{"id":"https://openalex.org/W2007855128","doi":"https://doi.org/10.1109/icsc.2013.49","title":"Analysis of Big Data Technologies and Method - Query Large Web Public RDF Datasets on Amazon Cloud Using Hadoop and Open Source Parsers","display_name":"Analysis of Big Data Technologies and Method - Query Large Web Public RDF Datasets on Amazon Cloud Using Hadoop and Open Source Parsers","publication_year":2013,"publication_date":"2013-09-01","ids":{"openalex":"https://openalex.org/W2007855128","doi":"https://doi.org/10.1109/icsc.2013.49","mag":"2007855128"},"language":"en","primary_location":{"id":"doi:10.1109/icsc.2013.49","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icsc.2013.49","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE Seventh International Conference on Semantic Computing","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/A5091535909","display_name":"Ted Garcia","orcid":null},"institutions":[{"id":"https://openalex.org/I157638225","display_name":"California State University, Northridge","ror":"https://ror.org/005f5hv41","country_code":"US","type":"education","lineage":["https://openalex.org/I157638225"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Ted Garcia","raw_affiliation_strings":["Department of Computer Science, California State University, Northridge Northridge, California","[Department of Computer Science, California State University, Northridge, Northridge, CA, USA]"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, California State University, Northridge Northridge, California","institution_ids":["https://openalex.org/I157638225"]},{"raw_affiliation_string":"[Department of Computer Science, California State University, Northridge, Northridge, CA, USA]","institution_ids":["https://openalex.org/I157638225"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5067116801","display_name":"Taehyung Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I157638225","display_name":"California State University, Northridge","ror":"https://ror.org/005f5hv41","country_code":"US","type":"education","lineage":["https://openalex.org/I157638225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Taehyung Wang","raw_affiliation_strings":["Department of Computer Science, California State University, Northridge Northridge, California","[Department of Computer Science, California State University, Northridge, Northridge, CA, USA]"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, California State University, Northridge Northridge, California","institution_ids":["https://openalex.org/I157638225"]},{"raw_affiliation_string":"[Department of Computer Science, California State University, Northridge, Northridge, CA, USA]","institution_ids":["https://openalex.org/I157638225"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5091535909"],"corresponding_institution_ids":["https://openalex.org/I157638225"],"apc_list":null,"apc_paid":null,"fwci":1.2328,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.81860726,"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":"244","last_page":"251"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9926999807357788,"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":0.9926999807357788,"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/T10215","display_name":"Semantic Web and Ontologies","score":0.9896000027656555,"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.9704999923706055,"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":0.8772016763687134},{"id":"https://openalex.org/keywords/cloud-computing","display_name":"Cloud computing","score":0.6651920080184937},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.6386028528213501},{"id":"https://openalex.org/keywords/sparql","display_name":"SPARQL","score":0.5964283347129822},{"id":"https://openalex.org/keywords/rdf","display_name":"RDF","score":0.5619598031044006},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.49875879287719727},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.46838289499282837},{"id":"https://openalex.org/keywords/parsing","display_name":"Parsing","score":0.4443950057029724},{"id":"https://openalex.org/keywords/the-internet","display_name":"The Internet","score":0.41107186675071716},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3612019121646881},{"id":"https://openalex.org/keywords/semantic-web","display_name":"Semantic Web","score":0.34062933921813965},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.33815228939056396},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.281452476978302},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.14253631234169006}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8772016763687134},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.6651920080184937},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.6386028528213501},{"id":"https://openalex.org/C41009113","wikidata":"https://www.wikidata.org/wiki/Q54871","display_name":"SPARQL","level":4,"score":0.5964283347129822},{"id":"https://openalex.org/C147497476","wikidata":"https://www.wikidata.org/wiki/Q54872","display_name":"RDF","level":3,"score":0.5619598031044006},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.49875879287719727},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.46838289499282837},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.4443950057029724},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.41107186675071716},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3612019121646881},{"id":"https://openalex.org/C2129575","wikidata":"https://www.wikidata.org/wiki/Q54837","display_name":"Semantic Web","level":2,"score":0.34062933921813965},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.33815228939056396},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.281452476978302},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.14253631234169006},{"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:10.1109/icsc.2013.49","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icsc.2013.49","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE Seventh International Conference on Semantic Computing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","score":0.5699999928474426,"id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2615202182","https://openalex.org/W4206665951","https://openalex.org/W2529794967","https://openalex.org/W2904139343","https://openalex.org/W2604011835","https://openalex.org/W3139465322","https://openalex.org/W2484233589","https://openalex.org/W2528203718","https://openalex.org/W4241483715","https://openalex.org/W4243630814"],"abstract_inverted_index":{"Extremely":[0],"large":[1,53,84],"datasets":[2,61,85],"found":[3],"in":[4,44,135,164],"Big":[5,40,132],"Data":[6,41,102,107,133],"projects":[7],"are":[8],"difficult":[9],"to":[10,46,58,80,129,155,162],"work":[11,59,74,121],"with":[12,83,137],"using":[13],"conventional":[14],"databases,":[15],"statistical":[16],"software,":[17,23],"and":[18,78,89,126,148],"visualization":[19],"tools.":[20],"Massively":[21],"parallel":[22],"such":[24],"as":[25],"Hadoop,":[26,144],"running":[27],"on":[28,94],"tens,":[29],"hundreds,":[30],"or":[31,66],"even":[32],"thousands":[33],"of":[34,113],"servers":[35],"is":[36,56],"more":[37],"suitable":[38],"for":[39,168],"challenges.":[42],"Additionally,":[43],"order":[45,161],"achieve":[47],"the":[48,95,99,118,131],"highest":[49],"performance":[50],"when":[51],"querying":[52,90],"datasets,":[54],"it":[55],"necessary":[57],"these":[60,138,158],"at":[62,86],"rest":[63],"without":[64],"preprocessing":[65],"moving":[67],"them":[68],"into":[69],"a":[70],"repository.":[71],"Therefore,":[72],"this":[73],"will":[75,91,122,152,171],"analyze":[76,123],"tools":[77,125],"techniques":[79],"overcome":[81],"working":[82,136],"rest.":[87],"Parsing":[88],"be":[92,153,172],"done":[93],"raw":[96],"dataset":[97],"-":[98],"untouched":[100],"Web":[101,106],"Commons":[103,108],"RDF":[104,142],"files.":[105,159],"comprises":[109],"five":[110],"billion":[111],"pages":[112,115],"web":[114],"crawled":[116],"from":[117],"Internet.":[119],"This":[120],"available":[124],"appropriate":[127],"methods":[128],"assist":[130,163],"developer":[134],"extremely":[139],"large,":[140],"semantic":[141],"datasets.":[143],"open":[145],"source":[146],"parsers,":[147],"Amazon":[149],"Cloud":[150],"services":[151],"used":[154],"data":[156],"mine":[157],"In":[160],"further":[165],"discovery,":[166],"recommendations":[167],"future":[169],"research":[170],"included.":[173]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2014,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
