{"id":"https://openalex.org/W2750964846","doi":"https://doi.org/10.1109/iscc.2017.8024632","title":"Spark-based Streamlined Metablocking","display_name":"Spark-based Streamlined Metablocking","publication_year":2017,"publication_date":"2017-07-01","ids":{"openalex":"https://openalex.org/W2750964846","doi":"https://doi.org/10.1109/iscc.2017.8024632","mag":"2750964846"},"language":"en","primary_location":{"id":"doi:10.1109/iscc.2017.8024632","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscc.2017.8024632","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE Symposium on Computers and Communications (ISCC)","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/A5040142167","display_name":"Tiago Brasileiro Ara\u00fajo","orcid":"https://orcid.org/0000-0001-6339-9117"},"institutions":[{"id":"https://openalex.org/I41455075","display_name":"Universidade Federal de Campina Grande","ror":"https://ror.org/00eftnx64","country_code":"BR","type":"education","lineage":["https://openalex.org/I41455075"]}],"countries":["BR"],"is_corresponding":true,"raw_author_name":"Tiago Brasileiro Araujo","raw_affiliation_strings":["Department of Systems and Computer, Federal University of Campina Grande, Campina Grande, Brazil"],"affiliations":[{"raw_affiliation_string":"Department of Systems and Computer, Federal University of Campina Grande, Campina Grande, Brazil","institution_ids":["https://openalex.org/I41455075"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040330943","display_name":"Carlos Eduardo Santos Pires","orcid":"https://orcid.org/0000-0001-7743-899X"},"institutions":[{"id":"https://openalex.org/I41455075","display_name":"Universidade Federal de Campina Grande","ror":"https://ror.org/00eftnx64","country_code":"BR","type":"education","lineage":["https://openalex.org/I41455075"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Carlos Eduardo Santos Pires","raw_affiliation_strings":["Department of Systems and Computer, Universidade Federal de Campina Grande, Campina Grande, PB, BR"],"affiliations":[{"raw_affiliation_string":"Department of Systems and Computer, Universidade Federal de Campina Grande, Campina Grande, PB, BR","institution_ids":["https://openalex.org/I41455075"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088926017","display_name":"Thiago N\u00f3brega","orcid":"https://orcid.org/0000-0001-7532-2109"},"institutions":[{"id":"https://openalex.org/I136754270","display_name":"Universidade Estadual da Para\u00edba","ror":"https://ror.org/02cm65z11","country_code":"BR","type":"education","lineage":["https://openalex.org/I136754270"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Thiago Pereira da Nobrega","raw_affiliation_strings":["Para\u00edba State University, Campina Grande, Brazil"],"affiliations":[{"raw_affiliation_string":"Para\u00edba State University, Campina Grande, Brazil","institution_ids":["https://openalex.org/I136754270"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5040142167"],"corresponding_institution_ids":["https://openalex.org/I41455075"],"apc_list":null,"apc_paid":null,"fwci":1.8083,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.86545127,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"844","last_page":"850"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9990000128746033,"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":0.9990000128746033,"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/T11478","display_name":"Caching and Content Delivery","score":0.9972000122070312,"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/T10742","display_name":"Peer-to-Peer Network Technologies","score":0.9937000274658203,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/spark","display_name":"SPARK (programming language)","score":0.8050186038017273},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7864406108856201},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5882591009140015},{"id":"https://openalex.org/keywords/blocking","display_name":"Blocking (statistics)","score":0.5876778364181519},{"id":"https://openalex.org/keywords/pruning","display_name":"Pruning","score":0.5678654909133911},{"id":"https://openalex.org/keywords/cardinality","display_name":"Cardinality (data modeling)","score":0.5654765963554382},{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.5490286350250244},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.5026059150695801},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4596402943134308},{"id":"https://openalex.org/keywords/usable","display_name":"USable","score":0.4244835078716278},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3404006361961365},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.3383990526199341},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2866268754005432}],"concepts":[{"id":"https://openalex.org/C2781215313","wikidata":"https://www.wikidata.org/wiki/Q3493345","display_name":"SPARK (programming language)","level":2,"score":0.8050186038017273},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7864406108856201},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5882591009140015},{"id":"https://openalex.org/C144745244","wikidata":"https://www.wikidata.org/wiki/Q4927286","display_name":"Blocking (statistics)","level":2,"score":0.5876778364181519},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.5678654909133911},{"id":"https://openalex.org/C87117476","wikidata":"https://www.wikidata.org/wiki/Q362383","display_name":"Cardinality (data modeling)","level":2,"score":0.5654765963554382},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.5490286350250244},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.5026059150695801},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4596402943134308},{"id":"https://openalex.org/C2780615836","wikidata":"https://www.wikidata.org/wiki/Q2471869","display_name":"USable","level":2,"score":0.4244835078716278},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3404006361961365},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3383990526199341},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2866268754005432},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iscc.2017.8024632","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscc.2017.8024632","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE Symposium on Computers and Communications (ISCC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W1504263697","https://openalex.org/W1547612978","https://openalex.org/W2035880583","https://openalex.org/W2079649893","https://openalex.org/W2079659743","https://openalex.org/W2131975293","https://openalex.org/W2145908616","https://openalex.org/W2216499221","https://openalex.org/W2398333000","https://openalex.org/W2512446543","https://openalex.org/W2559870814","https://openalex.org/W4242744113","https://openalex.org/W6679815717","https://openalex.org/W6712710463","https://openalex.org/W6730127832"],"related_works":["https://openalex.org/W2982321410","https://openalex.org/W2392004567","https://openalex.org/W2046296964","https://openalex.org/W2940029036","https://openalex.org/W4388292429","https://openalex.org/W2756595502","https://openalex.org/W2010789764","https://openalex.org/W2187233292","https://openalex.org/W2219281195","https://openalex.org/W1968167080"],"abstract_inverted_index":{"Blocking":[0],"techniques":[1],"are":[2,38],"widely":[3],"applied":[4,66],"in":[5,13,67,69,88],"Entity":[6],"Resolution":[7],"(ER)":[8],"approaches":[9],"as":[10,33],"preprocessing":[11],"step":[12],"order":[14,70],"to":[15,64,71],"avoid":[16],"the":[17,21,34,48,59,77,80,82,93,100,111],"quadratic":[18],"cost":[19],"of":[20,79],"ER":[22],"task.":[23],"In":[24,43],"this":[25,44,56,89],"context,":[26],"heterogeneous":[27],"data":[28],"and":[29,108],"Big":[30],"Data":[31],"emerges":[32],"major":[35],"challenges":[36],"that":[37,99],"faced":[39],"by":[40],"blocking":[41],"techniques.":[42],"sense,":[45],"we":[46,96],"propose":[47],"novel":[49],"approach":[50,102],"Spark-based":[51],"Streamlined":[52],"Metablocking":[53],"(SS-Metablocking).":[54],"Moreover,":[55],"work":[57],"proposes":[58],"Cardinality-based":[60],"load":[61],"balancing":[62],"technique":[63],"be":[65],"SS-Metablocking":[68],"improve":[72,76],"its":[73],"efficiency.":[74],"To":[75],"effectiveness":[78,109],"SS-Metablocking,":[81],"GWNP":[83],"pruning":[84],"algorithm":[85],"is":[86],"proposed":[87,101],"work.":[90],"Based":[91],"on":[92],"experimental":[94],"results,":[95],"can":[97],"highlight":[98],"presents":[103],"better":[104],"results":[105],"regarding":[106],"efficiency":[107],"than":[110],"state-of-the-art":[112],"approach.":[113]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
