{"id":"https://openalex.org/W2287091471","doi":"https://doi.org/10.1145/2838706.2838708","title":"Context-driven Dimensionality Reduction for Clustering Text Documents","display_name":"Context-driven Dimensionality Reduction for Clustering Text Documents","publication_year":2015,"publication_date":"2015-11-30","ids":{"openalex":"https://openalex.org/W2287091471","doi":"https://doi.org/10.1145/2838706.2838708","mag":"2287091471"},"language":"en","primary_location":{"id":"doi:10.1145/2838706.2838708","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2838706.2838708","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 7th Forum for Information Retrieval Evaluation","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/A5082339849","display_name":"Debasis Ganguly","orcid":"https://orcid.org/0000-0003-0050-7138"},"institutions":[{"id":"https://openalex.org/I42934936","display_name":"Dublin City University","ror":"https://ror.org/04a1a1e81","country_code":"IE","type":"education","lineage":["https://openalex.org/I42934936"]}],"countries":["IE"],"is_corresponding":true,"raw_author_name":"Debasis Ganguly","raw_affiliation_strings":["ADAPT Centre, School of Computing, Dublin City University, Dublin, Ireland"],"affiliations":[{"raw_affiliation_string":"ADAPT Centre, School of Computing, Dublin City University, Dublin, Ireland","institution_ids":["https://openalex.org/I42934936"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063045515","display_name":"Johannes Leveling","orcid":"https://orcid.org/0000-0003-0603-4191"},"institutions":[{"id":"https://openalex.org/I1318003438","display_name":"RELX Group (Netherlands)","ror":"https://ror.org/02scfj030","country_code":"NL","type":"company","lineage":["https://openalex.org/I1318003438","https://openalex.org/I4210160603"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Johannes Leveling","raw_affiliation_strings":["Elsevier, Amsterdam, Netherlands"],"affiliations":[{"raw_affiliation_string":"Elsevier, Amsterdam, Netherlands","institution_ids":["https://openalex.org/I1318003438"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5018481328","display_name":"Gareth J. F. Jones","orcid":"https://orcid.org/0000-0003-2923-8365"},"institutions":[{"id":"https://openalex.org/I42934936","display_name":"Dublin City University","ror":"https://ror.org/04a1a1e81","country_code":"IE","type":"education","lineage":["https://openalex.org/I42934936"]}],"countries":["IE"],"is_corresponding":false,"raw_author_name":"Gareth J. F. Jones","raw_affiliation_strings":["ADAPT Centre School of Computing, Dublin City University, Dublin, Ireland"],"affiliations":[{"raw_affiliation_string":"ADAPT Centre School of Computing, Dublin City University, Dublin, Ireland","institution_ids":["https://openalex.org/I42934936"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5082339849"],"corresponding_institution_ids":["https://openalex.org/I42934936"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.14629326,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10799","display_name":"Data Visualization and Analytics","score":0.9991000294685364,"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"}},"topics":[{"id":"https://openalex.org/T10799","display_name":"Data Visualization and Analytics","score":0.9991000294685364,"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"}},{"id":"https://openalex.org/T10637","display_name":"Advanced Clustering Algorithms Research","score":0.9980999827384949,"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/T11106","display_name":"Data Management and Algorithms","score":0.996399998664856,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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":0.8240820169448853},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7914856672286987},{"id":"https://openalex.org/keywords/unavailability","display_name":"Unavailability","score":0.7681443095207214},{"id":"https://openalex.org/keywords/dimensionality-reduction","display_name":"Dimensionality reduction","score":0.6950258016586304},{"id":"https://openalex.org/keywords/document-clustering","display_name":"Document clustering","score":0.6918129920959473},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5776433348655701},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5231669545173645},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4885910153388977},{"id":"https://openalex.org/keywords/curse-of-dimensionality","display_name":"Curse of dimensionality","score":0.4575752913951874},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.4338221848011017},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.35096579790115356},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10032892227172852}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.8240820169448853},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7914856672286987},{"id":"https://openalex.org/C2780505938","wikidata":"https://www.wikidata.org/wiki/Q17093282","display_name":"Unavailability","level":2,"score":0.7681443095207214},{"id":"https://openalex.org/C70518039","wikidata":"https://www.wikidata.org/wiki/Q16000077","display_name":"Dimensionality reduction","level":2,"score":0.6950258016586304},{"id":"https://openalex.org/C177937566","wikidata":"https://www.wikidata.org/wiki/Q4223102","display_name":"Document clustering","level":3,"score":0.6918129920959473},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5776433348655701},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5231669545173645},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4885910153388977},{"id":"https://openalex.org/C111030470","wikidata":"https://www.wikidata.org/wiki/Q1430460","display_name":"Curse of dimensionality","level":2,"score":0.4575752913951874},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.4338221848011017},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35096579790115356},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10032892227172852},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","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},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2838706.2838708","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2838706.2838708","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 7th Forum for Information Retrieval Evaluation","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320320834","display_name":"Enterprise Ireland","ror":"https://ror.org/023z51242"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W1488519867","https://openalex.org/W1494382025","https://openalex.org/W1507837710","https://openalex.org/W1516104228","https://openalex.org/W1982982698","https://openalex.org/W1987317478","https://openalex.org/W2037744768","https://openalex.org/W2079361215","https://openalex.org/W2079392363","https://openalex.org/W2136663225","https://openalex.org/W2145640629","https://openalex.org/W2147468287","https://openalex.org/W2153104460","https://openalex.org/W2170121748","https://openalex.org/W2229908198","https://openalex.org/W3139328003","https://openalex.org/W3142797275","https://openalex.org/W4292478130"],"related_works":["https://openalex.org/W1995622179","https://openalex.org/W4391160746","https://openalex.org/W1484111231","https://openalex.org/W1552543208","https://openalex.org/W2074396517","https://openalex.org/W2166963679","https://openalex.org/W2187269125","https://openalex.org/W1641615907","https://openalex.org/W3089231081","https://openalex.org/W2093956241"],"abstract_inverted_index":{"We":[0],"investigate":[1],"clustering":[2,22,48,152],"documents":[3,37,124],"based":[4],"on":[5,106],"automatically":[6,84],"annotated":[7,85],"potentially":[8],"sensitive":[9,86,117],"information":[10,118],"extracted":[11],"from":[12,79,122],"a":[13,67,89,154],"large":[14,55],"collection":[15],"of":[16,21,36,46,57,82,88,95,125,135,157,168],"organizational":[17,97],"data.":[18],"The":[19],"process":[20],"in":[23],"this":[24,63,126],"particular":[25],"use":[26,121],"case":[27],"is":[28,49,145],"helpful":[29],"to":[30,53,92,147,164],"visualize":[31],"and":[32,44,137],"navigate":[33],"through":[34],"groups":[35],"with":[38,75,153,162],"related":[39],"content.":[40],"However,":[41],"the":[42,54,58,80,83,93,107,115,123,129,133,165],"effectiveness":[43],"efficiency":[45],"document":[47,59,172],"limited":[50],"mainly":[51],"due":[52],"dimensionality":[56,68,173],"vectors.":[60],"To":[61],"alleviate":[62],"problem":[64],"we":[65,102,120],"propose":[66],"reduction":[69],"approach":[70,105,144],"which":[71],"involves":[72],"selecting":[73],"terms":[74],"high":[76],"tf-idf":[77],"scores":[78],"context":[81],"regions":[87],"document.":[90],"Due":[91],"unavailability":[94],"real":[96],"data":[98],"for":[99],"research":[100],"purposes,":[101,114],"evaluate":[103],"our":[104,143],"standard":[108],"20":[109],"news-groups":[110],"dataset.":[111],"For":[112],"evaluation":[113],"only":[116],"that":[119,142],"dataset":[127],"are":[128],"named":[130],"entities,":[131],"e.g.":[132],"names":[134],"persons":[136],"organizations.":[138],"Experimental":[139],"results":[140],"show":[141],"able":[146],"achieve":[148],"an":[149],"almost":[150],"perfect":[151],"purity":[155,166],"value":[156,167],"0.998":[158],"improving":[159],"by":[160],"22.60%":[161],"respect":[163],"0.814":[169],"obtained":[170],"without":[171],"reduction.":[174]},"counts_by_year":[{"year":2019,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}