{"id":"https://openalex.org/W2809109786","doi":"https://doi.org/10.1145/3206098.3206110","title":"Semantic Oriented Document Clustering Using Distribution Semantics","display_name":"Semantic Oriented Document Clustering Using Distribution Semantics","publication_year":2018,"publication_date":"2018-04-09","ids":{"openalex":"https://openalex.org/W2809109786","doi":"https://doi.org/10.1145/3206098.3206110","mag":"2809109786"},"language":"en","primary_location":{"id":"doi:10.1145/3206098.3206110","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3206098.3206110","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2nd International Conference on Information System and Data Mining","raw_type":"proceedings-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/A5108901657","display_name":"Umar Ali Khan","orcid":"https://orcid.org/0000-0002-3079-7538"},"institutions":[{"id":"https://openalex.org/I201384688","display_name":"National University of Computer and Emerging Sciences","ror":"https://ror.org/003eyb898","country_code":"PK","type":"education","lineage":["https://openalex.org/I201384688"]}],"countries":["PK"],"is_corresponding":true,"raw_author_name":"Umar Ali Khan","raw_affiliation_strings":["National University of and Emerging Sciences, Karachi, Pakistan"],"affiliations":[{"raw_affiliation_string":"National University of and Emerging Sciences, Karachi, Pakistan","institution_ids":["https://openalex.org/I201384688"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5086471874","display_name":"Muhammad Rafi","orcid":"https://orcid.org/0000-0002-3673-5979"},"institutions":[{"id":"https://openalex.org/I201384688","display_name":"National University of Computer and Emerging Sciences","ror":"https://ror.org/003eyb898","country_code":"PK","type":"education","lineage":["https://openalex.org/I201384688"]}],"countries":["PK"],"is_corresponding":false,"raw_author_name":"Muhammad Rafi","raw_affiliation_strings":["National University of and Emerging Sciences, Karachi, Pakistan"],"affiliations":[{"raw_affiliation_string":"National University of and Emerging Sciences, Karachi, Pakistan","institution_ids":["https://openalex.org/I201384688"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5108901657"],"corresponding_institution_ids":["https://openalex.org/I201384688"],"apc_list":null,"apc_paid":null,"fwci":0.1629,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.57367403,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"14","last_page":"18"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9977999925613403,"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":0.9977999925613403,"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":0.9965999722480774,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9955999851226807,"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/computer-science","display_name":"Computer science","score":0.7656533718109131},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.7482475638389587},{"id":"https://openalex.org/keywords/document-clustering","display_name":"Document clustering","score":0.7058016657829285},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.6753411293029785},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5875692367553711},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.48179978132247925},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.47722676396369934},{"id":"https://openalex.org/keywords/measure","display_name":"Measure (data warehouse)","score":0.47301509976387024},{"id":"https://openalex.org/keywords/semantic-similarity","display_name":"Semantic similarity","score":0.46864622831344604},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.46100351214408875},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4590200185775757},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4361562132835388},{"id":"https://openalex.org/keywords/distributional-semantics","display_name":"Distributional semantics","score":0.43293437361717224},{"id":"https://openalex.org/keywords/hierarchical-clustering","display_name":"Hierarchical clustering","score":0.4264146685600281},{"id":"https://openalex.org/keywords/meaning","display_name":"Meaning (existential)","score":0.4123808741569519},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3631485104560852},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.11247566342353821},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.06731626391410828}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7656533718109131},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.7482475638389587},{"id":"https://openalex.org/C177937566","wikidata":"https://www.wikidata.org/wiki/Q4223102","display_name":"Document clustering","level":3,"score":0.7058016657829285},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.6753411293029785},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5875692367553711},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.48179978132247925},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.47722676396369934},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.47301509976387024},{"id":"https://openalex.org/C130318100","wikidata":"https://www.wikidata.org/wiki/Q2268914","display_name":"Semantic similarity","level":2,"score":0.46864622831344604},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.46100351214408875},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4590200185775757},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4361562132835388},{"id":"https://openalex.org/C2778828372","wikidata":"https://www.wikidata.org/wiki/Q5283209","display_name":"Distributional semantics","level":3,"score":0.43293437361717224},{"id":"https://openalex.org/C92835128","wikidata":"https://www.wikidata.org/wiki/Q1277447","display_name":"Hierarchical clustering","level":3,"score":0.4264146685600281},{"id":"https://openalex.org/C2780876879","wikidata":"https://www.wikidata.org/wiki/Q3054749","display_name":"Meaning (existential)","level":2,"score":0.4123808741569519},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3631485104560852},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.11247566342353821},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.06731626391410828},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C542102704","wikidata":"https://www.wikidata.org/wiki/Q183257","display_name":"Psychotherapist","level":1,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3206098.3206110","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3206098.3206110","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2nd International Conference on Information System and Data Mining","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6100000143051147,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W74108380","https://openalex.org/W113586804","https://openalex.org/W186296515","https://openalex.org/W1546703457","https://openalex.org/W1666605052","https://openalex.org/W1693722119","https://openalex.org/W1967252265","https://openalex.org/W1971784203","https://openalex.org/W1981617416","https://openalex.org/W1985826049","https://openalex.org/W2005181355","https://openalex.org/W2034462435","https://openalex.org/W2034995091","https://openalex.org/W2042782365","https://openalex.org/W2066073289","https://openalex.org/W2099868020","https://openalex.org/W2102381086","https://openalex.org/W2108281845","https://openalex.org/W2108347737","https://openalex.org/W2112184938","https://openalex.org/W2120779048","https://openalex.org/W2140354722","https://openalex.org/W2147152072","https://openalex.org/W2165019836","https://openalex.org/W2269043412","https://openalex.org/W2316340232","https://openalex.org/W2578731660"],"related_works":["https://openalex.org/W2963364736","https://openalex.org/W4237492828","https://openalex.org/W2808113865","https://openalex.org/W78181647","https://openalex.org/W2112408611","https://openalex.org/W1840682977","https://openalex.org/W4299488910","https://openalex.org/W2130194910","https://openalex.org/W4386468556","https://openalex.org/W59191841"],"abstract_inverted_index":{"The":[0,166],"exponential":[1],"growth":[2],"of":[3,6,51,74,91,135,163,172],"electronic":[4],"form":[5],"textual":[7],"documents":[8,114,128],"in":[9,35,64,138,182],"both":[10],"public":[11],"and":[12,110,174],"proprietary":[13],"storage":[14],"force":[15],"researchers":[16],"to":[17,20,94,100,148,159,184],"find":[18,32,95,101],"way":[19],"efficiently":[21],"extract":[22],"meaningful,":[23],"actionable":[24],"information":[25],"from":[26],"these":[27,117,127],"documents.":[28,92],"Document":[29],"clustering":[30,144,180],"has":[31],"its":[33],"niche":[34],"this":[36,164],"area.":[37],"This":[38,72],"paper":[39],"proposes":[40],"a":[41,65,88],"document":[42,75],"representational":[43],"model":[44,76],"based":[45,169],"on":[46,170],"distributional":[47,52,104,108,118,136],"semantics,":[48],"the":[49,56,103,113,132,150,161],"law":[50],"semantics":[53,137],"says":[54],"that":[55,59,83,129],"linguist":[57],"terms":[58,80,105],"appear":[60],"with":[61],"similar":[62,70],"distribution":[63,86],"language":[66],"corpus":[67],"generally":[68],"have":[69,84],"meaning.":[71],"representation":[73],"uses":[77],"only":[78,116],"those":[79],"(linguistic":[81],"feature)":[82],"same":[85],"over":[87,126],"given":[89],"collection":[90],"So":[93],"this,":[96],"it":[97],"is":[98,124,146,168],"needed":[99],"out":[102],"by":[106,115],"using":[107],"criteria":[109],"then":[111],"representing":[112],"terms.":[119],"A":[120],"novel":[121],"similarity":[122,139],"measure":[123,160],"proposed":[125,175],"also":[130],"utilized":[131],"very":[133],"nature":[134],"calculation.":[140],"Finally,":[141],"hierarchal":[142],"agglomerative":[143],"(HAC)":[145],"used":[147,158],"produce":[149],"final":[151],"clusters.":[152],"Standard":[153],"text":[154],"mining":[155],"datasets":[156],"are":[157],"effectiveness":[162],"approach.":[165,186],"evaluation":[167],"purity":[171],"clusters":[173],"approach":[176],"achieved":[177],"far":[178],"better":[179],"results":[181],"comparison":[183],"conventional":[185]},"counts_by_year":[{"year":2020,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}