{"id":"https://openalex.org/W3032907619","doi":"https://doi.org/10.1145/3385209.3385224","title":"An Affinity Propagation Approach for Entity Clustering with Spark","display_name":"An Affinity Propagation Approach for Entity Clustering with Spark","publication_year":2020,"publication_date":"2020-02-19","ids":{"openalex":"https://openalex.org/W3032907619","doi":"https://doi.org/10.1145/3385209.3385224","mag":"3032907619"},"language":"en","primary_location":{"id":"doi:10.1145/3385209.3385224","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3385209.3385224","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2020 5th International Conference on Intelligent Information Technology","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/A5019938355","display_name":"Phuc Quang Tran","orcid":"https://orcid.org/0000-0001-5271-2323"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Phuc Quang Tran","raw_affiliation_strings":["Department of Foreign Languages and Informatics, People's Police College III, Cantho, Vietnam"],"affiliations":[{"raw_affiliation_string":"Department of Foreign Languages and Informatics, People's Police College III, Cantho, Vietnam","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072446309","display_name":"Thanh-Ngoan Trieu","orcid":"https://orcid.org/0000-0002-6837-6181"},"institutions":[{"id":"https://openalex.org/I177733328","display_name":"Can Tho University","ror":"https://ror.org/0071qz696","country_code":"VN","type":"education","lineage":["https://openalex.org/I177733328"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Ngoan Thanh Trieu","raw_affiliation_strings":["College of Information and Communication Technology, Can Tho University, Cantho, Vietnam"],"affiliations":[{"raw_affiliation_string":"College of Information and Communication Technology, Can Tho University, Cantho, Vietnam","institution_ids":["https://openalex.org/I177733328"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041604831","display_name":"Huong Hoang Luong","orcid":"https://orcid.org/0000-0002-0398-5090"},"institutions":[{"id":"https://openalex.org/I109689652","display_name":"FPT University","ror":"https://ror.org/03esj4g97","country_code":"VN","type":"education","lineage":["https://openalex.org/I109689652"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Huong Hoang Luong","raw_affiliation_strings":["Department of Information Technology, FPT University, Cantho, Vietnam"],"affiliations":[{"raw_affiliation_string":"Department of Information Technology, FPT University, Cantho, Vietnam","institution_ids":["https://openalex.org/I109689652"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088737329","display_name":"Nghi C. Tran","orcid":null},"institutions":[{"id":"https://openalex.org/I22265921","display_name":"National Central University","ror":"https://ror.org/00944ve71","country_code":"TW","type":"education","lineage":["https://openalex.org/I22265921"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Nghi C. Tran","raw_affiliation_strings":["College of Electrical Engineering and Computer Science, National Central University, Taoyuan, Taiwan"],"affiliations":[{"raw_affiliation_string":"College of Electrical Engineering and Computer Science, National Central University, Taoyuan, Taiwan","institution_ids":["https://openalex.org/I22265921"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5080447230","display_name":"Hiep Xuan Huynh","orcid":"https://orcid.org/0000-0002-9213-131X"},"institutions":[{"id":"https://openalex.org/I177733328","display_name":"Can Tho University","ror":"https://ror.org/0071qz696","country_code":"VN","type":"education","lineage":["https://openalex.org/I177733328"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Hiep Xuan Huynh","raw_affiliation_strings":["College of Information and Communication Technology, Can Tho University, Cantho, Vietnam"],"affiliations":[{"raw_affiliation_string":"College of Information and Communication Technology, Can Tho University, Cantho, Vietnam","institution_ids":["https://openalex.org/I177733328"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5019938355"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.05286373,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"23","issue":null,"first_page":"51","last_page":"55"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11106","display_name":"Data Management and Algorithms","score":0.9986000061035156,"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"}},"topics":[{"id":"https://openalex.org/T11106","display_name":"Data Management and Algorithms","score":0.9986000061035156,"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"}},{"id":"https://openalex.org/T10637","display_name":"Advanced Clustering Algorithms Research","score":0.9976000189781189,"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/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9969000220298767,"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":0.8985364437103271},{"id":"https://openalex.org/keywords/affinity-propagation","display_name":"Affinity propagation","score":0.8681604862213135},{"id":"https://openalex.org/keywords/spark","display_name":"SPARK (programming language)","score":0.8156355619430542},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.761364758014679},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.6511514782905579},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5583100318908691},{"id":"https://openalex.org/keywords/correlation-clustering","display_name":"Correlation clustering","score":0.4808238744735718},{"id":"https://openalex.org/keywords/cure-data-clustering-algorithm","display_name":"CURE data clustering algorithm","score":0.47027426958084106},{"id":"https://openalex.org/keywords/data-stream-clustering","display_name":"Data stream clustering","score":0.45554888248443604},{"id":"https://openalex.org/keywords/fuzzy-clustering","display_name":"Fuzzy clustering","score":0.4545823335647583},{"id":"https://openalex.org/keywords/clustering-high-dimensional-data","display_name":"Clustering high-dimensional data","score":0.44505277276039124},{"id":"https://openalex.org/keywords/canopy-clustering-algorithm","display_name":"Canopy clustering algorithm","score":0.42333298921585083},{"id":"https://openalex.org/keywords/knowledge-extraction","display_name":"Knowledge extraction","score":0.41124778985977173},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.34912392497062683}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.8985364437103271},{"id":"https://openalex.org/C109659709","wikidata":"https://www.wikidata.org/wiki/Q3407504","display_name":"Affinity propagation","level":5,"score":0.8681604862213135},{"id":"https://openalex.org/C2781215313","wikidata":"https://www.wikidata.org/wiki/Q3493345","display_name":"SPARK (programming language)","level":2,"score":0.8156355619430542},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.761364758014679},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.6511514782905579},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5583100318908691},{"id":"https://openalex.org/C94641424","wikidata":"https://www.wikidata.org/wiki/Q5172845","display_name":"Correlation clustering","level":3,"score":0.4808238744735718},{"id":"https://openalex.org/C33704608","wikidata":"https://www.wikidata.org/wiki/Q5014717","display_name":"CURE data clustering algorithm","level":4,"score":0.47027426958084106},{"id":"https://openalex.org/C193143536","wikidata":"https://www.wikidata.org/wiki/Q5227360","display_name":"Data stream clustering","level":5,"score":0.45554888248443604},{"id":"https://openalex.org/C17212007","wikidata":"https://www.wikidata.org/wiki/Q5511111","display_name":"Fuzzy clustering","level":3,"score":0.4545823335647583},{"id":"https://openalex.org/C184509293","wikidata":"https://www.wikidata.org/wiki/Q5136711","display_name":"Clustering high-dimensional data","level":3,"score":0.44505277276039124},{"id":"https://openalex.org/C104047586","wikidata":"https://www.wikidata.org/wiki/Q5033439","display_name":"Canopy clustering algorithm","level":4,"score":0.42333298921585083},{"id":"https://openalex.org/C120567893","wikidata":"https://www.wikidata.org/wiki/Q1582085","display_name":"Knowledge extraction","level":2,"score":0.41124778985977173},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34912392497062683},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3385209.3385224","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3385209.3385224","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2020 5th International Conference on Intelligent Information Technology","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":24,"referenced_works":["https://openalex.org/W22590311","https://openalex.org/W1614298861","https://openalex.org/W1980317569","https://openalex.org/W2020278455","https://openalex.org/W2117130368","https://openalex.org/W2158139315","https://openalex.org/W2163918411","https://openalex.org/W2165232124","https://openalex.org/W2171896402","https://openalex.org/W2313094819","https://openalex.org/W2518059497","https://openalex.org/W2519011775","https://openalex.org/W2561675875","https://openalex.org/W2625777111","https://openalex.org/W2735364069","https://openalex.org/W2740614682","https://openalex.org/W2906635035","https://openalex.org/W2912500072","https://openalex.org/W2951727499","https://openalex.org/W3011594683","https://openalex.org/W4285719527","https://openalex.org/W6680532216","https://openalex.org/W6680699249","https://openalex.org/W6687322159"],"related_works":["https://openalex.org/W2362911195","https://openalex.org/W2245611357","https://openalex.org/W2352610727","https://openalex.org/W4301002638","https://openalex.org/W2794209582","https://openalex.org/W2358586643","https://openalex.org/W2897883632","https://openalex.org/W2371010743","https://openalex.org/W2163563073","https://openalex.org/W2330550450"],"abstract_inverted_index":{"With":[0],"the":[1,8,16,19,31,52,57,61,86,91,100,106],"dramatically":[2],"increasing":[3],"amount":[4],"of":[5,13,54,63,88],"electronic":[6],"data,":[7],"automatic":[9],"detection":[10],"and":[11,37,56],"extraction":[12],"information":[14],"in":[15,42],"text":[17],"is":[18,30,97],"first":[20],"step":[21],"for":[22,34,81,103],"all":[23],"other":[24],"data":[25,40],"analysis":[26],"activities.":[27],"Clustering":[28],"entities":[29,83],"important":[32],"methods":[33,47],"discovering":[35],"knowledge":[36],"extracting":[38],"appropriate":[39],"applied":[41],"several":[43],"applications.":[44],"The":[45,95,109],"clustering":[46,82,107],"often":[48],"need":[49],"to":[50],"pre-determine":[51],"number":[53,87],"clusters":[55,89],"initial":[58],"centers":[59],"thus":[60],"problem":[62,80],"\"initial":[64],"staring":[65],"conditions\"":[66],"usually":[67],"occurs.":[68],"In":[69],"this":[70,79],"paper":[71],"we":[72],"propose":[73],"a":[74],"new":[75],"approach":[76],"that":[77],"overcome":[78],"without":[84],"pre-defining":[85],"with":[90],"Affinity":[92],"Propagation":[93],"algorithm.":[94],"algorithm":[96],"built":[98],"on":[99,113],"Spark":[101],"platform":[102],"speed":[104],"up":[105],"process.":[108],"experiments":[110],"are":[111],"conducted":[112],"different":[114],"characteristics":[115],"datasets.":[116]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}