{"id":"https://openalex.org/W2046642399","doi":"https://doi.org/10.1145/2818869.2818886","title":"Improving MapReduce-based Entity-resolution by Data-load Balancing","display_name":"Improving MapReduce-based Entity-resolution by Data-load Balancing","publication_year":2015,"publication_date":"2015-10-07","ids":{"openalex":"https://openalex.org/W2046642399","doi":"https://doi.org/10.1145/2818869.2818886","mag":"2046642399"},"language":"en","primary_location":{"id":"doi:10.1145/2818869.2818886","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2818869.2818886","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ASE BigData &amp; SocialInformatics 2015","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/A5085762059","display_name":"Ming-Yen Lin","orcid":"https://orcid.org/0000-0003-3180-3132"},"institutions":[{"id":"https://openalex.org/I4880106","display_name":"Feng Chia University","ror":"https://ror.org/05vhczg54","country_code":"TW","type":"education","lineage":["https://openalex.org/I4880106"]}],"countries":["TW"],"is_corresponding":true,"raw_author_name":"Ming-Yen Lin","raw_affiliation_strings":["Dept. of Information Engineering and Computer Science, Feng Chia University, Taichung, Taiwan","[Dept. of Information Engineering and Computer Science, Feng Chia University, Taichung, Taiwan]"],"affiliations":[{"raw_affiliation_string":"Dept. of Information Engineering and Computer Science, Feng Chia University, Taichung, Taiwan","institution_ids":["https://openalex.org/I4880106"]},{"raw_affiliation_string":"[Dept. of Information Engineering and Computer Science, Feng Chia University, Taichung, Taiwan]","institution_ids":["https://openalex.org/I4880106"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059113891","display_name":"Tien-Jing Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I4880106","display_name":"Feng Chia University","ror":"https://ror.org/05vhczg54","country_code":"TW","type":"education","lineage":["https://openalex.org/I4880106"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Tien-Jing Wang","raw_affiliation_strings":["Dept. of Information Engineering and Computer Science, Feng Chia University, Taichung, Taiwan","[Dept. of Information Engineering and Computer Science, Feng Chia University, Taichung, Taiwan]"],"affiliations":[{"raw_affiliation_string":"Dept. of Information Engineering and Computer Science, Feng Chia University, Taichung, Taiwan","institution_ids":["https://openalex.org/I4880106"]},{"raw_affiliation_string":"[Dept. of Information Engineering and Computer Science, Feng Chia University, Taichung, Taiwan]","institution_ids":["https://openalex.org/I4880106"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5077724127","display_name":"Sue-Chen Hsueh","orcid":"https://orcid.org/0000-0002-0330-6967"},"institutions":[{"id":"https://openalex.org/I126145234","display_name":"Chaoyang University of Technology","ror":"https://ror.org/04xwksx09","country_code":"TW","type":"education","lineage":["https://openalex.org/I126145234"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Sue-Chen Hsueh","raw_affiliation_strings":["Dept. of Information Management, Chaoyang University of Technology, Taichung, Taiwan","Department of Information Management; Chaoyang University of Technology; Taichung; Taiwan"],"affiliations":[{"raw_affiliation_string":"Dept. of Information Management, Chaoyang University of Technology, Taichung, Taiwan","institution_ids":["https://openalex.org/I126145234"]},{"raw_affiliation_string":"Department of Information Management; Chaoyang University of Technology; Taichung; Taiwan","institution_ids":["https://openalex.org/I126145234"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5085762059"],"corresponding_institution_ids":["https://openalex.org/I4880106"],"apc_list":null,"apc_paid":null,"fwci":0.4006,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.69332644,"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":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10317","display_name":"Advanced Database Systems and Queries","score":0.9695000052452087,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T11614","display_name":"Cloud Data Security Solutions","score":0.9484999775886536,"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":0.8752816319465637},{"id":"https://openalex.org/keywords/blocking","display_name":"Blocking (statistics)","score":0.7305454015731812},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.6344829201698303},{"id":"https://openalex.org/keywords/load-balancing","display_name":"Load balancing (electrical power)","score":0.5712528228759766},{"id":"https://openalex.org/keywords/pairwise-comparison","display_name":"Pairwise comparison","score":0.5679050087928772},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.5629289150238037},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5440536737442017},{"id":"https://openalex.org/keywords/distributed-database","display_name":"Distributed database","score":0.45539847016334534},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.40197548270225525},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.3720127046108246},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.2549998462200165},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.12201368808746338},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.09684726595878601}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8752816319465637},{"id":"https://openalex.org/C144745244","wikidata":"https://www.wikidata.org/wiki/Q4927286","display_name":"Blocking (statistics)","level":2,"score":0.7305454015731812},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.6344829201698303},{"id":"https://openalex.org/C138959212","wikidata":"https://www.wikidata.org/wiki/Q1806783","display_name":"Load balancing (electrical power)","level":3,"score":0.5712528228759766},{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.5679050087928772},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5629289150238037},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5440536737442017},{"id":"https://openalex.org/C70061542","wikidata":"https://www.wikidata.org/wiki/Q989016","display_name":"Distributed database","level":2,"score":0.45539847016334534},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.40197548270225525},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3720127046108246},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2549998462200165},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.12201368808746338},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.09684726595878601},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","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/C187691185","wikidata":"https://www.wikidata.org/wiki/Q2020720","display_name":"Grid","level":2,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","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:10.1145/2818869.2818886","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2818869.2818886","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ASE BigData &amp; SocialInformatics 2015","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/W2024770506","https://openalex.org/W2075975656","https://openalex.org/W2101811230","https://openalex.org/W2122465391","https://openalex.org/W2140509629","https://openalex.org/W2141267666","https://openalex.org/W2490088997","https://openalex.org/W2953034482","https://openalex.org/W4234053595","https://openalex.org/W6669436761"],"related_works":["https://openalex.org/W2487162673","https://openalex.org/W2793211469","https://openalex.org/W2949152769","https://openalex.org/W4372354731","https://openalex.org/W2942366970","https://openalex.org/W2807634898","https://openalex.org/W2010725720","https://openalex.org/W4310066305","https://openalex.org/W4285172683","https://openalex.org/W1973138370"],"abstract_inverted_index":{"Entity":[0],"resolution":[1,91],"(ER)":[2],"is":[3,106],"to":[4,9,32],"identify":[5],"the":[6,10,14,44,103],"entities":[7],"referring":[8],"same":[11],"entity":[12,90],"in":[13,48],"dataset.":[15],"The":[16,40,66],"nature":[17],"of":[18,27,34,46,68],"pairwise":[19],"similarity":[20],"computation":[21],"from":[22,55],"ER":[23],"combined":[24],"with":[25],"growth":[26],"data":[28],"size":[29],"today":[30],"leads":[31],"utilization":[33],"distributed":[35],"computing":[36],"such":[37],"as":[38],"MapReduce.":[39],"blocking":[41,52,60],"techniques":[42],"reduce":[43],"number":[45],"comparisons":[47],"ER.":[49],"However,":[50],"single":[51],"key":[53],"suffers":[54],"incomplete":[56],"results":[57],"but":[58],"multiple":[59,93],"keys":[61],"may":[62],"introduce":[63],"duplicated":[64,69],"comparisons.":[65],"issues":[67],"matching":[70],"and":[71,109],"data-load":[72,85],"balancing":[73],"have":[74],"not":[75],"been":[76],"fully":[77],"studied.":[78],"In":[79],"this":[80],"paper,":[81],"we":[82],"propose":[83],"a":[84],"balanced":[86],"MapReduce":[87],"algorithm":[88,105],"for":[89],"using":[92,97],"keys.":[94],"Our":[95],"experiments":[96],"two":[98],"real":[99],"datasets":[100],"show":[101],"that":[102],"proposed":[104],"both":[107],"efficient":[108],"effective.":[110]},"counts_by_year":[{"year":2017,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
