{"id":"https://openalex.org/W2030891299","doi":"https://doi.org/10.1109/bigdata.2013.6691676","title":"Mapping mutable genres in structurally complex volumes","display_name":"Mapping mutable genres in structurally complex volumes","publication_year":2013,"publication_date":"2013-10-01","ids":{"openalex":"https://openalex.org/W2030891299","doi":"https://doi.org/10.1109/bigdata.2013.6691676","mag":"2030891299"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata.2013.6691676","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata.2013.6691676","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE International Conference on Big Data","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1309.3323","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5006779213","display_name":"Ted Underwood","orcid":"https://orcid.org/0000-0001-8960-1846"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Ted Underwood","raw_affiliation_strings":["Department of English, University of Illinois, Urbana-Champaign, Urbana, IL, USA"],"affiliations":[{"raw_affiliation_string":"Department of English, University of Illinois, Urbana-Champaign, Urbana, IL, USA","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049826232","display_name":"Michael L. Black","orcid":"https://orcid.org/0000-0002-2222-6751"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael L. Black","raw_affiliation_strings":["Department of English, University of Illinois, Urbana-Champaign, Urbana, IL, USA"],"affiliations":[{"raw_affiliation_string":"Department of English, University of Illinois, Urbana-Champaign, Urbana, IL, USA","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020556428","display_name":"Loretta Auvil","orcid":null},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Loretta Auvil","raw_affiliation_strings":["Illinois Informatics Institute, University of Illinois, Urbana-Champaign, Urbana, IL, USA","Illinois Inf. Inst., Univ. of Illinois Urbana-Champaign, Urbana, IL, USA"],"affiliations":[{"raw_affiliation_string":"Illinois Informatics Institute, University of Illinois, Urbana-Champaign, Urbana, IL, USA","institution_ids":["https://openalex.org/I157725225"]},{"raw_affiliation_string":"Illinois Inf. Inst., Univ. of Illinois Urbana-Champaign, Urbana, IL, USA","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5048070110","display_name":"Boris Capitanu","orcid":null},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Boris Capitanu","raw_affiliation_strings":["Illinois Informatics Institute, University of Illinois, Urbana-Champaign, Urbana, IL, USA","Illinois Inf. Inst., Univ. of Illinois Urbana-Champaign, Urbana, IL, USA"],"affiliations":[{"raw_affiliation_string":"Illinois Informatics Institute, University of Illinois, Urbana-Champaign, Urbana, IL, USA","institution_ids":["https://openalex.org/I157725225"]},{"raw_affiliation_string":"Illinois Inf. Inst., Univ. of Illinois Urbana-Champaign, Urbana, IL, USA","institution_ids":["https://openalex.org/I157725225"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5006779213"],"corresponding_institution_ids":["https://openalex.org/I157725225"],"apc_list":null,"apc_paid":null,"fwci":6.9193,"has_fulltext":false,"cited_by_count":30,"citation_normalized_percentile":{"value":0.96578611,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"95","last_page":"103"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9950000047683716,"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"}},"topics":[{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9950000047683716,"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"}},{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9925000071525574,"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"}},{"id":"https://openalex.org/T12377","display_name":"Digital Humanities and Scholarship","score":0.991100013256073,"subfield":{"id":"https://openalex.org/subfields/1208","display_name":"Literature and Literary Theory"},"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/computer-science","display_name":"Computer science","score":0.7477352023124695},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6639655828475952},{"id":"https://openalex.org/keywords/narrative","display_name":"Narrative","score":0.653986930847168},{"id":"https://openalex.org/keywords/digital-library","display_name":"Digital library","score":0.6504969596862793},{"id":"https://openalex.org/keywords/trace","display_name":"TRACE (psycholinguistics)","score":0.6206891536712646},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.5568135976791382},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4969227612018585},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4435592293739319},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.43538427352905273},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.4305551052093506},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.42456039786338806},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.42146068811416626},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3760053515434265},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.13189002871513367},{"id":"https://openalex.org/keywords/cartography","display_name":"Cartography","score":0.08563321828842163}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7477352023124695},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6639655828475952},{"id":"https://openalex.org/C199033989","wikidata":"https://www.wikidata.org/wiki/Q1318295","display_name":"Narrative","level":2,"score":0.653986930847168},{"id":"https://openalex.org/C513874922","wikidata":"https://www.wikidata.org/wiki/Q212805","display_name":"Digital library","level":3,"score":0.6504969596862793},{"id":"https://openalex.org/C75291252","wikidata":"https://www.wikidata.org/wiki/Q1315756","display_name":"TRACE (psycholinguistics)","level":2,"score":0.6206891536712646},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5568135976791382},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4969227612018585},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4435592293739319},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.43538427352905273},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.4305551052093506},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.42456039786338806},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.42146068811416626},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3760053515434265},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.13189002871513367},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.08563321828842163},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/bigdata.2013.6691676","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata.2013.6691676","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE International Conference on Big Data","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1309.3323","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1309.3323","pdf_url":"https://arxiv.org/pdf/1309.3323","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.755.6932","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.755.6932","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://arxiv.org/pdf/1309.3323.pdf","raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1309.3323","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1309.3323","pdf_url":"https://arxiv.org/pdf/1309.3323","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"},"sustainable_development_goals":[{"score":0.8500000238418579,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W80699098","https://openalex.org/W1984762909","https://openalex.org/W1998870286","https://openalex.org/W2004915807","https://openalex.org/W2019096529","https://openalex.org/W2031253971","https://openalex.org/W2040099993","https://openalex.org/W2100454174","https://openalex.org/W2105594594","https://openalex.org/W2133990480","https://openalex.org/W2146241755","https://openalex.org/W2158304679","https://openalex.org/W2486125749","https://openalex.org/W2947020496","https://openalex.org/W2966207845","https://openalex.org/W3014779790","https://openalex.org/W3100051113","https://openalex.org/W3186546642","https://openalex.org/W4211148787","https://openalex.org/W4233639450","https://openalex.org/W4246909242","https://openalex.org/W4248756277"],"related_works":["https://openalex.org/W2364370872","https://openalex.org/W2053269318","https://openalex.org/W2025614924","https://openalex.org/W2294335174","https://openalex.org/W2097963413","https://openalex.org/W2001275470","https://openalex.org/W2073996508","https://openalex.org/W1591475660","https://openalex.org/W3145575561","https://openalex.org/W1974738623"],"abstract_inverted_index":{"To":[0],"mine":[1],"large":[2],"digital":[3],"libraries":[4,41,61],"in":[5,50],"humanistically":[6],"meaningful":[7],"ways,":[8],"we":[9],"need":[10,30],"to":[11,26,32,55,86,107,116],"divide":[12],"them":[13],"by":[14],"genre.":[15],"This":[16],"is":[17],"a":[18,99,124],"task":[19,93],"that":[20,102],"classification":[21,92],"algorithms":[22],"are":[23,79],"well":[24],"suited":[25],"assist,":[27],"but":[28],"they":[29,84],"adjustment":[31],"address":[33,117],"the":[34,51,65,73,91],"specific":[35],"challenges":[36],"of":[37,45,113,126],"this":[38,122],"domain.":[39],"Digital":[40,132],"pose":[42],"two":[43],"problems":[44],"scale":[46],"not":[47],"usually":[48],"found":[49],"article":[52],"datasets":[53],"used":[54],"test":[56],"these":[57],"algorithms.":[58],"1)":[59],"Because":[60,77],"span":[62],"several":[63],"centuries,":[64],"genres":[66],"being":[67],"identified":[68],"may":[69],"change":[70],"gradually":[71],"across":[72],"time":[74],"axis.":[75],"2)":[76],"volumes":[78,128],"much":[80],"longer":[81],"than":[82],"articles,":[83],"tend":[85],"be":[87],"internally":[88],"heterogeneous,":[89],"and":[90,110],"also":[94],"requires":[95],"segmentation.":[96],"We":[97,120],"describe":[98],"multilayered":[100],"solution":[101],"trains":[103],"hidden":[104],"Markov":[105],"models":[106],"segment":[108],"volumes,":[109],"uses":[111],"ensembles":[112],"overlapping":[114],"classifers":[115],"historical":[118],"change.":[119],"demonstrate":[121],"on":[123],"collection":[125],"469,200":[127],"drawn":[129],"from":[130],"HathiTrust":[131],"Library.":[133]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":1},{"year":2017,"cited_by_count":6},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":7},{"year":2014,"cited_by_count":5}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}
