{"id":"https://openalex.org/W2904595868","doi":"https://doi.org/10.3390/a11120209","title":"Hadoop vs. Spark: Impact on Performance of the Hammer Query Engine for Open Data Corpora","display_name":"Hadoop vs. Spark: Impact on Performance of the Hammer Query Engine for Open Data Corpora","publication_year":2018,"publication_date":"2018-12-17","ids":{"openalex":"https://openalex.org/W2904595868","doi":"https://doi.org/10.3390/a11120209","mag":"2904595868"},"language":"en","primary_location":{"id":"doi:10.3390/a11120209","is_oa":true,"landing_page_url":"https://doi.org/10.3390/a11120209","pdf_url":"https://www.mdpi.com/1999-4893/11/12/209/pdf?version=1545041431","source":{"id":"https://openalex.org/S190629608","display_name":"Algorithms","issn_l":"1999-4893","issn":["1999-4893"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Algorithms","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.mdpi.com/1999-4893/11/12/209/pdf?version=1545041431","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5025594972","display_name":"Mauro Pelucchi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mauro Pelucchi","raw_affiliation_strings":["Tabulaex, A Burning Glass Company, 20126 Milano, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tabulaex, A Burning Glass Company, 20126 Milano, Italy","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013644406","display_name":"Giuseppe Psaila","orcid":"https://orcid.org/0000-0002-9228-560X"},"institutions":[{"id":"https://openalex.org/I11039511","display_name":"University of Bergamo","ror":"https://ror.org/02mbd5571","country_code":"IT","type":"education","lineage":["https://openalex.org/I11039511"]}],"countries":["IT"],"is_corresponding":true,"raw_author_name":"Giuseppe Psaila","raw_affiliation_strings":["Dipartimento di Ingegneria Gestionale, dell\u2019Informazione e della Produzione (DIGIP), University of Bergamo, 24044 Dalmine, Italy","Dipartimento di Ingegneria Gestionale, dell'Informazione e della Produzione (DIGIP), University of Bergamo, 24044 Dalmine, Italy"],"raw_orcid":"https://orcid.org/0000-0002-9228-560X","affiliations":[{"raw_affiliation_string":"Dipartimento di Ingegneria Gestionale, dell\u2019Informazione e della Produzione (DIGIP), University of Bergamo, 24044 Dalmine, Italy","institution_ids":["https://openalex.org/I11039511"]},{"raw_affiliation_string":"Dipartimento di Ingegneria Gestionale, dell'Informazione e della Produzione (DIGIP), University of Bergamo, 24044 Dalmine, Italy","institution_ids":["https://openalex.org/I11039511"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5012705197","display_name":"Maurizio Toccu","orcid":"https://orcid.org/0000-0002-5769-1311"},"institutions":[{"id":"https://openalex.org/I11039511","display_name":"University of Bergamo","ror":"https://ror.org/02mbd5571","country_code":"IT","type":"education","lineage":["https://openalex.org/I11039511"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Maurizio Toccu","raw_affiliation_strings":["Dipartimento di Ingegneria Gestionale, dell\u2019Informazione e della Produzione (DIGIP), University of Bergamo, 24044 Dalmine, Italy","Dipartimento di Ingegneria Gestionale, dell'Informazione e della Produzione (DIGIP), University of Bergamo, 24044 Dalmine, Italy"],"raw_orcid":"https://orcid.org/0000-0002-5769-1311","affiliations":[{"raw_affiliation_string":"Dipartimento di Ingegneria Gestionale, dell\u2019Informazione e della Produzione (DIGIP), University of Bergamo, 24044 Dalmine, Italy","institution_ids":["https://openalex.org/I11039511"]},{"raw_affiliation_string":"Dipartimento di Ingegneria Gestionale, dell'Informazione e della Produzione (DIGIP), University of Bergamo, 24044 Dalmine, Italy","institution_ids":["https://openalex.org/I11039511"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5013644406"],"corresponding_institution_ids":["https://openalex.org/I11039511"],"apc_list":{"value":1600,"currency":"CHF","value_usd":1782},"apc_paid":{"value":1600,"currency":"CHF","value_usd":1782},"fwci":1.9401,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":{"value":0.9091557,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":"11","issue":"12","first_page":"209","last_page":"209"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.9994999766349792,"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"}},"topics":[{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.9994999766349792,"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"}},{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.9980999827384949,"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/T11478","display_name":"Caching and Content Delivery","score":0.9936000108718872,"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/computer-science","display_name":"Computer science","score":0.8776774406433105},{"id":"https://openalex.org/keywords/spark","display_name":"SPARK (programming language)","score":0.7615878582000732},{"id":"https://openalex.org/keywords/rewriting","display_name":"Rewriting","score":0.6663665771484375},{"id":"https://openalex.org/keywords/query-expansion","display_name":"Query expansion","score":0.616223156452179},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5218921303749084},{"id":"https://openalex.org/keywords/web-search-query","display_name":"Web search query","score":0.5216541886329651},{"id":"https://openalex.org/keywords/search-engine","display_name":"Search engine","score":0.5111997723579407},{"id":"https://openalex.org/keywords/query-language","display_name":"Query language","score":0.4870029091835022},{"id":"https://openalex.org/keywords/web-query-classification","display_name":"Web query classification","score":0.45885470509529114},{"id":"https://openalex.org/keywords/sparql","display_name":"SPARQL","score":0.45684823393821716},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.3595648407936096},{"id":"https://openalex.org/keywords/rdf","display_name":"RDF","score":0.32377880811691284},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.19017541408538818},{"id":"https://openalex.org/keywords/semantic-web","display_name":"Semantic Web","score":0.13736975193023682}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8776774406433105},{"id":"https://openalex.org/C2781215313","wikidata":"https://www.wikidata.org/wiki/Q3493345","display_name":"SPARK (programming language)","level":2,"score":0.7615878582000732},{"id":"https://openalex.org/C154690210","wikidata":"https://www.wikidata.org/wiki/Q1668499","display_name":"Rewriting","level":2,"score":0.6663665771484375},{"id":"https://openalex.org/C99016210","wikidata":"https://www.wikidata.org/wiki/Q5488129","display_name":"Query expansion","level":2,"score":0.616223156452179},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5218921303749084},{"id":"https://openalex.org/C164120249","wikidata":"https://www.wikidata.org/wiki/Q995982","display_name":"Web search query","level":3,"score":0.5216541886329651},{"id":"https://openalex.org/C97854310","wikidata":"https://www.wikidata.org/wiki/Q19541","display_name":"Search engine","level":2,"score":0.5111997723579407},{"id":"https://openalex.org/C192028432","wikidata":"https://www.wikidata.org/wiki/Q845739","display_name":"Query language","level":2,"score":0.4870029091835022},{"id":"https://openalex.org/C118689300","wikidata":"https://www.wikidata.org/wiki/Q7978614","display_name":"Web query classification","level":4,"score":0.45885470509529114},{"id":"https://openalex.org/C41009113","wikidata":"https://www.wikidata.org/wiki/Q54871","display_name":"SPARQL","level":4,"score":0.45684823393821716},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.3595648407936096},{"id":"https://openalex.org/C147497476","wikidata":"https://www.wikidata.org/wiki/Q54872","display_name":"RDF","level":3,"score":0.32377880811691284},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.19017541408538818},{"id":"https://openalex.org/C2129575","wikidata":"https://www.wikidata.org/wiki/Q54837","display_name":"Semantic Web","level":2,"score":0.13736975193023682}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.3390/a11120209","is_oa":true,"landing_page_url":"https://doi.org/10.3390/a11120209","pdf_url":"https://www.mdpi.com/1999-4893/11/12/209/pdf?version=1545041431","source":{"id":"https://openalex.org/S190629608","display_name":"Algorithms","issn_l":"1999-4893","issn":["1999-4893"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Algorithms","raw_type":"journal-article"},{"id":"pmh:oai:aisberg.unibg.it:10446/132600","is_oa":true,"landing_page_url":"http://hdl.handle.net/10446/132600","pdf_url":null,"source":{"id":"https://openalex.org/S4377196347","display_name":"Aisberg (University of Bergamo)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I11039511","host_organization_name":"University of Bergamo","host_organization_lineage":["https://openalex.org/I11039511"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:oai:doaj.org/article:562693326b244ff284afaca4cd82f1e8","is_oa":true,"landing_page_url":"https://doaj.org/article/562693326b244ff284afaca4cd82f1e8","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Algorithms, Vol 11, Iss 12, p 209 (2018)","raw_type":"article"},{"id":"pmh:oai:mdpi.com:/1999-4893/11/12/209/","is_oa":true,"landing_page_url":"http://dx.doi.org/10.3390/a11120209","pdf_url":null,"source":{"id":"https://openalex.org/S4306400947","display_name":"MDPI (MDPI AG)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210097602","host_organization_name":"Multidisciplinary Digital Publishing Institute (Switzerland)","host_organization_lineage":["https://openalex.org/I4210097602"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Algorithms","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.3390/a11120209","is_oa":true,"landing_page_url":"https://doi.org/10.3390/a11120209","pdf_url":"https://www.mdpi.com/1999-4893/11/12/209/pdf?version=1545041431","source":{"id":"https://openalex.org/S190629608","display_name":"Algorithms","issn_l":"1999-4893","issn":["1999-4893"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Algorithms","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.46000000834465027,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2904595868.pdf","grobid_xml":"https://content.openalex.org/works/W2904595868.grobid-xml"},"referenced_works_count":29,"referenced_works":["https://openalex.org/W46452414","https://openalex.org/W71739758","https://openalex.org/W86569730","https://openalex.org/W410850256","https://openalex.org/W1976860187","https://openalex.org/W1985419898","https://openalex.org/W1992540139","https://openalex.org/W2013344760","https://openalex.org/W2040263621","https://openalex.org/W2046804219","https://openalex.org/W2078082072","https://openalex.org/W2087177601","https://openalex.org/W2101114896","https://openalex.org/W2105947650","https://openalex.org/W2119738171","https://openalex.org/W2120458882","https://openalex.org/W2173213060","https://openalex.org/W2189465200","https://openalex.org/W2542459869","https://openalex.org/W2620658849","https://openalex.org/W2741489693","https://openalex.org/W2808946057","https://openalex.org/W2963288913","https://openalex.org/W4213009331","https://openalex.org/W4240422607","https://openalex.org/W6608302322","https://openalex.org/W6614148910","https://openalex.org/W6687322159","https://openalex.org/W6713134421"],"related_works":["https://openalex.org/W2572349046","https://openalex.org/W2096359267","https://openalex.org/W2017989738","https://openalex.org/W1981131819","https://openalex.org/W3197639690","https://openalex.org/W2026738364","https://openalex.org/W2146885082","https://openalex.org/W2186703450","https://openalex.org/W2124814993","https://openalex.org/W1984397732"],"abstract_inverted_index":{"The":[0,76,245,269],"Hammer":[1,212],"prototype":[2],"is":[3,56],"a":[4,126],"query":[5,54,64,97,144,156,213,221],"engine":[6,55,145],"for":[7,58,177,280],"corpora":[8,123],"of":[9,18,50,78,106,114,129,154,198,219,261,285,290],"Open":[10,26],"Data":[11,27,265],"that":[12,111],"provides":[13],"users":[14,31],"with":[15,258],"the":[16,48,53,62,66,96,102,107,112,115,136,143,155,161,166,185,196,200,211,220,228,235,251,259,267,283],"concept":[17],"blind":[19,63],"querying.":[20],"Since":[21],"data":[22,37,68,130],"sets":[23,38],"published":[24],"on":[25,160,165,184],"portals":[28],"are":[29,39,172,273],"heterogeneous,":[30],"wishing":[32],"to":[33,65,134,141,209],"find":[34],"out":[35],"interesting":[36],"blind:":[40],"queries":[41],"cannot":[42],"be":[43],"fully":[44],"specified,":[45],"as":[46],"in":[47,83,94,101,139,266],"case":[49],"databases.":[51],"Consequently,":[52],"responsible":[57],"rewriting":[59,227,234],"and":[60,73,146,170,179,203,275],"adapting":[61],"actual":[67],"sets,":[69],"by":[70,232,237,243,254,288],"exploiting":[71,238],"lexical":[72],"semantic":[74],"similarity.":[75],"effectiveness":[77],"this":[79,88,189],"approach":[80,202],"was":[81,118],"discussed":[82],"our":[84,92,193],"previous":[85],"works.":[86],"In":[87,99,188],"paper,":[89,190],"we":[90,109,191,215,248,271],"report":[91],"experience":[93],"developing":[95],"engine.":[98],"fact,":[100],"very":[103,174],"first":[104],"version":[105],"prototype,":[108],"realized":[110],"implementation":[113],"retrieval":[116],"technique":[117],"too":[119],"slow,":[120],"even":[121],"though":[122],"contained":[124],"only":[125],"few":[127],"thousands":[128],"sets.":[131],"We":[132,149],"decided":[133],"adopt":[135],"Map-Reduce":[137,186,201,291],"paradigm,":[138],"order":[140],"parallelize":[142,210],"improve":[147],"performances.":[148],"passed":[150],"through":[151],"several":[152],"versions":[153],"engine,":[157,222],"either":[158,223],"based":[159,183],"Hadoop":[162,169],"framework":[163],"or":[164,230],"Spark":[167,171],"framework.":[168],"two":[173,205],"popular":[175],"frameworks":[176,208],"writing":[178],"executing":[180],"parallel":[181],"algorithms":[182,287],"paradigm.":[187],"present":[192],"study":[194],"about":[195],"impact":[197],"adopting":[199],"its":[204],"most":[206],"famous":[207],"engine;":[214],"discuss":[216],"various":[217],"implementations":[218],"obtained":[224,231],"without":[225],"significantly":[226],"algorithm":[229,236],"completely":[233],"high":[239],"level":[240],"abstractions":[241],"provided":[242,253],"Spark.":[244],"experimental":[246],"campaign":[247],"performed":[249],"shows":[250],"benefits":[252],"each":[255],"studied":[256],"solution,":[257],"perspective":[260],"moving":[262],"toward":[263],"Big":[264],"future.":[268],"lessons":[270],"learned":[272],"collected":[274],"synthesized":[276],"into":[277],"behavioral":[278],"guidelines":[279],"developers":[281],"approaching":[282],"problem":[284],"parallelizing":[286],"means":[289],"frameworks.":[292]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":3},{"year":2019,"cited_by_count":1}],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2025-10-10T00:00:00"}
