{"id":"https://openalex.org/W2545639064","doi":"https://doi.org/10.1109/coginfocom.2013.6719262","title":"Near real-time thematic clustering of web documents and other internet contents","display_name":"Near real-time thematic clustering of web documents and other internet contents","publication_year":2013,"publication_date":"2013-12-01","ids":{"openalex":"https://openalex.org/W2545639064","doi":"https://doi.org/10.1109/coginfocom.2013.6719262","mag":"2545639064"},"language":"en","primary_location":{"id":"doi:10.1109/coginfocom.2013.6719262","is_oa":false,"landing_page_url":"https://doi.org/10.1109/coginfocom.2013.6719262","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE 4th International Conference on Cognitive Infocommunications (CogInfoCom)","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/A5084769520","display_name":"Adrian Pusztay","orcid":null},"institutions":[{"id":"https://openalex.org/I106118109","display_name":"E\u00f6tv\u00f6s Lor\u00e1nd University","ror":"https://ror.org/01jsq2704","country_code":"HU","type":"education","lineage":["https://openalex.org/I106118109"]}],"countries":["HU"],"is_corresponding":true,"raw_author_name":"Adrian Pusztay","raw_affiliation_strings":["Eotvos Lorand Tudomanyegyetem, Budapest, HU"],"affiliations":[{"raw_affiliation_string":"Eotvos Lorand Tudomanyegyetem, Budapest, HU","institution_ids":["https://openalex.org/I106118109"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073601500","display_name":"Janos Szuley","orcid":null},"institutions":[{"id":"https://openalex.org/I106118109","display_name":"E\u00f6tv\u00f6s Lor\u00e1nd University","ror":"https://ror.org/01jsq2704","country_code":"HU","type":"education","lineage":["https://openalex.org/I106118109"]}],"countries":["HU"],"is_corresponding":false,"raw_author_name":"Janos Szuley","raw_affiliation_strings":["Eotvos Lorand Tudomanyegyetem, Budapest, HU"],"affiliations":[{"raw_affiliation_string":"Eotvos Lorand Tudomanyegyetem, Budapest, HU","institution_ids":["https://openalex.org/I106118109"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5060308984","display_name":"S\u00e1ndor Laki","orcid":"https://orcid.org/0000-0002-8875-5330"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sandor Laki","raw_affiliation_strings":["Inter-University Centre for Telecommunications and Informatics, Debrecen, Hungary"],"affiliations":[{"raw_affiliation_string":"Inter-University Centre for Telecommunications and Informatics, Debrecen, Hungary","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5084769520"],"corresponding_institution_ids":["https://openalex.org/I106118109"],"apc_list":null,"apc_paid":null,"fwci":1.6178,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.89731759,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"9","issue":null,"first_page":"307","last_page":"312"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10679","display_name":"Service-Oriented Architecture and Web Services","score":0.9853000044822693,"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"}},"topics":[{"id":"https://openalex.org/T10679","display_name":"Service-Oriented Architecture and Web Services","score":0.9853000044822693,"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/T13382","display_name":"Robotics and Automated Systems","score":0.9714999794960022,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10757","display_name":"Geographic Information Systems Studies","score":0.9646000266075134,"subfield":{"id":"https://openalex.org/subfields/3305","display_name":"Geography, Planning and Development"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8395965099334717},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.6917406320571899},{"id":"https://openalex.org/keywords/the-internet","display_name":"The Internet","score":0.618993878364563},{"id":"https://openalex.org/keywords/upload","display_name":"Upload","score":0.5778748393058777},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.5618072152137756},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4198518991470337}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8395965099334717},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6917406320571899},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.618993878364563},{"id":"https://openalex.org/C71901391","wikidata":"https://www.wikidata.org/wiki/Q7126699","display_name":"Upload","level":2,"score":0.5778748393058777},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.5618072152137756},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4198518991470337},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/coginfocom.2013.6719262","is_oa":false,"landing_page_url":"https://doi.org/10.1109/coginfocom.2013.6719262","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE 4th International Conference on Cognitive Infocommunications (CogInfoCom)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/13","display_name":"Climate action","score":0.7200000286102295}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W54798235","https://openalex.org/W140312209","https://openalex.org/W1528167630","https://openalex.org/W1965893683","https://openalex.org/W1978394996","https://openalex.org/W2014615172","https://openalex.org/W2040221623","https://openalex.org/W2065251533","https://openalex.org/W2116429057","https://openalex.org/W2121184547","https://openalex.org/W2165612380","https://openalex.org/W2185859000","https://openalex.org/W4285719527","https://openalex.org/W6686508619"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W2944823289","https://openalex.org/W3037018281","https://openalex.org/W2003209439","https://openalex.org/W4321854979","https://openalex.org/W2358319515","https://openalex.org/W2972592048","https://openalex.org/W4312214821","https://openalex.org/W2497626292","https://openalex.org/W1992952236"],"abstract_inverted_index":{"In":[0,99],"the":[1,53,66,70,91,117,138,156,159,167,178,206,226,249],"past":[2],"decade,":[3],"Internet":[4,227],"has":[5,195],"radically":[6],"changed":[7],"our":[8,187],"lives,":[9],"enabling":[10],"us":[11],"to":[12,89,154,169,177,242],"obtain":[13],"information":[14,51],"on":[15,52,121,162,198,205],"everything":[16],"(disasters,":[17],"political":[18],"decisions,":[19],"ordinary":[20],"events,":[21],"etc.)":[22],"we":[23,102,136,213],"are":[24,229],"interested":[25],"in":[26,27,60,258],"almost":[28],"real-time.":[29],"Downloading":[30],"a":[31,35,104,163,199,216],"web":[32,126],"page":[33],"by":[34],"browser,":[36],"instant":[37],"messaging":[38],"or":[39,65,128],"file":[40],"sharing":[41],"generate":[42],"huge":[43,74],"amount":[44,75],"of":[45,72,76,111,158,186,208,225,232,235],"network":[46],"traffic":[47,236],"that":[48,57,248],"carry":[49],"valuable":[50],"most":[54],"relevant":[55],"topics":[56],"raise":[58],"interest":[59],"individual":[61],"users,":[62],"user":[63],"groups":[64],"entire":[67],"society.":[68],"However,":[69],"analysis":[71],"this":[73,100,259],"unstructured":[77],"textual":[78,108,130,240],"data":[79,92,202],"poses":[80],"many":[81],"challenges,":[82],"especially":[83],"if":[84],"it":[85],"is":[86,97,152,181],"not":[87],"possible":[88],"store":[90],"off-line":[93],"and":[94,123,166,172],"real-time":[95,107,134],"clustering":[96,110,142],"needed.":[98],"paper,":[101],"propose":[103],"framework":[105],"for":[106],"content":[109],"different":[112],"sources":[113],"called":[114,190],"documents":[115,228,241],"over":[116],"Internet,":[118],"including":[119],"posts":[120],"Twitter":[122],"Facebook,":[124],"blogs,":[125],"sites":[127],"other":[129],"contents.":[131],"To":[132],"support":[133],"processing,":[135],"extend":[137],"spherical":[139],"on-line":[140],"K-means":[141],"algorithm":[143,189],"with":[144],"heuristic":[145],"improvements:":[146],"an":[147],"adaptive":[148],"dimension":[149,157],"reduction":[150],"technique":[151],"introduced":[153],"keep":[155],"document":[160],"space":[161],"reasonable":[164,254],"level,":[165],"ability":[168],"open":[170],"new":[171],"remove":[173],"old":[174],"clusters":[175],"according":[176],"actual":[179],"demand":[180],"also":[182,214,246],"added.":[183],"The":[184],"performance":[185],"improved":[188],"ASKM":[191],"(Adaptive":[192],"Streaming":[193],"K-Means)":[194],"been":[196],"analyzed":[197],"ground":[200],"truth":[201],"set":[203],"based":[204],"catalog":[207],"Open":[209],"Directory":[210],"Project.":[211],"Furthermore,":[212],"consider":[215],"much":[217],"more":[218],"realistic":[219],"scenario":[220],"where":[221],"only":[222],"some":[223],"parts":[224],"available":[230],"because":[231],"practical":[233,260],"limitations":[234],"capturing,":[237],"resulting":[238],"incomplete":[239],"be":[243],"clustered.":[244],"We":[245],"show":[247],"proposed":[250],"method":[251],"can":[252],"achieve":[253],"good":[255],"accuracy":[256],"even":[257],"case.":[261]},"counts_by_year":[{"year":2017,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}