{"id":"https://openalex.org/W3030174007","doi":"https://doi.org/10.1145/3391274.3393632","title":"Towards making sense of Spark-SQL performance for processing vast distributed RDF datasets","display_name":"Towards making sense of Spark-SQL performance for processing vast distributed RDF datasets","publication_year":2020,"publication_date":"2020-05-26","ids":{"openalex":"https://openalex.org/W3030174007","doi":"https://doi.org/10.1145/3391274.3393632","mag":"3030174007"},"language":"en","primary_location":{"id":"doi:10.1145/3391274.3393632","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3391274.3393632","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of The International Workshop on Semantic Big Data","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/A5101606061","display_name":"Mohamed Ragab","orcid":"https://orcid.org/0000-0002-9048-7873"},"institutions":[{"id":"https://openalex.org/I56085075","display_name":"University of Tartu","ror":"https://ror.org/03z77qz90","country_code":"EE","type":"education","lineage":["https://openalex.org/I56085075"]}],"countries":["EE"],"is_corresponding":false,"raw_author_name":"Mohamed Ragab","raw_affiliation_strings":["Tartu University, Tartu, Estonia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tartu University, Tartu, Estonia","institution_ids":["https://openalex.org/I56085075"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101434315","display_name":"Riccardo Tommasini","orcid":"https://orcid.org/0000-0003-3404-5250"},"institutions":[{"id":"https://openalex.org/I56085075","display_name":"University of Tartu","ror":"https://ror.org/03z77qz90","country_code":"EE","type":"education","lineage":["https://openalex.org/I56085075"]}],"countries":["EE"],"is_corresponding":false,"raw_author_name":"Riccardo Tommasini","raw_affiliation_strings":["Tartu University, Tartu, Estonia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tartu University, Tartu, Estonia","institution_ids":["https://openalex.org/I56085075"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057685386","display_name":"Sadiq Eyvazov","orcid":null},"institutions":[{"id":"https://openalex.org/I56085075","display_name":"University of Tartu","ror":"https://ror.org/03z77qz90","country_code":"EE","type":"education","lineage":["https://openalex.org/I56085075"]}],"countries":["EE"],"is_corresponding":false,"raw_author_name":"Sadiq Eyvazov","raw_affiliation_strings":["Tartu University, Tartu, Estonia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tartu University, Tartu, Estonia","institution_ids":["https://openalex.org/I56085075"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5000296607","display_name":"Sherif Sakr","orcid":"https://orcid.org/0000-0002-2503-523X"},"institutions":[{"id":"https://openalex.org/I56085075","display_name":"University of Tartu","ror":"https://ror.org/03z77qz90","country_code":"EE","type":"education","lineage":["https://openalex.org/I56085075"]}],"countries":["EE"],"is_corresponding":false,"raw_author_name":"Sherif Sakr","raw_affiliation_strings":["Tartu University, Tartu, Estonia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tartu University, Tartu, Estonia","institution_ids":["https://openalex.org/I56085075"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.5873,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.68696012,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"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/T12292","display_name":"Graph Theory and Algorithms","score":0.9993000030517578,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T12292","display_name":"Graph Theory and Algorithms","score":0.9993000030517578,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10215","display_name":"Semantic Web and Ontologies","score":0.9991999864578247,"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.9976999759674072,"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/sparql","display_name":"SPARQL","score":0.9455378651618958},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8821860551834106},{"id":"https://openalex.org/keywords/rdf","display_name":"RDF","score":0.880227267742157},{"id":"https://openalex.org/keywords/sql","display_name":"SQL","score":0.6644799113273621},{"id":"https://openalex.org/keywords/spark","display_name":"SPARK (programming language)","score":0.6351991891860962},{"id":"https://openalex.org/keywords/rdf-schema","display_name":"RDF Schema","score":0.5680751204490662},{"id":"https://openalex.org/keywords/linked-data","display_name":"Linked data","score":0.5460202693939209},{"id":"https://openalex.org/keywords/cwm","display_name":"Cwm","score":0.5032224059104919},{"id":"https://openalex.org/keywords/rdf-query-language","display_name":"RDF query language","score":0.4780224561691284},{"id":"https://openalex.org/keywords/semantic-web","display_name":"Semantic Web","score":0.4659280478954315},{"id":"https://openalex.org/keywords/named-graph","display_name":"Named graph","score":0.4406065344810486},{"id":"https://openalex.org/keywords/relational-database-management-system","display_name":"Relational database management system","score":0.4402669072151184},{"id":"https://openalex.org/keywords/relational-database","display_name":"Relational database","score":0.4341002404689789},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.42542362213134766},{"id":"https://openalex.org/keywords/semantic-analytics","display_name":"Semantic analytics","score":0.4200298488140106},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.4197325110435486},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.3728626072406769},{"id":"https://openalex.org/keywords/social-semantic-web","display_name":"Social Semantic Web","score":0.19032469391822815},{"id":"https://openalex.org/keywords/search-engine","display_name":"Search engine","score":0.1855718493461609},{"id":"https://openalex.org/keywords/web-search-query","display_name":"Web search query","score":0.15440037846565247},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.12938982248306274},{"id":"https://openalex.org/keywords/web-query-classification","display_name":"Web query classification","score":0.08028468489646912}],"concepts":[{"id":"https://openalex.org/C41009113","wikidata":"https://www.wikidata.org/wiki/Q54871","display_name":"SPARQL","level":4,"score":0.9455378651618958},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8821860551834106},{"id":"https://openalex.org/C147497476","wikidata":"https://www.wikidata.org/wiki/Q54872","display_name":"RDF","level":3,"score":0.880227267742157},{"id":"https://openalex.org/C510870499","wikidata":"https://www.wikidata.org/wiki/Q47607","display_name":"SQL","level":2,"score":0.6644799113273621},{"id":"https://openalex.org/C2781215313","wikidata":"https://www.wikidata.org/wiki/Q3493345","display_name":"SPARK (programming language)","level":2,"score":0.6351991891860962},{"id":"https://openalex.org/C15657843","wikidata":"https://www.wikidata.org/wiki/Q1751819","display_name":"RDF Schema","level":5,"score":0.5680751204490662},{"id":"https://openalex.org/C69075417","wikidata":"https://www.wikidata.org/wiki/Q515701","display_name":"Linked data","level":3,"score":0.5460202693939209},{"id":"https://openalex.org/C157595922","wikidata":"https://www.wikidata.org/wiki/Q50745537","display_name":"Cwm","level":5,"score":0.5032224059104919},{"id":"https://openalex.org/C96956885","wikidata":"https://www.wikidata.org/wiki/Q6138701","display_name":"RDF query language","level":5,"score":0.4780224561691284},{"id":"https://openalex.org/C2129575","wikidata":"https://www.wikidata.org/wiki/Q54837","display_name":"Semantic Web","level":2,"score":0.4659280478954315},{"id":"https://openalex.org/C110893760","wikidata":"https://www.wikidata.org/wiki/Q3115590","display_name":"Named graph","level":5,"score":0.4406065344810486},{"id":"https://openalex.org/C24394798","wikidata":"https://www.wikidata.org/wiki/Q192588","display_name":"Relational database management system","level":3,"score":0.4402669072151184},{"id":"https://openalex.org/C5655090","wikidata":"https://www.wikidata.org/wiki/Q192588","display_name":"Relational database","level":2,"score":0.4341002404689789},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.42542362213134766},{"id":"https://openalex.org/C148792806","wikidata":"https://www.wikidata.org/wiki/Q7449046","display_name":"Semantic analytics","level":4,"score":0.4200298488140106},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4197325110435486},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.3728626072406769},{"id":"https://openalex.org/C534406577","wikidata":"https://www.wikidata.org/wiki/Q7550843","display_name":"Social Semantic Web","level":3,"score":0.19032469391822815},{"id":"https://openalex.org/C97854310","wikidata":"https://www.wikidata.org/wiki/Q19541","display_name":"Search engine","level":2,"score":0.1855718493461609},{"id":"https://openalex.org/C164120249","wikidata":"https://www.wikidata.org/wiki/Q995982","display_name":"Web search query","level":3,"score":0.15440037846565247},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.12938982248306274},{"id":"https://openalex.org/C118689300","wikidata":"https://www.wikidata.org/wiki/Q7978614","display_name":"Web query classification","level":4,"score":0.08028468489646912},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3391274.3393632","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3391274.3393632","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of The International Workshop on Semantic Big Data","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4300000071525574,"id":"https://metadata.un.org/sdg/17","display_name":"Partnerships for the goals"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W156852397","https://openalex.org/W191761767","https://openalex.org/W1906114547","https://openalex.org/W1996708667","https://openalex.org/W2033971127","https://openalex.org/W2113582899","https://openalex.org/W2131485737","https://openalex.org/W2140613126","https://openalex.org/W2148522916","https://openalex.org/W2250093878","https://openalex.org/W2542459869","https://openalex.org/W2765581018","https://openalex.org/W2899298991","https://openalex.org/W2914878865","https://openalex.org/W2918921333","https://openalex.org/W2944912777","https://openalex.org/W2995449190","https://openalex.org/W2997361479","https://openalex.org/W3009233884"],"related_works":["https://openalex.org/W4301152651","https://openalex.org/W2416869599","https://openalex.org/W3013807178","https://openalex.org/W2316359368","https://openalex.org/W2363838908","https://openalex.org/W2092512344","https://openalex.org/W2612001157","https://openalex.org/W3083425935","https://openalex.org/W2402236473","https://openalex.org/W2785696006"],"abstract_inverted_index":{"Recently,":[0],"a":[1,113],"wide":[2],"range":[3],"of":[4,16,30,38,116,119,150,166],"Web":[5,70],"applications":[6],"(e.g.":[7],"DBPedia,":[8],"Uniprot,":[9],"and":[10,21,41,46,135,142,181,187],"Probase)":[11],"are":[12,87],"built":[13],"on":[14,83,95],"top":[15],"vast":[17,61],"RDF":[18,48,102,132],"knowledge":[19,32],"bases":[20,33],"using":[22,129,151],"the":[23,36,68,117,148,164,174,185,188,192],"SPARQL":[24,124],"query":[25],"language.":[26],"The":[27],"continuous":[28],"growth":[29],"these":[31],"led":[34],"to":[35],"investigation":[37],"new":[39],"paradigms":[40],"technologies":[42],"for":[43,89,122,191],"storing,":[44],"accessing,":[45],"querying":[47],"data.":[49],"In":[50,108,144],"practice,":[51],"modern":[52],"big":[53],"data":[54,99],"systems":[55],"(e.g,":[56],"Hadoop,":[57],"Spark)":[58],"can":[59],"handle":[60],"relational":[62,90,133,159],"repositories,":[63],"however,":[64,92],"their":[65,93],"application":[66],"in":[67],"Semantic":[69],"context":[71],"is":[72,78],"still":[73],"limited.":[74],"One":[75],"possible":[76],"reason":[77],"that":[79,176],"such":[80],"frameworks":[81],"rely":[82],"distributed":[84],"systems,":[85],"which":[86],"good":[88],"data,":[91],"performance":[94,118],"dealing":[96],"with":[97,157],"graph":[98],"models":[100],"like":[101],"has":[103],"not":[104],"been":[105],"well-studied":[106],"yet.":[107],"this":[109],"paper,":[110],"we":[111,146,162,170,183],"present":[112,171],"systematic":[114],"evaluation":[115],"SparkSQL":[120],"engine":[121],"processing":[123],"queries.":[125],"We":[126],"stated":[127],"it":[128],"three":[130,152],"relevant":[131],"schemas,":[134],"two":[136],"different":[137,153,178],"storage":[138],"backends,":[139],"namely,":[140],"Hive,":[141],"HDFS.":[143],"addition,":[145],"show":[147],"impact":[149],"RDF-based":[154],"partitioning":[155],"techniques":[156],"our":[158,167],"scenario.":[160,195],"Additionally,":[161],"discuss":[163],"results":[165],"experiments:":[168],"(i)":[169],"insights":[172],"about":[173],"trade-offs":[175],"characterize":[177],"experimental":[179],"configurations,":[180],"(ii)":[182],"identify":[184],"best":[186],"worst":[189],"ones":[190],"SP2Bench's":[193],"benchmark":[194]},"counts_by_year":[{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":3}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}