{"id":"https://openalex.org/W4238044281","doi":"https://doi.org/10.1109/jcdl.2014.6970157","title":"Towards building a scholarly big data platform: Challenges, lessons and opportunities","display_name":"Towards building a scholarly big data platform: Challenges, lessons and opportunities","publication_year":2014,"publication_date":"2014-09-01","ids":{"openalex":"https://openalex.org/W4238044281","doi":"https://doi.org/10.1109/jcdl.2014.6970157"},"language":"en","primary_location":{"id":"doi:10.1109/jcdl.2014.6970157","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jcdl.2014.6970157","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Joint Conference on Digital Libraries","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/A5101973484","display_name":"Zhaohui Wu","orcid":"https://orcid.org/0000-0002-4319-3645"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Zhaohui Wu","raw_affiliation_strings":["Computer Science and Engineering"],"affiliations":[{"raw_affiliation_string":"Computer Science and Engineering","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075242841","display_name":"Jian Wu","orcid":"https://orcid.org/0000-0003-0173-4463"},"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":"Jian Wu","raw_affiliation_strings":["Information Sciences and Technology, Pennsylvania State University, University Park, PA, USA"],"affiliations":[{"raw_affiliation_string":"Information Sciences and Technology, Pennsylvania State University, University Park, PA, USA","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054253075","display_name":"Madian Khabsa","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":"Madian Khabsa","raw_affiliation_strings":["Pennsylvania State University, University Park, PA, US"],"affiliations":[{"raw_affiliation_string":"Pennsylvania State University, University Park, PA, US","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108439761","display_name":"Kyle Williams","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":"Kyle Williams","raw_affiliation_strings":["Information Sciences and Technology, Pennsylvania State University, University Park, PA, USA"],"affiliations":[{"raw_affiliation_string":"Information Sciences and Technology, Pennsylvania State University, University Park, PA, USA","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078925594","display_name":"Hung\u2010Hsuan Chen","orcid":"https://orcid.org/0000-0001-5137-4449"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hung-Hsuan Chen","raw_affiliation_strings":["Computer Science and Engineering"],"affiliations":[{"raw_affiliation_string":"Computer Science and Engineering","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069048388","display_name":"Wenyi Huang","orcid":"https://orcid.org/0000-0002-3526-6314"},"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":"Wenyi Huang","raw_affiliation_strings":["Information Sciences and Technology, Pennsylvania State University, University Park, PA, USA"],"affiliations":[{"raw_affiliation_string":"Information Sciences and Technology, Pennsylvania State University, University Park, PA, USA","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023506216","display_name":"Suppawong Tuarob","orcid":"https://orcid.org/0000-0002-5201-5699"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Suppawong Tuarob","raw_affiliation_strings":["Computer Science and Engineering"],"affiliations":[{"raw_affiliation_string":"Computer Science and Engineering","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112500027","display_name":"Sagnik Ray Choudhury","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":"Sagnik Ray Choudhury","raw_affiliation_strings":["Information Sciences and Technology, Pennsylvania State University, University Park, PA, USA"],"affiliations":[{"raw_affiliation_string":"Information Sciences and Technology, Pennsylvania State University, University Park, PA, USA","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084332360","display_name":"Alexander G. Ororbia","orcid":"https://orcid.org/0000-0002-2590-1310"},"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":"Alexander Ororbia","raw_affiliation_strings":["Information Sciences and Technology, Pennsylvania State University, University Park, PA, USA"],"affiliations":[{"raw_affiliation_string":"Information Sciences and Technology, Pennsylvania State University, University Park, PA, USA","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009542542","display_name":"Prasenjit Mitra","orcid":"https://orcid.org/0000-0002-7530-9497"},"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":"Prasenjit Mitra","raw_affiliation_strings":["Computer Science and Engineering","Information Sciences and Technology, Pennsylvania State University, University Park, PA, USA"],"affiliations":[{"raw_affiliation_string":"Computer Science and Engineering","institution_ids":[]},{"raw_affiliation_string":"Information Sciences and Technology, Pennsylvania State University, University Park, PA, USA","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","Information Sciences and Technology, Pennsylvania State University, University Park, PA, USA"],"affiliations":[{"raw_affiliation_string":"Computer Science and Engineering","institution_ids":[]},{"raw_affiliation_string":"Information Sciences and Technology, Pennsylvania State University, University Park, PA, USA","institution_ids":["https://openalex.org/I130769515"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":11,"corresponding_author_ids":["https://openalex.org/A5101973484"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":10.5784,"has_fulltext":false,"cited_by_count":38,"citation_normalized_percentile":{"value":0.98088607,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"117","last_page":"126"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.9983999729156494,"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"}},"topics":[{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.9983999729156494,"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"}},{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9973999857902527,"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/T11719","display_name":"Data Quality and Management","score":0.9905999898910522,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7635629177093506},{"id":"https://openalex.org/keywords/cloud-computing","display_name":"Cloud computing","score":0.6832993626594543},{"id":"https://openalex.org/keywords/workflow","display_name":"Workflow","score":0.6792555451393127},{"id":"https://openalex.org/keywords/analytics","display_name":"Analytics","score":0.6261279582977295},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.5857858061790466},{"id":"https://openalex.org/keywords/web-crawler","display_name":"Web crawler","score":0.5501610636711121},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.5016734600067139},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.5005383491516113},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.4661138653755188},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.42239829897880554},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.12361875176429749},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.11395949125289917}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7635629177093506},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.6832993626594543},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.6792555451393127},{"id":"https://openalex.org/C79158427","wikidata":"https://www.wikidata.org/wiki/Q485396","display_name":"Analytics","level":2,"score":0.6261279582977295},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.5857858061790466},{"id":"https://openalex.org/C13743948","wikidata":"https://www.wikidata.org/wiki/Q45842","display_name":"Web crawler","level":2,"score":0.5501610636711121},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.5016734600067139},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.5005383491516113},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.4661138653755188},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.42239829897880554},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.12361875176429749},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.11395949125289917},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/jcdl.2014.6970157","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jcdl.2014.6970157","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Joint Conference on Digital Libraries","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9","score":0.6000000238418579}],"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":44,"referenced_works":["https://openalex.org/W1511676561","https://openalex.org/W1559499673","https://openalex.org/W1590650811","https://openalex.org/W1846765585","https://openalex.org/W1968797728","https://openalex.org/W1983531058","https://openalex.org/W1984953306","https://openalex.org/W1991869139","https://openalex.org/W1992549066","https://openalex.org/W1993594224","https://openalex.org/W1999762660","https://openalex.org/W2022685363","https://openalex.org/W2026784708","https://openalex.org/W2027346915","https://openalex.org/W2028657008","https://openalex.org/W2031837460","https://openalex.org/W2042014073","https://openalex.org/W2046819726","https://openalex.org/W2053604034","https://openalex.org/W2060186854","https://openalex.org/W2073853190","https://openalex.org/W2080099271","https://openalex.org/W2083089853","https://openalex.org/W2091344457","https://openalex.org/W2091533596","https://openalex.org/W2095377587","https://openalex.org/W2121259645","https://openalex.org/W2121577889","https://openalex.org/W2122778642","https://openalex.org/W2129647599","https://openalex.org/W2131257962","https://openalex.org/W2132083030","https://openalex.org/W2156897567","https://openalex.org/W2168190036","https://openalex.org/W2251270842","https://openalex.org/W2253675773","https://openalex.org/W2736801446","https://openalex.org/W4234307579","https://openalex.org/W4253723135","https://openalex.org/W6633305578","https://openalex.org/W6639062144","https://openalex.org/W6642417952","https://openalex.org/W6691667650","https://openalex.org/W6691690466"],"related_works":["https://openalex.org/W3005260231","https://openalex.org/W2904469652","https://openalex.org/W4362647146","https://openalex.org/W2383572231","https://openalex.org/W2042034567","https://openalex.org/W3179424333","https://openalex.org/W2782340266","https://openalex.org/W4230722125","https://openalex.org/W2149158941","https://openalex.org/W2019038080"],"abstract_inverted_index":{"We":[0,90],"introduce":[1,92],"a":[2,28,35,41,47,93],"big":[3],"data":[4,33,66,75],"platform":[5,24,81,103],"that":[6,39],"provides":[7],"various":[8],"services":[9],"for":[10],"harvesting":[11],"scholarly":[12,17,36,65,96],"information":[13,68,72],"and":[14,54,60,70,73,82,87,107],"enabling":[15],"efficient":[16],"applications.":[18],"The":[19],"core":[20],"architecture":[21],"of":[22,95,101],"the":[23,80],"is":[25,55],"built":[26,98],"on":[27,99],"secured":[29],"private":[30],"cloud,":[31],"crawls":[32],"using":[34],"focused":[37],"crawler":[38],"leverages":[40],"dynamic":[42],"scheduler,":[43],"processes":[44],"by":[45,84],"utilizing":[46],"map":[48],"reduce":[49],"based":[50],"crawl-extraction-ingestion":[51],"(CEI)":[52],"workflow,":[53],"stored":[56],"in":[57],"distributed":[58],"repositories":[59],"databases.":[61],"Services":[62],"such":[63],"as":[64],"harvesting,":[67],"extraction,":[69],"user":[71],"log":[74],"analytics":[76],"are":[77],"integrated":[78],"into":[79],"provided":[83],"an":[85],"OAI":[86],"RESTful":[88],"API.":[89],"also":[91],"set":[94],"applications":[97],"top":[100],"this":[102],"including":[104],"citation":[105],"recommendation":[106],"collaborator":[108],"discovery.":[109]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":9},{"year":2017,"cited_by_count":5},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
