{"id":"https://openalex.org/W7166555757","doi":"https://doi.org/10.63317/3oaq8zxp9hwx","title":"Mining the Pre-1948 Palestinian Press: Unsupervised Keyphrase Extraction and Temporal Discourse Analysis from Five Historical Arabic Newspapers","display_name":"Mining the Pre-1948 Palestinian Press: Unsupervised Keyphrase Extraction and Temporal Discourse Analysis from Five Historical Arabic Newspapers","publication_year":2026,"publication_date":"2026-05-01","ids":{"openalex":"https://openalex.org/W7166555757","doi":"https://doi.org/10.63317/3oaq8zxp9hwx"},"language":"en","primary_location":{"id":"doi:10.63317/3oaq8zxp9hwx","doi":"https://doi.org/10.63317/3oaq8zxp9hwx","is_oa":true,"landing_page_url":"https://doi.org/10.63317/3oaq8zxp9hwx","pdf_url":"http://www.lrec-conf.org/proceedings/lrec2026/workshops/nakbanlp/pdf/2026.nakbanlp-1.2.pdf","source":{"id":"https://openalex.org/S7407088301","display_name":"Language Resources and Evaluation Conference (LREC)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Language Resources and Evaluation Conference","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"http://www.lrec-conf.org/proceedings/lrec2026/workshops/nakbanlp/pdf/2026.nakbanlp-1.2.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5078565561","display_name":"Basel Barakat","orcid":"https://orcid.org/0000-0001-9126-7613","observed_orcids":["https://orcid.org/0000-0001-9126-7613"]},"institutions":[{"id":"https://openalex.org/I55521800","display_name":"Goldsmiths University of London","ror":"https://ror.org/01khx4a30","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I55521800"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Basel Barakat","raw_affiliation_strings":["School of Computing , Goldsmiths University of London , New Cross , London , UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computing , Goldsmiths University of London , New Cross , London , UK","institution_ids":["https://openalex.org/I55521800"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5137264638","display_name":"Nizam Barakat","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nizam Barakat","raw_affiliation_strings":["Independent Scholar"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Independent Scholar","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.43879555,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"23","last_page":"32"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9077000021934509,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9077000021934509,"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/T13910","display_name":"Computational and Text Analysis Methods","score":0.05660000070929527,"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/T12377","display_name":"Digital Humanities and Scholarship","score":0.015799999237060547,"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/unsupervised-keyphrase-extraction","display_name":"unsupervised keyphrase extraction","score":0.8949999809265137},{"id":"https://openalex.org/keywords/keybert","display_name":"KeyBERT","score":0.8539999723434448},{"id":"https://openalex.org/keywords/arabert","display_name":"AraBERT","score":0.9900000095367432},{"id":"https://openalex.org/keywords/ottoman-palestine","display_name":"Ottoman Palestine","score":0.527999997138977},{"id":"https://openalex.org/keywords/british-mandate-for-palestine","display_name":"British Mandate Palestine","score":0.9879999756813049},{"id":"https://openalex.org/keywords/pan-arab-nationalism","display_name":"pan-Arab nationalism","score":0.8479999899864197},{"id":"https://openalex.org/keywords/anticolonial-resistance","display_name":"anti-colonial resistance","score":0.9760000109672546}],"concepts":[{"id":"https://openalex.org/C201280247","wikidata":"https://www.wikidata.org/wiki/Q11032","display_name":"Newspaper","level":2,"score":0.6797999739646912},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5116999745368958},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.49889999628067017},{"id":"https://openalex.org/C61423126","wikidata":"https://www.wikidata.org/wiki/Q187432","display_name":"Scripting language","level":2,"score":0.461899995803833},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.4603999853134155},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.45329999923706055},{"id":"https://openalex.org/C26983874","wikidata":"https://www.wikidata.org/wiki/Q263864","display_name":"Tag cloud","level":3,"score":0.45089998841285706},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41269999742507935},{"id":"https://openalex.org/C96455323","wikidata":"https://www.wikidata.org/wiki/Q13955","display_name":"Arabic","level":2,"score":0.4041999876499176},{"id":"https://openalex.org/C84389358","wikidata":"https://www.wikidata.org/wiki/Q1129466","display_name":"Discourse analysis","level":2,"score":0.4036000072956085},{"id":"https://openalex.org/C2778689934","wikidata":"https://www.wikidata.org/wiki/Q1313396","display_name":"Headline","level":2,"score":0.39149999618530273},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.38350000977516174},{"id":"https://openalex.org/C2775884135","wikidata":"https://www.wikidata.org/wiki/Q845436","display_name":"Mandate","level":2,"score":0.3797999918460846},{"id":"https://openalex.org/C2779837783","wikidata":"https://www.wikidata.org/wiki/Q691101","display_name":"Carelessness","level":2,"score":0.3637999892234802},{"id":"https://openalex.org/C2778121359","wikidata":"https://www.wikidata.org/wiki/Q8096","display_name":"Lexicon","level":2,"score":0.3580000102519989},{"id":"https://openalex.org/C519991488","wikidata":"https://www.wikidata.org/wiki/Q28865","display_name":"Python (programming language)","level":2,"score":0.3564999997615814},{"id":"https://openalex.org/C162446236","wikidata":"https://www.wikidata.org/wiki/Q653137","display_name":"Content analysis","level":2,"score":0.34540000557899475},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.3337000012397766},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.323199987411499},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.28769999742507935},{"id":"https://openalex.org/C2780799905","wikidata":"https://www.wikidata.org/wiki/Q20901295","display_name":"Ministry of Foreign Affairs","level":2,"score":0.2727999985218048},{"id":"https://openalex.org/C26022165","wikidata":"https://www.wikidata.org/wiki/Q8091","display_name":"Grammar","level":2,"score":0.267300009727478},{"id":"https://openalex.org/C18918823","wikidata":"https://www.wikidata.org/wiki/Q49389","display_name":"Tourism","level":2,"score":0.2513999938964844},{"id":"https://openalex.org/C518677369","wikidata":"https://www.wikidata.org/wiki/Q202833","display_name":"Social media","level":2,"score":0.25}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.63317/3oaq8zxp9hwx","doi":"https://doi.org/10.63317/3oaq8zxp9hwx","is_oa":true,"landing_page_url":"https://doi.org/10.63317/3oaq8zxp9hwx","pdf_url":"http://www.lrec-conf.org/proceedings/lrec2026/workshops/nakbanlp/pdf/2026.nakbanlp-1.2.pdf","source":{"id":"https://openalex.org/S7407088301","display_name":"Language Resources and Evaluation Conference (LREC)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Language Resources and Evaluation Conference","raw_type":"proceedings-article"},{"id":"pmh:oai:eprints.gold.ac.uk:40472","doi":null,"is_oa":true,"landing_page_url":"https://orcid.org/0000-0001-9126-7613>;","pdf_url":"https://research.gold.ac.uk/id/eprint/40472/1/PLS-9.pdf","source":{"id":"https://openalex.org/S4306400496","display_name":"Goldsmiths (University of London)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I166337079","host_organization_name":"Queen Mary University of London","host_organization_lineage":["https://openalex.org/I166337079"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"Accepted Version","raw_type":"Conference or Workshop Item"}],"best_oa_location":{"id":"doi:10.63317/3oaq8zxp9hwx","doi":"https://doi.org/10.63317/3oaq8zxp9hwx","is_oa":true,"landing_page_url":"https://doi.org/10.63317/3oaq8zxp9hwx","pdf_url":"http://www.lrec-conf.org/proceedings/lrec2026/workshops/nakbanlp/pdf/2026.nakbanlp-1.2.pdf","source":{"id":"https://openalex.org/S7407088301","display_name":"Language Resources and Evaluation Conference (LREC)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Language Resources and Evaluation Conference","raw_type":"proceedings-article"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[{"id":"https://metadata.un.org/sdg/4","score":0.4229534864425659,"display_name":"Quality education"}],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7166555757.pdf","grobid_xml":"https://content.openalex.org/works/W7166555757.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W3031867036","https://openalex.org/W2317369480","https://openalex.org/W7132660415","https://openalex.org/W7020148937","https://openalex.org/W2971582275","https://openalex.org/W2945961522","https://openalex.org/W1584144291","https://openalex.org/W6908020704","https://openalex.org/W7167161807","https://openalex.org/W7166584017"],"abstract_inverted_index":{"The":[0],"Palestinian":[1,47,145],"Arabic-language":[2],"press":[3],"of":[4,23,66,90,144,176],"the":[5,21,64,80,88,124,129,169,174],"late":[6],"Ottoman":[7],"and":[8,26,39,59,100,114,140,150,155,173,185],"British":[9],"Mandate":[10],"periods":[11],"constitutes":[12],"a":[13,67,102],"rich":[14],"but":[15],"computationally":[16],"under-explored":[17],"archive":[18],"for":[19,37,96],"studying":[20],"evolution":[22],"political,":[24],"cultural,":[25],"social":[27],"discourse":[28,178],"in":[29],"pre-1948":[30],"Palestine.This":[31],"paper":[32],"presents":[33],"an":[34,93],"end-to-end":[35],"pipeline":[36,130],"extracting":[38],"analyzing":[40],"thematic":[41],"content":[42],"from":[43,70,75],"five":[44,125],"historically":[45],"significant":[46],"newspapers:":[48],"Lis\u0101n":[49],"al-\u02bfArab":[50],"\u202b\ufedf\ufeb4\ufe8e\u0646(\u202c":[51],"\u202b,)\u0627\ufedf\ufecc\ufeae\u0628\u202c":[52],"Al-Bushr\u0101":[53],"\u202b,)\u0627\ufedf\ufe92\ufeb8\ufeae\u0649(\u202c":[54],"Al-Karmil":[55],"\u202b,)\u0627\ufedf\ufedc\ufeae\ufee3\ufede(\u202c":[56],"Al-Dif\u0101\u02bf":[57],"\u202b,)\u0627\ufedf\ufeaa\ufed3\ufe8e\u0639(\u202c":[58],"Filas\u1e6d\u012bn":[60],"\u202b.)\ufed3\ufee0\ufeb4\ufec4\ufef4\ufee6(\u202cWe":[61],"describe":[62],"(i)":[63],"construction":[65],"five-source":[68],"corpus":[69],"scanned":[71],"newspaper":[72],"images":[73],"obtained":[74],"archival":[76],"collections,":[77],"processed":[78],"using":[79],"Google":[81],"Cloud":[82],"Vision":[83],"OCR":[84],"(GCV-OCR)":[85],"API,":[86],"(ii)":[87],"adaptation":[89],"KeyBERT":[91],"with":[92,118,164],"AraBERT":[94],"backbone":[95],"unsupervised":[97],"keyphrase":[98],"extraction,":[99],"(iii)":[101],"purpose-built":[103],"Python":[104],"visualization":[105,186],"toolkit":[106],"that":[107,128,162],"produces":[108],"keyword-frequency":[109],"heatmaps,":[110],"longitudinal":[111],"trend":[112],"charts,":[113],"ranked":[115],"bar":[116],"charts":[117],"full":[119],"Arabic":[120],"script":[121],"rendering.Experiments":[122],"across":[123],"subcorpora":[126],"show":[127],"yields":[131],"topically":[132],"diverse":[133],"keyphrases":[134],"reflecting":[135],"each":[136],"newspaper's":[137],"editorial":[138],"orientation":[139],"its":[141],"distinct":[142],"representation":[143],"native":[146],"perspectives-from":[147],"pan-Arab":[148],"nationalism":[149],"anti-colonial":[151],"resistance":[152],"to":[153],"religious":[154],"communal":[156],"affairs.Temporal":[157],"analysis":[158],"reveals":[159],"event-responsive":[160],"patterns":[161],"align":[163],"major":[165],"historical":[166],"developments,":[167],"including":[168],"1936-1939":[170],"Arab":[171],"Revolt":[172],"intensification":[175],"sovereignty":[177],"toward":[179],"1948.The":[180],"pipeline,":[181],"data":[182],"format":[183],"specifications,":[184],"code":[187],"are":[188],"provided":[189],"as":[190],"supplementary":[191],"material.":[192]},"counts_by_year":[],"updated_date":"2026-10-05T09:50:58.205359","created_date":"2026-06-30T00:00:00"}
