{"id":"https://openalex.org/W3195710474","doi":"https://doi.org/10.1145/3469096.3469866","title":"Efficient clustering of short text streams using online-offline clustering","display_name":"Efficient clustering of short text streams using online-offline clustering","publication_year":2021,"publication_date":"2021-08-16","ids":{"openalex":"https://openalex.org/W3195710474","doi":"https://doi.org/10.1145/3469096.3469866","mag":"3195710474"},"language":"en","primary_location":{"id":"doi:10.1145/3469096.3469866","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3469096.3469866","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 21st ACM Symposium on Document Engineering","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/A5056840301","display_name":"Md Rashadul Hasan Rakib","orcid":null},"institutions":[{"id":"https://openalex.org/I129902397","display_name":"Dalhousie University","ror":"https://ror.org/01e6qks80","country_code":"CA","type":"education","lineage":["https://openalex.org/I129902397"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Md Rashadul Hasan Rakib","raw_affiliation_strings":["Dalhousie University, Nova Scotia, Canada"],"affiliations":[{"raw_affiliation_string":"Dalhousie University, Nova Scotia, Canada","institution_ids":["https://openalex.org/I129902397"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019738080","display_name":"Norbert Zeh","orcid":"https://orcid.org/0000-0002-0562-1629"},"institutions":[{"id":"https://openalex.org/I129902397","display_name":"Dalhousie University","ror":"https://ror.org/01e6qks80","country_code":"CA","type":"education","lineage":["https://openalex.org/I129902397"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Norbert Zeh","raw_affiliation_strings":["Dalhousie University, Nova Scotia, Canada"],"affiliations":[{"raw_affiliation_string":"Dalhousie University, Nova Scotia, Canada","institution_ids":["https://openalex.org/I129902397"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5013989913","display_name":"Evangelos Milios","orcid":"https://orcid.org/0000-0001-5549-4675"},"institutions":[{"id":"https://openalex.org/I129902397","display_name":"Dalhousie University","ror":"https://ror.org/01e6qks80","country_code":"CA","type":"education","lineage":["https://openalex.org/I129902397"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Evangelos Milios","raw_affiliation_strings":["Dalhousie University, Nova Scotia, Canada"],"affiliations":[{"raw_affiliation_string":"Dalhousie University, Nova Scotia, Canada","institution_ids":["https://openalex.org/I129902397"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5056840301"],"corresponding_institution_ids":["https://openalex.org/I129902397"],"apc_list":null,"apc_paid":null,"fwci":1.3597,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.84575562,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"10"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12761","display_name":"Data Stream Mining Techniques","score":1.0,"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/T12761","display_name":"Data Stream Mining Techniques","score":1.0,"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":0.9948999881744385,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9911999702453613,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8630919456481934},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.8214254379272461},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5666837096214294},{"id":"https://openalex.org/keywords/document-clustering","display_name":"Document clustering","score":0.47621044516563416},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4671090841293335},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.43499937653541565},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.43110793828964233},{"id":"https://openalex.org/keywords/data-stream-clustering","display_name":"Data stream clustering","score":0.4278540015220642},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.33947402238845825},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3179953992366791},{"id":"https://openalex.org/keywords/correlation-clustering","display_name":"Correlation clustering","score":0.31683313846588135},{"id":"https://openalex.org/keywords/cure-data-clustering-algorithm","display_name":"CURE data clustering algorithm","score":0.2215876281261444}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8630919456481934},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.8214254379272461},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5666837096214294},{"id":"https://openalex.org/C177937566","wikidata":"https://www.wikidata.org/wiki/Q4223102","display_name":"Document clustering","level":3,"score":0.47621044516563416},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4671090841293335},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.43499937653541565},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.43110793828964233},{"id":"https://openalex.org/C193143536","wikidata":"https://www.wikidata.org/wiki/Q5227360","display_name":"Data stream clustering","level":5,"score":0.4278540015220642},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.33947402238845825},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3179953992366791},{"id":"https://openalex.org/C94641424","wikidata":"https://www.wikidata.org/wiki/Q5172845","display_name":"Correlation clustering","level":3,"score":0.31683313846588135},{"id":"https://openalex.org/C33704608","wikidata":"https://www.wikidata.org/wiki/Q5014717","display_name":"CURE data clustering algorithm","level":4,"score":0.2215876281261444},{"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3469096.3469866","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3469096.3469866","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 21st ACM Symposium on Document Engineering","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.5099999904632568,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W1597195725","https://openalex.org/W1680822381","https://openalex.org/W1826790618","https://openalex.org/W1976749751","https://openalex.org/W1983910883","https://openalex.org/W2024932032","https://openalex.org/W2028544407","https://openalex.org/W2045938006","https://openalex.org/W2072169887","https://openalex.org/W2088340225","https://openalex.org/W2250539671","https://openalex.org/W2296719434","https://openalex.org/W2338551862","https://openalex.org/W2382102351","https://openalex.org/W2390768509","https://openalex.org/W2403008614","https://openalex.org/W2581984516","https://openalex.org/W2612063921","https://openalex.org/W2750501929","https://openalex.org/W2808998506","https://openalex.org/W2898017895","https://openalex.org/W2914584698","https://openalex.org/W2915063781","https://openalex.org/W3003787189","https://openalex.org/W3034719632","https://openalex.org/W3035983125","https://openalex.org/W3102015031","https://openalex.org/W4236979447","https://openalex.org/W6691431627"],"related_works":["https://openalex.org/W2356198087","https://openalex.org/W3144143113","https://openalex.org/W2371010743","https://openalex.org/W3120229345","https://openalex.org/W1802840531","https://openalex.org/W3022637481","https://openalex.org/W2393816671","https://openalex.org/W1999117613","https://openalex.org/W3186815950","https://openalex.org/W2999604716"],"abstract_inverted_index":{"Short":[0],"text":[1,14,39,66,87,100,109,132,137],"stream":[2,67],"clustering":[3,34,54,68,129],"is":[4,15,40],"an":[5,63],"important":[6],"but":[7],"challenging":[8],"task":[9],"since":[10],"massive":[11,36],"amount":[12,37,47],"of":[13,33,38,48,73,82,114,117,127,130,162,168],"generated":[16],"from":[17],"different":[18],"sources":[19],"such":[20,35],"as":[21,94],"micro-blogging,":[22],"question-answering,":[23],"and":[24,50,77,110,120],"social":[25],"news":[26],"aggregation":[27],"websites.":[28],"The":[29,79,159],"two":[30,59,74],"major":[31],"challenges":[32],"to":[41,51,88,101,138,187],"cluster":[42,90,103,140],"them":[43],"within":[44],"a":[45,86,89,99,102,108,111,136,139],"reasonable":[46],"time":[49,126],"achieve":[52],"better":[53],"result.":[55],"To":[56,97],"overcome":[57],"these":[58],"challenges,":[60],"we":[61],"propose":[62],"efficient":[64],"short":[65,131,182],"algorithm":[69,84,164],"(called":[70],"EStream)":[71],"consisting":[72],"modules:":[75],"online":[76,80,176],"offline.":[78],"module":[81,161,177],"EStream":[83,134,151,163],"assigns":[85,135],"one":[91,93],"by":[92,174],"it":[95,104],"arrives.":[96],"assign":[98],"computes":[105],"similarity":[106,148],"between":[107],"selected":[112],"number":[113],"clusters":[115,119,172],"instead":[116],"all":[118],"thus":[121],"significantly":[122],"reduces":[123],"the":[124,128,145,155,166,171,175,180,188],"running":[125],"streams.":[133],"(new":[141],"or":[142],"existing)":[143],"using":[144],"dynamically":[146],"computed":[147],"thresholds.":[149],"Thus":[150],"efficiently":[152],"deals":[153],"with":[154],"concept":[156],"drift":[157],"problem.":[158],"offline":[160],"enhances":[165],"distributions":[167],"texts":[169,183],"in":[170],"obtained":[173],"so":[178],"that":[179],"upcoming":[181],"can":[184],"be":[185],"assigned":[186],"appropriate":[189],"clusters.":[190]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}