{"id":"https://openalex.org/W3025710213","doi":"https://doi.org/10.1109/iciot48696.2020.9089558","title":"Can We Build a Search Engine over Spark?","display_name":"Can We Build a Search Engine over Spark?","publication_year":2020,"publication_date":"2020-02-01","ids":{"openalex":"https://openalex.org/W3025710213","doi":"https://doi.org/10.1109/iciot48696.2020.9089558","mag":"3025710213"},"language":"en","primary_location":{"id":"doi:10.1109/iciot48696.2020.9089558","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iciot48696.2020.9089558","pdf_url":null,"source":{"id":"https://openalex.org/S4306498678","display_name":"2020 IEEE International Conference on Informatics, IoT, and Enabling Technologies (ICIoT)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE International Conference on Informatics, IoT, and Enabling Technologies (ICIoT)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5032088410","display_name":"Sara Al-Rasbi","orcid":null},"institutions":[{"id":"https://openalex.org/I60342839","display_name":"Qatar University","ror":"https://ror.org/00yhnba62","country_code":"QA","type":"education","lineage":["https://openalex.org/I60342839"]}],"countries":["QA"],"is_corresponding":false,"raw_author_name":"Sara Al-Rasbi","raw_affiliation_strings":["Computer Science and Engineering, Qatar University, Doha, Qatar"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science and Engineering, Qatar University, Doha, Qatar","institution_ids":["https://openalex.org/I60342839"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032141720","display_name":"Tamer Elsayed","orcid":"https://orcid.org/0000-0001-5786-4668"},"institutions":[{"id":"https://openalex.org/I60342839","display_name":"Qatar University","ror":"https://ror.org/00yhnba62","country_code":"QA","type":"education","lineage":["https://openalex.org/I60342839"]}],"countries":["QA"],"is_corresponding":false,"raw_author_name":"Tamer Elsayed","raw_affiliation_strings":["Computer Science and Engineering, Qatar University, Doha, Qatar"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science and Engineering, Qatar University, Doha, Qatar","institution_ids":["https://openalex.org/I60342839"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I60342839"],"apc_list":null,"apc_paid":null,"fwci":0.2342,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.3433597,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":93},"biblio":{"volume":null,"issue":null,"first_page":"345","last_page":"350"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11478","display_name":"Caching and Content Delivery","score":0.9983000159263611,"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"}},"topics":[{"id":"https://openalex.org/T11478","display_name":"Caching and Content Delivery","score":0.9983000159263611,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9954000115394592,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9919000267982483,"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/search-engine-indexing","display_name":"Search engine indexing","score":0.8637086153030396},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.8293873071670532},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8249479532241821},{"id":"https://openalex.org/keywords/spark","display_name":"SPARK (programming language)","score":0.7427277565002441},{"id":"https://openalex.org/keywords/search-engine","display_name":"Search engine","score":0.7008811831474304},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6649727821350098},{"id":"https://openalex.org/keywords/pruning","display_name":"Pruning","score":0.5808701515197754},{"id":"https://openalex.org/keywords/metasearch-engine","display_name":"Metasearch engine","score":0.555578887462616},{"id":"https://openalex.org/keywords/search-oriented-architecture","display_name":"Search-oriented architecture","score":0.5445828437805176},{"id":"https://openalex.org/keywords/scheme","display_name":"Scheme (mathematics)","score":0.46349191665649414},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.3709065318107605},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3210607171058655},{"id":"https://openalex.org/keywords/web-search-query","display_name":"Web search query","score":0.3016641139984131}],"concepts":[{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.8637086153030396},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.8293873071670532},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8249479532241821},{"id":"https://openalex.org/C2781215313","wikidata":"https://www.wikidata.org/wiki/Q3493345","display_name":"SPARK (programming language)","level":2,"score":0.7427277565002441},{"id":"https://openalex.org/C97854310","wikidata":"https://www.wikidata.org/wiki/Q19541","display_name":"Search engine","level":2,"score":0.7008811831474304},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6649727821350098},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.5808701515197754},{"id":"https://openalex.org/C173979980","wikidata":"https://www.wikidata.org/wiki/Q114106","display_name":"Metasearch engine","level":4,"score":0.555578887462616},{"id":"https://openalex.org/C157154645","wikidata":"https://www.wikidata.org/wiki/Q7441612","display_name":"Search-oriented architecture","level":5,"score":0.5445828437805176},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.46349191665649414},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.3709065318107605},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3210607171058655},{"id":"https://openalex.org/C164120249","wikidata":"https://www.wikidata.org/wiki/Q995982","display_name":"Web search query","level":3,"score":0.3016641139984131},{"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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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},{"id":"https://openalex.org/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/iciot48696.2020.9089558","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iciot48696.2020.9089558","pdf_url":null,"source":{"id":"https://openalex.org/S4306498678","display_name":"2020 IEEE International Conference on Informatics, IoT, and Enabling Technologies (ICIoT)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE International Conference on Informatics, IoT, and Enabling Technologies (ICIoT)","raw_type":"proceedings-article"},{"id":"pmh:oai:qspace.qu.edu.qa:10576/60887","is_oa":false,"landing_page_url":"http://hdl.handle.net/10576/60887","pdf_url":null,"source":{"id":"https://openalex.org/S4306400014","display_name":"Qatar University QSpace (Qatar University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I60342839","host_organization_name":"Qatar University","host_organization_lineage":["https://openalex.org/I60342839"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W109598456","https://openalex.org/W224439989","https://openalex.org/W1495984639","https://openalex.org/W1929352279","https://openalex.org/W1994915827","https://openalex.org/W2122465391","https://openalex.org/W2131975293","https://openalex.org/W2133990480","https://openalex.org/W2173213060","https://openalex.org/W2625392185","https://openalex.org/W2745862296","https://openalex.org/W2953200623","https://openalex.org/W6608859458","https://openalex.org/W6679815717","https://openalex.org/W6739498180"],"related_works":["https://openalex.org/W2533706070","https://openalex.org/W2186487484","https://openalex.org/W3210975432","https://openalex.org/W2547614144","https://openalex.org/W2105258824","https://openalex.org/W2154792254","https://openalex.org/W4256136669","https://openalex.org/W2184474188","https://openalex.org/W4285246856","https://openalex.org/W2363322605"],"abstract_inverted_index":{"Search":[0],"engines":[1],"have":[2],"to":[3,16,83],"deal":[4],"with":[5],"a":[6,53],"huge":[7],"amount":[8],"of":[9,28,92,108],"data":[10,43],"in":[11],"scalable":[12,33],"and":[13,32,69,117,124],"efficient":[14,31],"ways":[15],"produce":[17],"effective":[18],"search":[19,35],"results.":[20],"In":[21],"this":[22],"paper,":[23],"we":[24],"address":[25],"the":[26,85,90,109],"problem":[27],"building":[29],"an":[30,39],"experimental":[34],"engine":[36],"over":[37,105],"Spark,":[38],"in-memory":[40],"distributed":[41],"big":[42],"processing":[44],"framework.":[45],"The":[46],"proposed":[47],"system,":[48],"SparkIR,":[49],"can":[50],"serve":[51],"as":[52],"research":[54],"framework":[55],"for":[56,67,72,121],"conducting":[57],"information":[58],"retrieval":[59,86],"(IR)":[60],"experiments.":[61],"SparkIR":[62,93,113],"supports":[63],"document-based":[64],"partitioning":[65],"scheme":[66],"indexing":[68,123],"document-at-a-time":[70],"(DAAT)":[71],"query":[73],"evaluation.":[74],"Moreover,":[75],"it":[76],"offers":[77],"static":[78],"pruning":[79],"(using":[80],"champion":[81],"list)":[82],"improve":[84],"efficiency.":[87],"We":[88],"evaluated":[89],"performance":[91,119],"using":[94],"ClueWeb12-B13":[95],"collection":[96,110],"that":[97,112],"contains":[98],"about":[99],"50M":[100],"English":[101],"Web":[102],"pages.":[103],"Experiments":[104],"different":[106],"subsets":[107],"showed":[111],"exhibits":[114],"reasonable":[115],"efficiency":[116],"scalability":[118],"overall":[120],"both":[122],"retrieval.":[125]},"counts_by_year":[{"year":2021,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
