{"id":"https://openalex.org/W1585388891","doi":"https://doi.org/10.1109/ccis.2014.7175694","title":"Incremental clustering in short text streams based on BM25","display_name":"Incremental clustering in short text streams based on BM25","publication_year":2014,"publication_date":"2014-11-01","ids":{"openalex":"https://openalex.org/W1585388891","doi":"https://doi.org/10.1109/ccis.2014.7175694","mag":"1585388891"},"language":"en","primary_location":{"id":"doi:10.1109/ccis.2014.7175694","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ccis.2014.7175694","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE 3rd International Conference on Cloud Computing and Intelligence Systems","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/A5100936028","display_name":"XU Li-Xin","orcid":null},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Lixin Xu","raw_affiliation_strings":["Beijing University of Posts and Telecommunications, Beijing, China","Beijing University of Posts and Telecommunications, 100876 China"],"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]},{"raw_affiliation_string":"Beijing University of Posts and Telecommunications, 100876 China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100323016","display_name":"Guang Chen","orcid":"https://orcid.org/0000-0001-5611-6561"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guang Chen","raw_affiliation_strings":["Beijing University of Posts and Telecommunications, Beijing, China","Beijing University of Posts and Telecommunications, 100876 China"],"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]},{"raw_affiliation_string":"Beijing University of Posts and Telecommunications, 100876 China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101012679","display_name":"Lei Yang","orcid":"https://orcid.org/0000-0001-6466-5755"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lei Yang","raw_affiliation_strings":["Beijing University of Posts and Telecommunications, Beijing, China","Beijing University of Posts and Telecommunications, 100876 China"],"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]},{"raw_affiliation_string":"Beijing University of Posts and Telecommunications, 100876 China","institution_ids":["https://openalex.org/I139759216"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5100936028"],"corresponding_institution_ids":["https://openalex.org/I139759216"],"apc_list":null,"apc_paid":null,"fwci":0.818,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.79252039,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"8","last_page":"12"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10637","display_name":"Advanced Clustering Algorithms Research","score":0.9940000176429749,"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/T10637","display_name":"Advanced Clustering Algorithms Research","score":0.9940000176429749,"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/T12761","display_name":"Data Stream Mining Techniques","score":0.9939000010490417,"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":0.9929999709129333,"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/cluster-analysis","display_name":"Cluster analysis","score":0.8248692750930786},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7895597219467163},{"id":"https://openalex.org/keywords/data-stream-clustering","display_name":"Data stream clustering","score":0.6663426160812378},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.6267262697219849},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.6148003935813904},{"id":"https://openalex.org/keywords/fuzzy-clustering","display_name":"Fuzzy clustering","score":0.4737868010997772},{"id":"https://openalex.org/keywords/correlation-clustering","display_name":"Correlation clustering","score":0.4680708646774292},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46252354979515076},{"id":"https://openalex.org/keywords/document-clustering","display_name":"Document clustering","score":0.44916871190071106},{"id":"https://openalex.org/keywords/concept-drift","display_name":"Concept drift","score":0.42055195569992065},{"id":"https://openalex.org/keywords/cure-data-clustering-algorithm","display_name":"CURE data clustering algorithm","score":0.39294952154159546},{"id":"https://openalex.org/keywords/data-stream-mining","display_name":"Data stream mining","score":0.3835693895816803},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.32667073607444763},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.08119186758995056}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.8248692750930786},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7895597219467163},{"id":"https://openalex.org/C193143536","wikidata":"https://www.wikidata.org/wiki/Q5227360","display_name":"Data stream clustering","level":5,"score":0.6663426160812378},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.6267262697219849},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.6148003935813904},{"id":"https://openalex.org/C17212007","wikidata":"https://www.wikidata.org/wiki/Q5511111","display_name":"Fuzzy clustering","level":3,"score":0.4737868010997772},{"id":"https://openalex.org/C94641424","wikidata":"https://www.wikidata.org/wiki/Q5172845","display_name":"Correlation clustering","level":3,"score":0.4680708646774292},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46252354979515076},{"id":"https://openalex.org/C177937566","wikidata":"https://www.wikidata.org/wiki/Q4223102","display_name":"Document clustering","level":3,"score":0.44916871190071106},{"id":"https://openalex.org/C60777511","wikidata":"https://www.wikidata.org/wiki/Q3045002","display_name":"Concept drift","level":3,"score":0.42055195569992065},{"id":"https://openalex.org/C33704608","wikidata":"https://www.wikidata.org/wiki/Q5014717","display_name":"CURE data clustering algorithm","level":4,"score":0.39294952154159546},{"id":"https://openalex.org/C89198739","wikidata":"https://www.wikidata.org/wiki/Q3079880","display_name":"Data stream mining","level":2,"score":0.3835693895816803},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.32667073607444763},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.08119186758995056}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ccis.2014.7175694","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ccis.2014.7175694","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE 3rd International Conference on Cloud Computing and Intelligence Systems","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W13337097","https://openalex.org/W2003850925","https://openalex.org/W2098071561","https://openalex.org/W2112800329","https://openalex.org/W2155772381","https://openalex.org/W2356198087","https://openalex.org/W2369708710","https://openalex.org/W2373766213","https://openalex.org/W2379538068","https://openalex.org/W6600533390"],"related_works":["https://openalex.org/W2802243998","https://openalex.org/W2469699777","https://openalex.org/W4200217704","https://openalex.org/W3201554469","https://openalex.org/W2368264659","https://openalex.org/W4307392573","https://openalex.org/W3112950814","https://openalex.org/W3208495060","https://openalex.org/W4312214159","https://openalex.org/W2079625735"],"abstract_inverted_index":{"Since":[0],"short":[1,4,33,49,103],"text":[2,34,50,104],"is":[3],"of":[5,28,60,67,102],"keywords":[6,64],"and":[7,25,65,70,79,94,98],"has":[8],"sparse":[9],"features,":[10],"it":[11],"brings":[12],"about":[13],"the":[14,38,83,89,109],"similarity":[15,75,90],"drift":[16,91],"problem.":[17],"The":[18,55],"traditional":[19,110],"clustering":[20,46,86,111],"algorithms":[21],"are":[22],"usually":[23],"ineffective":[24],"a":[26],"waste":[27],"resources":[29],"on":[30,53],"dealing":[31],"with":[32,108],"stream.":[35],"To":[36],"overcome":[37],"above":[39],"problems,":[40],"this":[41],"paper":[42],"proposes":[43],"an":[44],"incremental":[45,85],"algorithm":[47,87],"in":[48,100],"streams":[51],"based":[52],"BM25.":[54],"approach":[56],"makes":[57],"full":[58],"use":[59],"BM25":[61],"to":[62,74],"extract":[63],"weights":[66],"each":[68],"cluster,":[69],"applies":[71],"extracted":[72],"parameters":[73],"calculation.":[76],"Theoretical":[77],"analysis":[78],"experiments":[80],"show":[81],"that":[82],"proposed":[84],"solves":[88],"problem":[92],"well":[93],"achieves":[95],"satisfactory":[96],"accuracy":[97],"performance":[99],"terms":[101],"stream":[105],"clustering,":[106],"compared":[107],"algorithms.":[112]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2016,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}