{"id":"https://openalex.org/W2772005286","doi":"https://doi.org/10.1147/jrd.2017.2742706","title":"Extracting information from newspaper archives in Africa","display_name":"Extracting information from newspaper archives in Africa","publication_year":2017,"publication_date":"2017-11-01","ids":{"openalex":"https://openalex.org/W2772005286","doi":"https://doi.org/10.1147/jrd.2017.2742706","mag":"2772005286"},"language":"en","primary_location":{"id":"doi:10.1147/jrd.2017.2742706","is_oa":false,"landing_page_url":"https://doi.org/10.1147/jrd.2017.2742706","pdf_url":null,"source":{"id":"https://openalex.org/S4210219925","display_name":"IBM Journal of Research and Development","issn_l":"0018-8646","issn":["0018-8646","2151-8556"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320652","host_organization_name":"IBM","host_organization_lineage":["https://openalex.org/P4310320652"],"host_organization_lineage_names":["IBM"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IBM Journal of Research and Development","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/A5106225936","display_name":"Mattia Zeni","orcid":"https://orcid.org/0000-0002-6767-9519"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"M. Zeni","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5040195857","display_name":"Komminist Weldemariam","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"K. Weldemariam","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0902,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.48633912,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"61","issue":"6","first_page":"12:1","last_page":"12:12"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","score":0.9988999962806702,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T11439","display_name":"Video Analysis and Summarization","score":0.9988999962806702,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T11309","display_name":"Music and Audio Processing","score":0.9980999827384949,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9977999925613403,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/newspaper","display_name":"Newspaper","score":0.9838064908981323},{"id":"https://openalex.org/keywords/digital-archives","display_name":"Digital Archives","score":0.6211228966712952},{"id":"https://openalex.org/keywords/reading","display_name":"Reading (process)","score":0.5619567632675171},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5459129810333252},{"id":"https://openalex.org/keywords/service","display_name":"Service (business)","score":0.42940765619277954},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.38246914744377136},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.35781532526016235},{"id":"https://openalex.org/keywords/political-science","display_name":"Political science","score":0.1742381751537323},{"id":"https://openalex.org/keywords/media-studies","display_name":"Media studies","score":0.16095814108848572},{"id":"https://openalex.org/keywords/sociology","display_name":"Sociology","score":0.1351512372493744},{"id":"https://openalex.org/keywords/business","display_name":"Business","score":0.10452702641487122}],"concepts":[{"id":"https://openalex.org/C201280247","wikidata":"https://www.wikidata.org/wiki/Q11032","display_name":"Newspaper","level":2,"score":0.9838064908981323},{"id":"https://openalex.org/C2780157182","wikidata":"https://www.wikidata.org/wiki/Q11154625","display_name":"Digital Archives","level":2,"score":0.6211228966712952},{"id":"https://openalex.org/C554936623","wikidata":"https://www.wikidata.org/wiki/Q199657","display_name":"Reading (process)","level":2,"score":0.5619567632675171},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5459129810333252},{"id":"https://openalex.org/C2780378061","wikidata":"https://www.wikidata.org/wiki/Q25351891","display_name":"Service (business)","level":2,"score":0.42940765619277954},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.38246914744377136},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.35781532526016235},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.1742381751537323},{"id":"https://openalex.org/C29595303","wikidata":"https://www.wikidata.org/wiki/Q165650","display_name":"Media studies","level":1,"score":0.16095814108848572},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.1351512372493744},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.10452702641487122},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C162853370","wikidata":"https://www.wikidata.org/wiki/Q39809","display_name":"Marketing","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1147/jrd.2017.2742706","is_oa":false,"landing_page_url":"https://doi.org/10.1147/jrd.2017.2742706","pdf_url":null,"source":{"id":"https://openalex.org/S4210219925","display_name":"IBM Journal of Research and Development","issn_l":"0018-8646","issn":["0018-8646","2151-8556"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320652","host_organization_name":"IBM","host_organization_lineage":["https://openalex.org/P4310320652"],"host_organization_lineage_names":["IBM"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IBM Journal of Research and Development","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4699999988079071,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W423591211","https://openalex.org/W1539712790","https://openalex.org/W1997739353","https://openalex.org/W1998729616","https://openalex.org/W2001642682","https://openalex.org/W2007989973","https://openalex.org/W2009557763","https://openalex.org/W2021123232","https://openalex.org/W2025384595","https://openalex.org/W2030393865","https://openalex.org/W2089298206","https://openalex.org/W2094191620","https://openalex.org/W2094549658","https://openalex.org/W2103986443","https://openalex.org/W2123442489","https://openalex.org/W2131448412","https://openalex.org/W2133004463","https://openalex.org/W2135231474","https://openalex.org/W2139821942","https://openalex.org/W2146570986","https://openalex.org/W2154032543","https://openalex.org/W2155619922","https://openalex.org/W2156483112","https://openalex.org/W2162431081","https://openalex.org/W2338299627","https://openalex.org/W2346333951","https://openalex.org/W2346770837","https://openalex.org/W3023264106","https://openalex.org/W3148081028","https://openalex.org/W4239466315","https://openalex.org/W4248625073","https://openalex.org/W6650820226","https://openalex.org/W6682843645","https://openalex.org/W6703838484","https://openalex.org/W6705177702"],"related_works":["https://openalex.org/W2125294603","https://openalex.org/W2401210030","https://openalex.org/W302995870","https://openalex.org/W2808460144","https://openalex.org/W2489050821","https://openalex.org/W2377062261","https://openalex.org/W1825588579","https://openalex.org/W2749017085","https://openalex.org/W2470303750","https://openalex.org/W2113169315","https://openalex.org/W1751907424","https://openalex.org/W2478090783","https://openalex.org/W304147300","https://openalex.org/W3011816190","https://openalex.org/W2998847294","https://openalex.org/W2182961170","https://openalex.org/W1257150244","https://openalex.org/W3029796176","https://openalex.org/W2574092322","https://openalex.org/W2571236102"],"abstract_inverted_index":{"In":[0],"sub-Saharan":[1],"Africa,":[2],"lack":[3],"of":[4,17,29,52,60,88,94,114,128,134],"useful":[5,62],"information":[6,170],"for":[7],"the":[8,15,27,56,74,91,95,115,125,132,169,181],"public":[9,18],"good":[10],"is":[11,171],"one":[12],"obstacle":[13],"to":[14,54,78,81],"development":[16],"services":[19],"(public":[20],"safety,":[21],"education,":[22],"healthcare,":[23],"etc.).":[24],"This":[25],"makes":[26,131],"extraction":[28],"data":[30,53,135],"from":[31,136,159,167],"digital":[32,160],"archives":[33,41,161,166],"(e.g.,":[34],"analog":[35],"sources":[36,44],"such":[37],"as":[38],"printed":[39],"newspaper":[40,75,116,165],"and":[42,58,97,107,154],"born-digital":[43],"like":[45],"native":[46],"PDF)":[47],"an":[48,89],"interesting":[49],"alternative":[50],"source":[51],"increase":[55],"amount":[57],"diversity":[59],"potentially":[61],"information.":[63],"Printed":[64],"newspapers":[65,138,158],"contain":[66],"various":[67,112],"multiarticle":[68],"page":[69],"layouts,":[70],"wherein":[71],"articles":[72,156],"in":[73,117,157],"are":[76,100,109],"designed":[77],"allow":[79],"readers":[80],"define":[82],"their":[83],"own":[84],"reading.":[85],"The":[86],"title":[87],"article,":[90],"introductory":[92],"story":[93],"title,":[96],"related":[98],"images":[99,108],"mostly":[101],"grouped":[102],"together.":[103],"However,":[104],"subsequent":[105],"paragraphs":[106],"spread":[110],"across":[111],"pages":[113],"a":[118,139,149],"somewhat":[119],"unpredictable":[120],"manner.":[121],"This,":[122],"together":[123],"with":[124],"poor":[126],"quality":[127],"existing":[129],"archives,":[130],"extracting":[133],"archived":[137],"daunting":[140],"research":[141],"problem.":[142],"To":[143],"solve":[144],"these":[145],"challenges,":[146],"we":[147,174],"present":[148],"system":[150],"that":[151],"extracts,":[152],"detects,":[153],"clusters":[155],"(mainly":[162],"containing":[163],"scanned":[164],"which":[168],"extracted).":[172],"Finally,":[173],"also":[175],"describe":[176],"our":[177],"proof-of-concept":[178],"service":[179],"using":[180],"extracted":[182],"data.":[183]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
