{"id":"https://openalex.org/W4252065207","doi":"https://doi.org/10.1109/jcdl.2017.7991569","title":"Estimating the Date of First Publication in a Large-Scale Digital Library","display_name":"Estimating the Date of First Publication in a Large-Scale Digital Library","publication_year":2017,"publication_date":"2017-06-01","ids":{"openalex":"https://openalex.org/W4252065207","doi":"https://doi.org/10.1109/jcdl.2017.7991569"},"language":"en","primary_location":{"id":"doi:10.1109/jcdl.2017.7991569","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jcdl.2017.7991569","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 ACM/IEEE Joint Conference on Digital Libraries (JCDL)","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/A5058212934","display_name":"David Bamman","orcid":"https://orcid.org/0009-0003-1171-9408"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"David Bamman","raw_affiliation_strings":["School of Information, University of California, Berkeley"],"affiliations":[{"raw_affiliation_string":"School of Information, University of California, Berkeley","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013974495","display_name":"Michelle Mohr Carney","orcid":"https://orcid.org/0000-0002-9194-7384"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michelle Carney","raw_affiliation_strings":["School of Information, University of California, Berkeley"],"affiliations":[{"raw_affiliation_string":"School of Information, University of California, Berkeley","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000508033","display_name":"Jon Gillick","orcid":null},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jon Gillick","raw_affiliation_strings":["School of Information, University of California, Berkeley"],"affiliations":[{"raw_affiliation_string":"School of Information, University of California, Berkeley","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065487970","display_name":"Cody Hennesy","orcid":"https://orcid.org/0000-0002-9410-9810"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Cody Hennesy","raw_affiliation_strings":["Doe Library, University of California, Berkeley"],"affiliations":[{"raw_affiliation_string":"Doe Library, University of California, Berkeley","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5003673361","display_name":"Vijitha Sridhar","orcid":null},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vijitha Sridhar","raw_affiliation_strings":["Doe Library, University of California, Berkeley"],"affiliations":[{"raw_affiliation_string":"Doe Library, University of California, Berkeley","institution_ids":["https://openalex.org/I95457486"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5058212934"],"corresponding_institution_ids":["https://openalex.org/I95457486"],"apc_list":null,"apc_paid":null,"fwci":0.7397,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.73635548,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"10"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9947999715805054,"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"}},"topics":[{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9947999715805054,"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/T13910","display_name":"Computational and Text Analysis Methods","score":0.9883999824523926,"subfield":{"id":"https://openalex.org/subfields/3300","display_name":"General Social Sciences"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12090","display_name":"Language and cultural evolution","score":0.9812999963760376,"subfield":{"id":"https://openalex.org/subfields/3316","display_name":"Cultural Studies"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/metadata","display_name":"Metadata","score":0.8850158452987671},{"id":"https://openalex.org/keywords/data-deduplication","display_name":"Data deduplication","score":0.7966622114181519},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7661911249160767},{"id":"https://openalex.org/keywords/digital-library","display_name":"Digital library","score":0.7503691911697388},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6393108367919922},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.5738521814346313},{"id":"https://openalex.org/keywords/heuristic","display_name":"Heuristic","score":0.4928126633167267},{"id":"https://openalex.org/keywords/composition","display_name":"Composition (language)","score":0.4822317063808441},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.3830357789993286},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.3370726704597473},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.22911164164543152},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.12737029790878296},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.1078953742980957},{"id":"https://openalex.org/keywords/cartography","display_name":"Cartography","score":0.08060163259506226}],"concepts":[{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.8850158452987671},{"id":"https://openalex.org/C32587265","wikidata":"https://www.wikidata.org/wiki/Q1182260","display_name":"Data deduplication","level":2,"score":0.7966622114181519},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7661911249160767},{"id":"https://openalex.org/C513874922","wikidata":"https://www.wikidata.org/wiki/Q212805","display_name":"Digital library","level":3,"score":0.7503691911697388},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6393108367919922},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.5738521814346313},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.4928126633167267},{"id":"https://openalex.org/C40231798","wikidata":"https://www.wikidata.org/wiki/Q1333743","display_name":"Composition (language)","level":2,"score":0.4822317063808441},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.3830357789993286},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3370726704597473},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.22911164164543152},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.12737029790878296},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.1078953742980957},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.08060163259506226},{"id":"https://openalex.org/C164913051","wikidata":"https://www.wikidata.org/wiki/Q482","display_name":"Poetry","level":2,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"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/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/jcdl.2017.7991569","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jcdl.2017.7991569","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 ACM/IEEE Joint Conference on Digital Libraries (JCDL)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.6800000071525574}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W198744195","https://openalex.org/W1552472270","https://openalex.org/W1562765109","https://openalex.org/W1570098300","https://openalex.org/W1597826727","https://openalex.org/W1808906688","https://openalex.org/W1969168960","https://openalex.org/W1972672340","https://openalex.org/W2022095054","https://openalex.org/W2042641525","https://openalex.org/W2053107662","https://openalex.org/W2061838198","https://openalex.org/W2079066173","https://openalex.org/W2095881835","https://openalex.org/W2099984129","https://openalex.org/W2102343050","https://openalex.org/W2105286768","https://openalex.org/W2107550813","https://openalex.org/W2117897510","https://openalex.org/W2132069633","https://openalex.org/W2135870693","https://openalex.org/W2148036569","https://openalex.org/W2251747890","https://openalex.org/W2267520627","https://openalex.org/W2285531450","https://openalex.org/W2307020448","https://openalex.org/W2317477910","https://openalex.org/W2398266592","https://openalex.org/W2609517418","https://openalex.org/W4242859709","https://openalex.org/W4243754476","https://openalex.org/W4246032955","https://openalex.org/W4246334968","https://openalex.org/W6679663036","https://openalex.org/W6691528603","https://openalex.org/W6695973988","https://openalex.org/W6712538997"],"related_works":["https://openalex.org/W3144870715","https://openalex.org/W3142319788","https://openalex.org/W2587188779","https://openalex.org/W3132870970","https://openalex.org/W4385804830","https://openalex.org/W2943088381","https://openalex.org/W2074021203","https://openalex.org/W2144348063","https://openalex.org/W4296125805","https://openalex.org/W1982579475"],"abstract_inverted_index":{"One":[0],"prerequisite":[1],"for":[2],"cultural":[3],"analysis":[4,130],"in":[5,80,89,118],"large-scale":[6],"digital":[7],"libraries":[8],"is":[9,124],"an":[10,28],"accurate":[11,125],"estimate":[12],"of":[13,16,18,25,27,43,46,48,51,85,99,104,113,131],"the":[14,19,23,30,54,69,83,97,102,105,129],"date":[15,24,84,98],"composition":[17,100,122],"text-as":[20],"distinct":[21],"from":[22,53,101],"publication":[26,47,86],"edition-for":[29],"works":[31,116],"they":[32],"contain.":[33],"In":[34],"this":[35],"work,":[36],"we":[37],"present":[38],"a":[39,110],"manually":[40],"annotated":[41],"dataset":[42],"first":[44],"dates":[45],"three":[49],"samples":[50],"books":[52],"HathiTrust":[55],"Digital":[56],"Library":[57],"(uniform":[58],"random,":[59],"uniform":[60],"fiction,":[61],"and":[62,66,76,94,120],"stratified":[63],"by":[64],"decade),":[65],"empirically":[67],"evaluate":[68],"disparity":[70],"between":[71],"these":[72],"gold":[73],"standard":[74],"labels":[75],"several":[77,91],"approximations":[78],"used":[79],"practice":[81],"(using":[82],"as":[87],"provided":[88],"metadata,":[90],"deduplication":[92,115],"methods,":[93],"automatically":[95],"predicting":[96],"text":[103],"book).":[106],"We":[107],"find":[108],"that":[109],"simple":[111],"heuristic":[112],"metadata-based":[114],"best":[117],"practice,":[119],"text-based":[121],"dating":[123],"enough":[126],"to":[127],"inform":[128],"apparent":[132],"time.":[133]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":4},{"year":2019,"cited_by_count":2},{"year":2017,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
