{"id":"https://openalex.org/W2974273246","doi":"https://doi.org/10.1108/jd-10-2018-0175","title":"Comparing \u201cparallel passages\u201d in digital archives","display_name":"Comparing \u201cparallel passages\u201d in digital archives","publication_year":2019,"publication_date":"2019-09-02","ids":{"openalex":"https://openalex.org/W2974273246","doi":"https://doi.org/10.1108/jd-10-2018-0175","mag":"2974273246"},"language":"en","primary_location":{"id":"doi:10.1108/jd-10-2018-0175","is_oa":false,"landing_page_url":"https://doi.org/10.1108/jd-10-2018-0175","pdf_url":null,"source":{"id":"https://openalex.org/S10082577","display_name":"Journal of Documentation","issn_l":"0022-0418","issn":["0022-0418","1758-7379"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319811","host_organization_name":"Emerald Publishing Limited","host_organization_lineage":["https://openalex.org/P4310319811"],"host_organization_lineage_names":["Emerald Publishing Limited"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Documentation","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":"https://openalex.org/A5014086872","display_name":"Martyn Harris","orcid":"https://orcid.org/0000-0003-4851-4679"},"institutions":[{"id":"https://openalex.org/I98259816","display_name":"Birkbeck, University of London","ror":"https://ror.org/02mb95055","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I98259816"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Martyn Harris","raw_affiliation_strings":["Department of Computer Science and Information Systems, Birkbeck, University of London, London, UK"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Information Systems, Birkbeck, University of London, London, UK","institution_ids":["https://openalex.org/I98259816"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015725705","display_name":"Mark Levene","orcid":"https://orcid.org/0000-0001-8632-4732"},"institutions":[{"id":"https://openalex.org/I98259816","display_name":"Birkbeck, University of London","ror":"https://ror.org/02mb95055","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I98259816"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Mark Levene","raw_affiliation_strings":["Department of Computer Science and Information Systems, Birkbeck, University of London, London, UK"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Information Systems, Birkbeck, University of London, London, UK","institution_ids":["https://openalex.org/I98259816"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015784640","display_name":"Dell Zhang","orcid":"https://orcid.org/0000-0002-8774-3725"},"institutions":[{"id":"https://openalex.org/I98259816","display_name":"Birkbeck, University of London","ror":"https://ror.org/02mb95055","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I98259816"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Dell Zhang","raw_affiliation_strings":["Department of Computer Science and Information Systems, Birkbeck, University of London, London, UK"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Information Systems, Birkbeck, University of London, London, UK","institution_ids":["https://openalex.org/I98259816"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5111310912","display_name":"Dan Levene","orcid":null},"institutions":[{"id":"https://openalex.org/I43439940","display_name":"University of Southampton","ror":"https://ror.org/01ryk1543","country_code":"GB","type":"education","lineage":["https://openalex.org/I43439940"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Dan Levene","raw_affiliation_strings":["Department of History, Southampton University, Southampton, UK"],"affiliations":[{"raw_affiliation_string":"Department of History, Southampton University, Southampton, UK","institution_ids":["https://openalex.org/I43439940"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5014086872"],"corresponding_institution_ids":["https://openalex.org/I98259816"],"apc_list":null,"apc_paid":null,"fwci":0.2893,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.67046613,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"76","issue":"1","first_page":"271","last_page":"289"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9966999888420105,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9966999888420105,"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/T11269","display_name":"Algorithms and Data Compression","score":0.994700014591217,"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/T10028","display_name":"Topic Modeling","score":0.9945999979972839,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7905587553977966},{"id":"https://openalex.org/keywords/originality","display_name":"Originality","score":0.6305803060531616},{"id":"https://openalex.org/keywords/cultural-heritage","display_name":"Cultural heritage","score":0.5472825765609741},{"id":"https://openalex.org/keywords/digital-library","display_name":"Digital library","score":0.5049102902412415},{"id":"https://openalex.org/keywords/string","display_name":"String (physics)","score":0.5003392696380615},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4870155453681946},{"id":"https://openalex.org/keywords/character","display_name":"Character (mathematics)","score":0.48179692029953003},{"id":"https://openalex.org/keywords/reuse","display_name":"Reuse","score":0.4649316966533661},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.43988150358200073},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.43957772850990295},{"id":"https://openalex.org/keywords/value","display_name":"Value (mathematics)","score":0.42334744334220886},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.3819678723812103},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.3596230745315552},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3383744955062866},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.28047239780426025}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7905587553977966},{"id":"https://openalex.org/C2776950860","wikidata":"https://www.wikidata.org/wiki/Q2914681","display_name":"Originality","level":3,"score":0.6305803060531616},{"id":"https://openalex.org/C60671577","wikidata":"https://www.wikidata.org/wiki/Q210272","display_name":"Cultural heritage","level":2,"score":0.5472825765609741},{"id":"https://openalex.org/C513874922","wikidata":"https://www.wikidata.org/wiki/Q212805","display_name":"Digital library","level":3,"score":0.5049102902412415},{"id":"https://openalex.org/C157486923","wikidata":"https://www.wikidata.org/wiki/Q1376436","display_name":"String (physics)","level":2,"score":0.5003392696380615},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4870155453681946},{"id":"https://openalex.org/C2780861071","wikidata":"https://www.wikidata.org/wiki/Q1062934","display_name":"Character (mathematics)","level":2,"score":0.48179692029953003},{"id":"https://openalex.org/C206588197","wikidata":"https://www.wikidata.org/wiki/Q846574","display_name":"Reuse","level":2,"score":0.4649316966533661},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.43988150358200073},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.43957772850990295},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.42334744334220886},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3819678723812103},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.3596230745315552},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3383744955062866},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.28047239780426025},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.0},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.0},{"id":"https://openalex.org/C11012388","wikidata":"https://www.wikidata.org/wiki/Q170658","display_name":"Creativity","level":2,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","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/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","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":3,"locations":[{"id":"doi:10.1108/jd-10-2018-0175","is_oa":false,"landing_page_url":"https://doi.org/10.1108/jd-10-2018-0175","pdf_url":null,"source":{"id":"https://openalex.org/S10082577","display_name":"Journal of Documentation","issn_l":"0022-0418","issn":["0022-0418","1758-7379"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319811","host_organization_name":"Emerald Publishing Limited","host_organization_lineage":["https://openalex.org/P4310319811"],"host_organization_lineage_names":["Emerald Publishing Limited"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Documentation","raw_type":"journal-article"},{"id":"pmh:oai:eprints.bbk.ac.uk.oai2:28183","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4306400466","display_name":"BIROn (Birkbeck, University of London)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98259816","host_organization_name":"Birkbeck, University of London","host_organization_lineage":["https://openalex.org/I98259816"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"PeerReviewed"},{"id":"pmh:oai:eprints.soton.ac.uk:436352","is_oa":false,"landing_page_url":"https://eprints.soton.ac.uk/436352/","pdf_url":null,"source":{"id":"https://openalex.org/S4306401019","display_name":"ePrints Soton (University of Southampton)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I43439940","host_organization_name":"University of Southampton","host_organization_lineage":["https://openalex.org/I43439940"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6200000047683716,"id":"https://metadata.un.org/sdg/11","display_name":"Sustainable cities and communities"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W60385418","https://openalex.org/W123495503","https://openalex.org/W173640133","https://openalex.org/W1565725288","https://openalex.org/W1583551282","https://openalex.org/W1647671624","https://openalex.org/W1938755728","https://openalex.org/W1966812932","https://openalex.org/W1972594981","https://openalex.org/W1973957152","https://openalex.org/W1976091498","https://openalex.org/W1992327814","https://openalex.org/W1993610807","https://openalex.org/W2004329216","https://openalex.org/W2005892921","https://openalex.org/W2019135282","https://openalex.org/W2027447543","https://openalex.org/W2029097226","https://openalex.org/W2041614298","https://openalex.org/W2051593977","https://openalex.org/W2067053930","https://openalex.org/W2108872112","https://openalex.org/W2132481658","https://openalex.org/W2140679639","https://openalex.org/W2141599568","https://openalex.org/W2142943833","https://openalex.org/W2158195707","https://openalex.org/W2159726290","https://openalex.org/W2195330689","https://openalex.org/W2586547182","https://openalex.org/W2803771812","https://openalex.org/W2973518926","https://openalex.org/W3125740831","https://openalex.org/W4242883504","https://openalex.org/W4285719527","https://openalex.org/W6637468571","https://openalex.org/W6805873119"],"related_works":["https://openalex.org/W2593155302","https://openalex.org/W2041415459","https://openalex.org/W2072812638","https://openalex.org/W3126095231","https://openalex.org/W2352855287","https://openalex.org/W2378906650","https://openalex.org/W2384288445","https://openalex.org/W2382526412","https://openalex.org/W4200071106","https://openalex.org/W2347474189"],"abstract_inverted_index":{"Purpose":[0],"The":[1,28,67,150,189,223],"purpose":[2],"of":[3,16,48,64,75,84,90,113,121,136,145,160,180,191,202,207,255,275,280],"this":[4],"paper":[5],"is":[6,69,128,225],"to":[7,12,54,71,102,132,156,170,196,277],"present":[8],"a":[9,31,38,45,72,88,111,133,205,229,250],"language-agnostic":[10],"approach":[11,68,127,151,168,224],"facilitate":[13],"the":[14,49,82,85,114,126,167,198,260,272,278,281],"discovery":[15],"\u201cparallel":[17,192],"passages\u201d":[18,193],"stored":[19],"in":[20,81,92,140,204,249],"historic":[21,174],"and":[22,33,57,77,99,105,130,144,162,200,219,227,241],"cultural":[23,220],"heritage":[24],"digital":[25,158,171],"archives.":[26],"Design/methodology/approach":[27],"authors":[29,261],"explore":[30],"novel,":[32],"relatively":[34],"simple":[35],"approach,":[36],"using":[37],"character-based":[39],"statistical":[40],"language":[41,95,279],"model":[42],"combined":[43],"with":[44,138],"tailored":[46],"version":[47],"Basic":[50],"Local":[51],"Alignment":[52],"Tool":[53],"extract":[55],"exact":[56],"approximate":[58],"string":[59],"patterns":[60],"shared":[61,246],"between":[62],"groups":[63],"documents.":[65,256,282],"Findings":[66],"applicable":[70,169],"wide":[73,134],"range":[74,135],"languages,":[76,142],"compensates":[78],"for":[79,185,234],"variability":[80],"text":[83,217,247],"documents":[86,139,240],"as":[87,110,259],"result":[89,112],"differences":[91],"dialect,":[93],"authorship,":[94],"change":[96],"over":[97],"time":[98],"errors":[100,109],"due":[101],"inaccurate":[103],"transcriptions":[104],"optical":[106],"character":[107],"recognition":[108],"digitisation":[115],"process.":[116],"Research":[117],"limitations/implications":[118],"A":[119],"number":[120],"case":[122],"studies":[123],"demonstrate":[124],"that":[125,236,270],"practical":[129],"generalisable":[131],"archives":[137,172],"different":[141],"domains":[143],"varying":[146],"quality.":[147],"Practical":[148],"implications":[149,188],"described":[152],"can":[153,210,237],"be":[154],"applied":[155],"any":[157],"archive":[159,254],"modern":[161],"contemporary":[163],"texts.":[164],"This":[165],"makes":[166],"recording":[173],"texts,":[175],"but":[176],"also":[177],"those":[178],"composed":[179],"more":[181],"recent":[182],"news":[183],"articles,":[184],"example.":[186],"Social":[187],"analysis":[190],"enables":[194],"researchers":[195,233],"quantify":[197],"presence":[199],"extent":[201],"text-reuse":[203],"collection":[206],"documents,":[208],"which":[209],"provide":[211,271],"useful":[212],"data":[213],"on":[214],"author":[215],"style,":[216],"genres":[218],"contexts.":[221],"Originality/value":[222],"novel":[226],"addresses":[228],"need":[230],"by":[231,245],"humanities":[232],"tools":[235,267],"identify":[238],"similar":[239],"local":[242],"similarities":[243],"represented":[244],"sequences":[248],"potentially":[251],"vast":[252],"large":[253],"As":[257],"far":[258],"are":[262,265],"aware,":[263],"there":[264],"no":[266],"currently":[268],"exist":[269],"same":[273],"level":[274],"tolerance":[276]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}
