{"id":"https://openalex.org/W2781262772","doi":"https://doi.org/10.18329/09757597/2017/10101","title":"Large-scale Metadata Harvesting\u2014Tools, Techniques and Challenges: A Case Study of National Digital Library (NDL)","display_name":"Large-scale Metadata Harvesting\u2014Tools, Techniques and Challenges: A Case Study of National Digital Library (NDL)","publication_year":2017,"publication_date":"2017-01-01","ids":{"openalex":"https://openalex.org/W2781262772","doi":"https://doi.org/10.18329/09757597/2017/10101","mag":"2781262772"},"language":"en","primary_location":{"id":"doi:10.18329/09757597/2017/10101","is_oa":false,"landing_page_url":"https://doi.org/10.18329/09757597/2017/10101","pdf_url":null,"source":{"id":"https://openalex.org/S2764388036","display_name":"World Digital Libraries - An international journal","issn_l":"0974-567X","issn":["0974-567X","0975-7597"],"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":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"World Digital Libraries: An International Journal","raw_type":"journal-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":null,"display_name":"IIT Kharagpur","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"IIT Kharagpur","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007576073","display_name":"Samrat Roy","orcid":"https://orcid.org/0000-0001-7291-3747"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Samrat Guha Roy","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086138828","display_name":"B. Sutradhar","orcid":"https://orcid.org/0000-0001-8818-9036"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"B Sutradhar","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011440310","display_name":"Partha Pratim Das","orcid":"https://orcid.org/0000-0003-1435-6051"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Partha Pratim Das","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"IIT Kharagpur","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"IIT Kharagpur","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"IIT Kharagpur","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"IIT Kharagpur","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.25300114,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"10","issue":"1","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11937","display_name":"Research Data Management Practices","score":0.9574999809265137,"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/T11937","display_name":"Research Data Management Practices","score":0.9574999809265137,"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/T11657","display_name":"Digital and Traditional Archives Management","score":0.9097999930381775,"subfield":{"id":"https://openalex.org/subfields/1206","display_name":"Conservation"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/metadata","display_name":"Metadata","score":0.8793002367019653},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.6583606600761414},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6269433498382568},{"id":"https://openalex.org/keywords/digital-library","display_name":"Digital library","score":0.5704051852226257},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.3748937249183655},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.37423086166381836},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.35460132360458374},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3469724953174591},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.16485151648521423},{"id":"https://openalex.org/keywords/cartography","display_name":"Cartography","score":0.08586588501930237},{"id":"https://openalex.org/keywords/art","display_name":"Art","score":0.06243795156478882}],"concepts":[{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.8793002367019653},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.6583606600761414},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6269433498382568},{"id":"https://openalex.org/C513874922","wikidata":"https://www.wikidata.org/wiki/Q212805","display_name":"Digital library","level":3,"score":0.5704051852226257},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.3748937249183655},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.37423086166381836},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.35460132360458374},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3469724953174591},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.16485151648521423},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.08586588501930237},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.06243795156478882},{"id":"https://openalex.org/C164913051","wikidata":"https://www.wikidata.org/wiki/Q482","display_name":"Poetry","level":2,"score":0.0},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18329/09757597/2017/10101","is_oa":false,"landing_page_url":"https://doi.org/10.18329/09757597/2017/10101","pdf_url":null,"source":{"id":"https://openalex.org/S2764388036","display_name":"World Digital Libraries - An international journal","issn_l":"0974-567X","issn":["0974-567X","0975-7597"],"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":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"World Digital Libraries: An International Journal","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.44999998807907104,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":3,"referenced_works":["https://openalex.org/W1510913464","https://openalex.org/W1582027222","https://openalex.org/W2351318201"],"related_works":["https://openalex.org/W2392768766","https://openalex.org/W2058118494","https://openalex.org/W2095118173","https://openalex.org/W2382021449","https://openalex.org/W848359858","https://openalex.org/W2106424170","https://openalex.org/W2501188010","https://openalex.org/W4299935056","https://openalex.org/W2768810474","https://openalex.org/W1987401411"],"abstract_inverted_index":{"OAI-PMH-enabled":[0],"open":[1],"source":[2],"digital":[3,140,145],"library":[4,41],"software,":[5],"such":[6,116,159],"as":[7,117,194],"DSpace,":[8],"EPrints,":[9],"VuFind,":[10],"Drupal":[11],"OAI":[12],"harvester,":[13,16],"and":[14,32,51,58,100,107,125,147,209,243,264,278],"PKP":[15],"have":[17,153,260],"made":[18],"it":[19],"possible":[20,280],"to":[21,39,46,134,214,239,282],"harvest":[22],"massive":[23],"metadata":[24,56,59,156,224,275],"from":[25,101,157],"different":[26,95,98,158],"IDRs.":[27],"IT":[28],"brought":[29],"new":[30,37],"hope":[31],"opportunities":[33],"for":[34,54,143,166,251,288],"providing":[35,167],"various":[36,102,138],"services":[38],"our":[40,200],"users.":[42],"This":[43,266],"article":[44,267],"attempts":[45],"explore":[47],"the":[48,80,91,155,180,215,234,247,255,271,279,286,292],"tools,":[49],"techniques,":[50],"significant":[52],"challenges":[53,281],"largescale":[55],"harvesting":[57],"curation.":[60],"A":[61],"recent":[62],"bibliographic":[63],"study":[64],"of":[65,77,86,237,254,274,291],"Scopus":[66],"has":[67],"shown":[68],"that":[69,179],"there":[70],"is":[71,182,226],"a":[72,162,168,206,222,227],"rapid":[73],"increase":[74],"in":[75,94,97,137,199],"publication":[76],"articles":[78],"over":[79],"last":[81],"two":[82,248],"decades.":[83],"\u201cA":[84],"total":[85],"25,":[87],"482":[88],"publications":[89],"represent":[90],"literary":[92],"output":[93],"formats,":[96],"subjects,":[99],"nations\u201d":[103],"(ul":[104],"Ajaz":[105],"Wani":[106],"Gul":[108],"2008).":[109],"All":[110],"these":[111],"preprint":[112],"academic":[113,216],"research":[114],"documents,":[115],"conference":[118],"papers,":[119],"journal":[120],"articles,":[121],"annual":[122],"reports,":[123],"protocols,":[124],"lecture":[126],"notes":[127],"may":[128,177],"be":[129,135,197,205,211,283],"already":[130],"uploaded":[131,136],"or":[132],"need":[133,190],"institutional":[139],"repositories":[141],"(IDRs)":[142],"long-term":[144],"preservation":[146],"reuse.":[148],"In":[149],"this":[150],"study,":[151],"we":[152,176,187],"harvested":[154,256],"IDRs":[160],"into":[161],"centrally":[163],"indexed":[164],"repository":[165],"single":[169],"window":[170],"search":[171],"box.":[172],"Therefore,":[173],"with":[174,220],"this,":[175,221],"dream":[178],"day":[181],"not":[183,189],"far":[184],"away":[185],"when":[186],"will":[188,196,203,210],"any":[191],"e-resource":[192],"subscriptions,":[193],"those":[195],"available":[198],"IDR.":[201],"It":[202],"indeed":[204],"great":[207],"achievement":[208],"extremely":[212],"helpful":[213],"community.":[217],"However,":[218],"along":[219],"continuous":[223],"curation":[225,242,245,253],"major":[228],"intermediate":[229],"phase,":[230],"which":[231],"focusses":[232,269],"on":[233,270],"proper":[235,289],"mapping":[236],"data":[238,276],"metadata.":[240],"Programmatic":[241],"manual":[244],"are":[246],"processes":[249],"conducted":[250],"final":[252],"metadata,":[257],"where":[258],"both":[259],"their":[261],"own":[262],"merits":[263],"demerits.":[265],"further":[268],"process":[272],"workflow":[273],"curation,":[277],"managed":[284],"by":[285],"librarian":[287],"indexing":[290],"items.":[293]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2021,"cited_by_count":1}],"updated_date":"2026-03-25T23:56:10.502304","created_date":"2018-01-05T00:00:00"}
