{"id":"https://openalex.org/W4206262478","doi":"https://doi.org/10.1109/bigdata52589.2021.9671612","title":"Building an Accessible, Usable, Scalable, and Sustainable Service for Scholarly Big Data","display_name":"Building an Accessible, Usable, Scalable, and Sustainable Service for Scholarly Big Data","publication_year":2021,"publication_date":"2021-12-15","ids":{"openalex":"https://openalex.org/W4206262478","doi":"https://doi.org/10.1109/bigdata52589.2021.9671612"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata52589.2021.9671612","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata52589.2021.9671612","pdf_url":null,"source":{"id":"https://openalex.org/S4363607718","display_name":"2021 IEEE International Conference on Big Data (Big Data)","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":"2021 IEEE International Conference on Big Data (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/A5075242841","display_name":"Jian Wu","orcid":"https://orcid.org/0000-0003-0173-4463"},"institutions":[{"id":"https://openalex.org/I81365321","display_name":"Old Dominion University","ror":"https://ror.org/04zjtrb98","country_code":"US","type":"education","lineage":["https://openalex.org/I81365321"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Jian Wu","raw_affiliation_strings":["Computer Science, Old Dominion University, Norfolk, VA, United States"],"affiliations":[{"raw_affiliation_string":"Computer Science, Old Dominion University, Norfolk, VA, United States","institution_ids":["https://openalex.org/I81365321"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045452927","display_name":"Shaurya Rohatgi","orcid":"https://orcid.org/0000-0001-7426-4576"},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shaurya Rohatgi","raw_affiliation_strings":["Information Sciences and Technology, Pennsylvania State University, PA, United States"],"affiliations":[{"raw_affiliation_string":"Information Sciences and Technology, Pennsylvania State University, PA, United States","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032974084","display_name":"Sai Raghav Reddy Keesara","orcid":null},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sai Raghav Reddy Keesara","raw_affiliation_strings":["Computer Science and Engineering, Pennsylvania State University, PA, United States"],"affiliations":[{"raw_affiliation_string":"Computer Science and Engineering, Pennsylvania State University, PA, United States","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061042503","display_name":"Jason Chhay","orcid":null},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jason Chhay","raw_affiliation_strings":["Computer Science and Engineering, Pennsylvania State University, PA, United States"],"affiliations":[{"raw_affiliation_string":"Computer Science and Engineering, Pennsylvania State University, PA, United States","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068640850","display_name":"Kevin Kuo","orcid":"https://orcid.org/0000-0001-7803-7901"},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kevin Kuo","raw_affiliation_strings":["Computer Science and Engineering, Pennsylvania State University, PA, United States"],"affiliations":[{"raw_affiliation_string":"Computer Science and Engineering, Pennsylvania State University, PA, United States","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039601473","display_name":"Arjun Manoj Menon","orcid":null},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Arjun Manoj Menon","raw_affiliation_strings":["Computer Science and Engineering, Pennsylvania State University, PA, United States"],"affiliations":[{"raw_affiliation_string":"Computer Science and Engineering, Pennsylvania State University, PA, United States","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006110681","display_name":"Sarah Parsons","orcid":"https://orcid.org/0000-0001-5823-2929"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sean Parsons","raw_affiliation_strings":["Microsoft Inc., Redmond, WA, United States"],"affiliations":[{"raw_affiliation_string":"Microsoft Inc., Redmond, WA, United States","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030643132","display_name":"Bhuvan Urgaonkar","orcid":"https://orcid.org/0000-0003-3495-6345"},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bhuvan Urgaonkar","raw_affiliation_strings":["Computer Science and Engineering, Pennsylvania State University, PA, United States"],"affiliations":[{"raw_affiliation_string":"Computer Science and Engineering, Pennsylvania State University, PA, United States","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001294898","display_name":"C. Lee Giles","orcid":"https://orcid.org/0000-0002-1931-585X"},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"C. Lee Giles","raw_affiliation_strings":["Computer Science and Engineering, Pennsylvania State University, PA, United States","Information Sciences and Technology, Pennsylvania State University, PA, United States"],"affiliations":[{"raw_affiliation_string":"Computer Science and Engineering, Pennsylvania State University, PA, United States","institution_ids":["https://openalex.org/I130769515"]},{"raw_affiliation_string":"Information Sciences and Technology, Pennsylvania State University, PA, United States","institution_ids":["https://openalex.org/I130769515"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5075242841"],"corresponding_institution_ids":["https://openalex.org/I81365321"],"apc_list":null,"apc_paid":null,"fwci":0.8548,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.7358631,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"94","issue":null,"first_page":"141","last_page":"152"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9948999881744385,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9948999881744385,"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.9922999739646912,"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/T11986","display_name":"Scientific Computing and Data Management","score":0.9876999855041504,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7682881355285645},{"id":"https://openalex.org/keywords/usable","display_name":"USable","score":0.6576614379882812},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6297592520713806},{"id":"https://openalex.org/keywords/digital-library","display_name":"Digital library","score":0.5293985605239868},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.5111060738563538},{"id":"https://openalex.org/keywords/upgrade","display_name":"Upgrade","score":0.5109526515007019},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.5061692595481873},{"id":"https://openalex.org/keywords/service","display_name":"Service (business)","score":0.4833095073699951},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.34564951062202454},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.3427397310733795},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.15803992748260498}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7682881355285645},{"id":"https://openalex.org/C2780615836","wikidata":"https://www.wikidata.org/wiki/Q2471869","display_name":"USable","level":2,"score":0.6576614379882812},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6297592520713806},{"id":"https://openalex.org/C513874922","wikidata":"https://www.wikidata.org/wiki/Q212805","display_name":"Digital library","level":3,"score":0.5293985605239868},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.5111060738563538},{"id":"https://openalex.org/C2780615140","wikidata":"https://www.wikidata.org/wiki/Q920419","display_name":"Upgrade","level":2,"score":0.5109526515007019},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.5061692595481873},{"id":"https://openalex.org/C2780378061","wikidata":"https://www.wikidata.org/wiki/Q25351891","display_name":"Service (business)","level":2,"score":0.4833095073699951},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.34564951062202454},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.3427397310733795},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.15803992748260498},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"score":0.0},{"id":"https://openalex.org/C164913051","wikidata":"https://www.wikidata.org/wiki/Q482","display_name":"Poetry","level":2,"score":0.0},{"id":"https://openalex.org/C136264566","wikidata":"https://www.wikidata.org/wiki/Q159810","display_name":"Economy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bigdata52589.2021.9671612","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata52589.2021.9671612","pdf_url":null,"source":{"id":"https://openalex.org/S4363607718","display_name":"2021 IEEE International Conference on Big Data (Big Data)","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":"2021 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","score":0.6499999761581421,"display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":47,"referenced_works":["https://openalex.org/W926830766","https://openalex.org/W1603719052","https://openalex.org/W1932742904","https://openalex.org/W1987391925","https://openalex.org/W1991869139","https://openalex.org/W2003754790","https://openalex.org/W2022322548","https://openalex.org/W2038276547","https://openalex.org/W2039884530","https://openalex.org/W2042641525","https://openalex.org/W2052569240","https://openalex.org/W2061858109","https://openalex.org/W2063002113","https://openalex.org/W2080099271","https://openalex.org/W2091533596","https://openalex.org/W2092950680","https://openalex.org/W2120109270","https://openalex.org/W2121259645","https://openalex.org/W2123845384","https://openalex.org/W2145349611","https://openalex.org/W2168065722","https://openalex.org/W2168190036","https://openalex.org/W2294064099","https://openalex.org/W2416987009","https://openalex.org/W2562691023","https://openalex.org/W2570427954","https://openalex.org/W2722421329","https://openalex.org/W2740811004","https://openalex.org/W2788643179","https://openalex.org/W2801930304","https://openalex.org/W2912067075","https://openalex.org/W2913261131","https://openalex.org/W2970296612","https://openalex.org/W2978352415","https://openalex.org/W2993670251","https://openalex.org/W3015453090","https://openalex.org/W3093272903","https://openalex.org/W3112131000","https://openalex.org/W3126284168","https://openalex.org/W3137230591","https://openalex.org/W4238044281","https://openalex.org/W4243343826","https://openalex.org/W4253723135","https://openalex.org/W4297751839","https://openalex.org/W6696715908","https://openalex.org/W6697460127","https://openalex.org/W6759139182"],"related_works":["https://openalex.org/W2368672678","https://openalex.org/W2370626080","https://openalex.org/W2965111880","https://openalex.org/W2368576029","https://openalex.org/W2377210208","https://openalex.org/W116478885","https://openalex.org/W2391279445","https://openalex.org/W2390420166","https://openalex.org/W2354998446","https://openalex.org/W2188310145"],"abstract_inverted_index":{"Since":[0],"the":[1,25,45,66,74,92,97,118,154,173,198],"emergence":[2],"of":[3,24,29,82,96,117,138,145,156],"scholarly":[4,61],"big":[5,62],"data,":[6],"there":[7],"have":[8,37],"been":[9,39,122],"several":[10],"efforts":[11],"for":[12,60],"web-based":[13],"services":[14],"such":[15],"as":[16],"digital":[17,86],"library":[18,87],"search":[19,88,185],"engines":[20],"(DLSEs).":[21],"However,":[22],"much":[23],"design":[26,104,120,199],"and":[27,34,42,68,77,80,94,100,111,124,131,148,158,181,201,206,211,218],"specifications":[28],"an":[30],"accessible,":[31],"usable,":[32],"scalable,":[33],"sustainable":[35],"DLSE":[36],"not":[38],"well":[40],"represented":[41],"discussed":[43],"in":[44,192],"literature.":[46],"We":[47,90,196],"argue":[48],"that":[49],"these":[50],"four":[51],"characteristics":[52],"are":[53],"essential":[54],"to":[55,171],"providing":[56],"a":[57,84,102,106,135,142,178],"high-quality":[58],"service":[59],"data":[63,146],"from":[64],"both":[65],"user":[67,174],"developer\u2019s":[69],"perspectives.":[70],"This":[71],"paper":[72],"reviews":[73],"design,":[75,99,210],"implementation,":[76],"operation":[78],"experiences,":[79],"lessons":[81],"CiteSeerX,":[83],"real-world":[85],"engine.":[89],"analyze":[91],"strengths":[93],"weaknesses":[95],"current":[98],"proposed":[101],"new":[103,119,127],"with":[105,134,215],"revised":[107],"architecture,":[108],"enhanced":[109],"hardware,":[110],"software":[112],"infrastructure.":[113],"The":[114,126,166,187],"Alpha":[115],"version":[116],"has":[121],"implemented":[123],"tested.":[125],"system":[128,188],"replaces":[129],"MySQL":[130],"Apache":[132],"Solr":[133],"single":[136],"instance":[137],"Elasticsearch,":[139],"which":[140,160],"plays":[141],"dual":[143],"role":[144],"storage":[147],"search.":[149],"Another":[150],"major":[151],"improvement":[152],"is":[153,169,189],"integration":[155],"extraction":[157],"ingestion,":[159],"significantly":[161],"boosts":[162],"document":[163],"ingestion":[164],"speed.":[165],"web":[167],"application":[168],"re-engineered":[170],"enhance":[172],"experience":[175,202],"by":[176],"applying":[177],"learning-to-rank":[179],"model":[180],"offering":[182],"more":[183],"refined":[184],"tools.":[186],"also":[190],"improved":[191],"many":[193],"other":[194],"aspects.":[195],"believe":[197],"considerations":[200],"can":[203],"benefit":[204],"researchers":[205],"engineers":[207],"who":[208],"plan,":[209],"upgrade":[212],"future":[213],"systems":[214],"comparable":[216],"scales":[217],"functionalities.":[219]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2}],"updated_date":"2026-04-02T15:55:50.835912","created_date":"2025-10-10T00:00:00"}