,":[233],"because,":[234],"dataset,":[237],"algorithms":[239],"find":[240,276],"topics":[242,277],"neither":[245],"entirely":[246],"meaningful":[247],"nor":[248],"effective":[249,270],"extrinsic":[251],"tasks.":[252],"Third,":[253],"our":[254],"Seeded-ULDA":[258],"performs":[259],"both":[262],"because":[264],"straightforward":[268],"instruct":[272],"topic":[273],"specific":[279],"interest.":[280],"It":[281],"shown":[283],"paper":[286],"model,":[290],"Seeded-ULDA,":[291],"provides":[292],"significant":[293],"as":[295],"compared":[296],"algorithms.":[299]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":5}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2020-11-09T00:00:00"}