{"id":"https://openalex.org/W3138644485","doi":"https://doi.org/10.1109/bigdata50022.2020.9378448","title":"Automated Indexing of Structured Scientific Metadata Using Apache Solr","display_name":"Automated Indexing of Structured Scientific Metadata Using Apache Solr","publication_year":2020,"publication_date":"2020-12-10","ids":{"openalex":"https://openalex.org/W3138644485","doi":"https://doi.org/10.1109/bigdata50022.2020.9378448","mag":"3138644485"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata50022.2020.9378448","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata50022.2020.9378448","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.osti.gov/servlets/purl/1777737","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5031039575","display_name":"Kavya Guntupally","orcid":"https://orcid.org/0000-0001-8694-8019"},"institutions":[{"id":"https://openalex.org/I1289243028","display_name":"Oak Ridge National Laboratory","ror":"https://ror.org/01qz5mb56","country_code":"US","type":"facility","lineage":["https://openalex.org/I1289243028","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I4210159294"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Kavya Guntupally","raw_affiliation_strings":["ARM Data Center, Environmental Sciences Division, Oak Ridge National Laboratory, Oak Ridge, TN, USA"],"affiliations":[{"raw_affiliation_string":"ARM Data Center, Environmental Sciences Division, Oak Ridge National Laboratory, Oak Ridge, TN, USA","institution_ids":["https://openalex.org/I1289243028"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030159650","display_name":"Kyle Dumas","orcid":null},"institutions":[{"id":"https://openalex.org/I1289243028","display_name":"Oak Ridge National Laboratory","ror":"https://ror.org/01qz5mb56","country_code":"US","type":"facility","lineage":["https://openalex.org/I1289243028","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I4210159294"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kyle Dumas","raw_affiliation_strings":["ARM Data Center, Environmental Sciences Division, Oak Ridge National Laboratory, Oak Ridge, TN, USA"],"affiliations":[{"raw_affiliation_string":"ARM Data Center, Environmental Sciences Division, Oak Ridge National Laboratory, Oak Ridge, TN, USA","institution_ids":["https://openalex.org/I1289243028"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000853114","display_name":"Wade Darnell","orcid":null},"institutions":[{"id":"https://openalex.org/I1289243028","display_name":"Oak Ridge National Laboratory","ror":"https://ror.org/01qz5mb56","country_code":"US","type":"facility","lineage":["https://openalex.org/I1289243028","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I4210159294"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wade Darnell","raw_affiliation_strings":["ARM Data Center, Environmental Sciences Division, Oak Ridge National Laboratory, Oak Ridge, TN, USA"],"affiliations":[{"raw_affiliation_string":"ARM Data Center, Environmental Sciences Division, Oak Ridge National Laboratory, Oak Ridge, TN, USA","institution_ids":["https://openalex.org/I1289243028"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003620086","display_name":"Michael Crow","orcid":"https://orcid.org/0000-0002-7260-807X"},"institutions":[{"id":"https://openalex.org/I1289243028","display_name":"Oak Ridge National Laboratory","ror":"https://ror.org/01qz5mb56","country_code":"US","type":"facility","lineage":["https://openalex.org/I1289243028","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I4210159294"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael Crow","raw_affiliation_strings":["ARM Data Center, Environmental Sciences Division, Oak Ridge National Laboratory, Oak Ridge, TN, USA"],"affiliations":[{"raw_affiliation_string":"ARM Data Center, Environmental Sciences Division, Oak Ridge National Laboratory, Oak Ridge, TN, USA","institution_ids":["https://openalex.org/I1289243028"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023450342","display_name":"Ranjeet Devarakonda","orcid":"https://orcid.org/0000-0003-2661-1937"},"institutions":[{"id":"https://openalex.org/I1289243028","display_name":"Oak Ridge National Laboratory","ror":"https://ror.org/01qz5mb56","country_code":"US","type":"facility","lineage":["https://openalex.org/I1289243028","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I4210159294"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ranjeet Devarakonda","raw_affiliation_strings":["ARM Data Center, Environmental Sciences Division, Oak Ridge National Laboratory, Oak Ridge, TN, USA"],"affiliations":[{"raw_affiliation_string":"ARM Data Center, Environmental Sciences Division, Oak Ridge National Laboratory, Oak Ridge, TN, USA","institution_ids":["https://openalex.org/I1289243028"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103589907","display_name":"Prakash Giri","orcid":null},"institutions":[{"id":"https://openalex.org/I1289243028","display_name":"Oak Ridge National Laboratory","ror":"https://ror.org/01qz5mb56","country_code":"US","type":"facility","lineage":["https://openalex.org/I1289243028","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I4210159294"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Prakash Giri","raw_affiliation_strings":["ARM Data Center, Environmental Sciences Division, Oak Ridge National Laboratory, Oak Ridge, TN, USA"],"affiliations":[{"raw_affiliation_string":"ARM Data Center, Environmental Sciences Division, Oak Ridge National Laboratory, Oak Ridge, TN, USA","institution_ids":["https://openalex.org/I1289243028"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5031039575"],"corresponding_institution_ids":["https://openalex.org/I1289243028"],"apc_list":null,"apc_paid":null,"fwci":0.6447,"has_fulltext":true,"cited_by_count":6,"citation_normalized_percentile":{"value":0.73785004,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"5685","last_page":"5687"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10317","display_name":"Advanced Database Systems and Queries","score":0.9959999918937683,"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.9959999918937683,"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/T11106","display_name":"Data Management and Algorithms","score":0.9904000163078308,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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":0.9891999959945679,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8202579021453857},{"id":"https://openalex.org/keywords/metadata","display_name":"Metadata","score":0.8105995655059814},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.7482147216796875},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.6198551654815674},{"id":"https://openalex.org/keywords/relational-database","display_name":"Relational database","score":0.5705748200416565},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5554258227348328},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.5438010096549988},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.528740644454956},{"id":"https://openalex.org/keywords/relational-database-management-system","display_name":"Relational database management system","score":0.502657413482666},{"id":"https://openalex.org/keywords/search-engine","display_name":"Search engine","score":0.4949728846549988},{"id":"https://openalex.org/keywords/raw-data","display_name":"Raw data","score":0.49029305577278137},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.4103754758834839},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.08922019600868225}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8202579021453857},{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.8105995655059814},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.7482147216796875},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.6198551654815674},{"id":"https://openalex.org/C5655090","wikidata":"https://www.wikidata.org/wiki/Q192588","display_name":"Relational database","level":2,"score":0.5705748200416565},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5554258227348328},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.5438010096549988},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.528740644454956},{"id":"https://openalex.org/C24394798","wikidata":"https://www.wikidata.org/wiki/Q192588","display_name":"Relational database management system","level":3,"score":0.502657413482666},{"id":"https://openalex.org/C97854310","wikidata":"https://www.wikidata.org/wiki/Q19541","display_name":"Search engine","level":2,"score":0.4949728846549988},{"id":"https://openalex.org/C132964779","wikidata":"https://www.wikidata.org/wiki/Q2110223","display_name":"Raw data","level":2,"score":0.49029305577278137},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.4103754758834839},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.08922019600868225},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/bigdata50022.2020.9378448","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata50022.2020.9378448","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-article"},{"id":"pmh:oai:osti.gov:1777737","is_oa":true,"landing_page_url":"https://www.osti.gov/biblio/1777737","pdf_url":"https://www.osti.gov/servlets/purl/1777737","source":{"id":"https://openalex.org/S4306402487","display_name":"OSTI OAI (U.S. Department of Energy Office of Scientific and Technical Information)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I139351228","host_organization_name":"Office of Scientific and Technical Information","host_organization_lineage":["https://openalex.org/I139351228"],"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":null}],"best_oa_location":{"id":"pmh:oai:osti.gov:1777737","is_oa":true,"landing_page_url":"https://www.osti.gov/biblio/1777737","pdf_url":"https://www.osti.gov/servlets/purl/1777737","source":{"id":"https://openalex.org/S4306402487","display_name":"OSTI OAI (U.S. Department of Energy Office of Scientific and Technical Information)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I139351228","host_organization_name":"Office of Scientific and Technical Information","host_organization_lineage":["https://openalex.org/I139351228"],"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":null},"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9","score":0.46000000834465027}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306084","display_name":"U.S. Department of Energy","ror":"https://ror.org/01bj3aw27"},{"id":"https://openalex.org/F4320306250","display_name":"Battelle","ror":"https://ror.org/01h5tnr73"},{"id":"https://openalex.org/F4320316892","display_name":"UT-Battelle","ror":"https://ror.org/04nza6677"},{"id":"https://openalex.org/F4320338287","display_name":"Oak Ridge National Laboratory","ror":"https://ror.org/01qz5mb56"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3138644485.pdf"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4282568653","https://openalex.org/W2119380317","https://openalex.org/W2082868123","https://openalex.org/W2070155952","https://openalex.org/W2505630977","https://openalex.org/W2383709723","https://openalex.org/W2748529818","https://openalex.org/W2626533837","https://openalex.org/W2163438384","https://openalex.org/W2375584934"],"abstract_inverted_index":{"Scientific":[0],"datasets":[1],"are":[2,40],"continuously":[3],"growing":[4],"with":[5,89],"the":[6,19,101],"amount":[7,15],"of":[8,16],"raw":[9],"data":[10,17,38,53,56],"being":[11],"collected":[12],"worldwide.":[13],"This":[14,32],"poses":[18],"biggest":[20],"challenge":[21],"to":[22,28,50,81,100],"web":[23],"search":[24,44,86,103],"engines":[25],"on":[26,75],"how":[27,35,76],"retrieve":[29,51],"them":[30],"efficiently.":[31],"paper":[33],"discusses":[34],"major":[36],"scientific":[37,102],"centers":[39],"using":[41,64],"popular":[42],"open-source":[43],"platforms":[45],"such":[46,58],"as":[47,59],"Solr":[48,80],"[1]":[49],"structured":[52],"stored":[54],"in":[55],"sources":[57],"relational":[60],"database":[61],"management":[62],"systems":[63],"its":[65,90],"import":[66],"handler":[67],"mechanisms":[68],"[2].":[69],"Additionally,":[70],"we":[71,77],"will":[72],"also":[73],"focus":[74],"can":[78],"configure":[79],"serve":[82],"advanced":[83],"full-text,":[84],"faceted":[85],"capabilities,":[87],"along":[88],"key":[91],"features,":[92],"which":[93],"simplify":[94],"representing":[95],"and":[96],"delivering":[97],"better":[98],"performance":[99],"interfaces.":[104]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}
