@inproceedings{barakat-barakat-2026-mining,
title = "Mining the Pre-1948 Palestinian Press: Unsupervised Keyphrase Extraction and Temporal Discourse Analysis from Five Historical {A}rabic Newspapers",
author = "Barakat, Basel and
Barakat, Nizam",
editor = "Jarrar, Mustafa and
El-Haj, Mo and
Haddad, Amal and
Atiani, Serin and
Abudalfa, Shadi and
Regier, Terry and
Rayson, Paul and
Sima{'}an, Khalil and
Mansour, Camille",
booktitle = "Proceedings of the 2nd International Workshop on Nakba Narratives as Language Resources @ {LREC} 2026",
month = may,
year = "2026",
address = "Palma, Mallorca (Spain)",
publisher = "ELRA Language Resources Association (ELRA)",
url = "https://aclanthology.org/2026.nakbanlp-1.2/",
doi = "10.63317/3oaq8zxp9hwx",
pages = "23--32",
abstract = "The Palestinian Arabic-language press of the late Ottoman and British Mandate periods constitutes a rich but computationally under-explored archive for studying the evolution of political, cultural, and social discourse in pre-1948 Palestine. This paper presents an end-to-end pipeline for extracting and analyzing thematic content from five historically significant Palestinian newspapers: Lis{\={a}}n al-ʿArab (اﻟﻌﺮب ﻟﺴﺎن), Al-Bushr{\={a}} (اﻟﺒﺸﺮى), Al-Karmil (اﻟﻜﺮﻣﻞ), Al-Dif{\={a}}ʿ (اﻟﺪﻓﺎع), and Filasṭ{\={i}}n (ﻓﻠﺴﻄﻴﻦ). We describe (i) the construction of a five-source corpus from scanned newspaper images obtained from archival collections, processed using the Google Cloud Vision OCR (GCV-OCR) API, (ii) the adaptation of KeyBERT with an AraBERT backbone for unsupervised keyphrase extraction, and (iii) a purpose-built Python visualization toolkit that produces keyword-frequency heatmaps, longitudinal trend charts, and ranked bar charts with full Arabic script rendering. Experiments across the five subcorpora show that the pipeline yields topically diverse keyphrases reflecting each newspaper{'}s editorial orientation and its distinct representation of Palestinian native perspectives{---}from pan-Arab nationalism and anti-colonial resistance to religious and communal affairs. Temporal analysis reveals event-responsive patterns that align with major historical developments, including the 1936{--}1939 Arab Revolt and the intensification of sovereignty discourse toward 1948. The pipeline, data format specifications, and visualization code are provided as supplementary material."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="barakat-barakat-2026-mining">
<titleInfo>
<title>Mining the Pre-1948 Palestinian Press: Unsupervised Keyphrase Extraction and Temporal Discourse Analysis from Five Historical Arabic Newspapers</title>
</titleInfo>
<name type="personal">
<namePart type="given">Basel</namePart>
<namePart type="family">Barakat</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nizam</namePart>
<namePart type="family">Barakat</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2nd International Workshop on Nakba Narratives as Language Resources @ LREC 2026</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mustafa</namePart>
<namePart type="family">Jarrar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mo</namePart>
<namePart type="family">El-Haj</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Amal</namePart>
<namePart type="family">Haddad</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Serin</namePart>
<namePart type="family">Atiani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shadi</namePart>
<namePart type="family">Abudalfa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Terry</namePart>
<namePart type="family">Regier</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Paul</namePart>
<namePart type="family">Rayson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khalil</namePart>
<namePart type="family">Sima’an</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Camille</namePart>
<namePart type="family">Mansour</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Palma, Mallorca (Spain)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The Palestinian Arabic-language press of the late Ottoman and British Mandate periods constitutes a rich but computationally under-explored archive for studying the evolution of political, cultural, and social discourse in pre-1948 Palestine. This paper presents an end-to-end pipeline for extracting and analyzing thematic content from five historically significant Palestinian newspapers: Lisān al-ʿArab (اﻟﻌﺮب ﻟﺴﺎن), Al-Bushrā (اﻟﺒﺸﺮى), Al-Karmil (اﻟﻜﺮﻣﻞ), Al-Difāʿ (اﻟﺪﻓﺎع), and Filasṭīn (ﻓﻠﺴﻄﻴﻦ). We describe (i) the construction of a five-source corpus from scanned newspaper images obtained from archival collections, processed using the Google Cloud Vision OCR (GCV-OCR) API, (ii) the adaptation of KeyBERT with an AraBERT backbone for unsupervised keyphrase extraction, and (iii) a purpose-built Python visualization toolkit that produces keyword-frequency heatmaps, longitudinal trend charts, and ranked bar charts with full Arabic script rendering. Experiments across the five subcorpora show that the pipeline yields topically diverse keyphrases reflecting each newspaper’s editorial orientation and its distinct representation of Palestinian native perspectives—from pan-Arab nationalism and anti-colonial resistance to religious and communal affairs. Temporal analysis reveals event-responsive patterns that align with major historical developments, including the 1936–1939 Arab Revolt and the intensification of sovereignty discourse toward 1948. The pipeline, data format specifications, and visualization code are provided as supplementary material.</abstract>
<identifier type="citekey">barakat-barakat-2026-mining</identifier>
<identifier type="doi">10.63317/3oaq8zxp9hwx</identifier>
<location>
<url>https://aclanthology.org/2026.nakbanlp-1.2/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>23</start>
<end>32</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Mining the Pre-1948 Palestinian Press: Unsupervised Keyphrase Extraction and Temporal Discourse Analysis from Five Historical Arabic Newspapers
%A Barakat, Basel
%A Barakat, Nizam
%Y Jarrar, Mustafa
%Y El-Haj, Mo
%Y Haddad, Amal
%Y Atiani, Serin
%Y Abudalfa, Shadi
%Y Regier, Terry
%Y Rayson, Paul
%Y Sima’an, Khalil
%Y Mansour, Camille
%S Proceedings of the 2nd International Workshop on Nakba Narratives as Language Resources @ LREC 2026
%D 2026
%8 May
%I ELRA Language Resources Association (ELRA)
%C Palma, Mallorca (Spain)
%F barakat-barakat-2026-mining
%X The Palestinian Arabic-language press of the late Ottoman and British Mandate periods constitutes a rich but computationally under-explored archive for studying the evolution of political, cultural, and social discourse in pre-1948 Palestine. This paper presents an end-to-end pipeline for extracting and analyzing thematic content from five historically significant Palestinian newspapers: Lisān al-ʿArab (اﻟﻌﺮب ﻟﺴﺎن), Al-Bushrā (اﻟﺒﺸﺮى), Al-Karmil (اﻟﻜﺮﻣﻞ), Al-Difāʿ (اﻟﺪﻓﺎع), and Filasṭīn (ﻓﻠﺴﻄﻴﻦ). We describe (i) the construction of a five-source corpus from scanned newspaper images obtained from archival collections, processed using the Google Cloud Vision OCR (GCV-OCR) API, (ii) the adaptation of KeyBERT with an AraBERT backbone for unsupervised keyphrase extraction, and (iii) a purpose-built Python visualization toolkit that produces keyword-frequency heatmaps, longitudinal trend charts, and ranked bar charts with full Arabic script rendering. Experiments across the five subcorpora show that the pipeline yields topically diverse keyphrases reflecting each newspaper’s editorial orientation and its distinct representation of Palestinian native perspectives—from pan-Arab nationalism and anti-colonial resistance to religious and communal affairs. Temporal analysis reveals event-responsive patterns that align with major historical developments, including the 1936–1939 Arab Revolt and the intensification of sovereignty discourse toward 1948. The pipeline, data format specifications, and visualization code are provided as supplementary material.
%R 10.63317/3oaq8zxp9hwx
%U https://aclanthology.org/2026.nakbanlp-1.2/
%U https://doi.org/10.63317/3oaq8zxp9hwx
%P 23-32
Markdown (Informal)
[Mining the Pre-1948 Palestinian Press: Unsupervised Keyphrase Extraction and Temporal Discourse Analysis from Five Historical Arabic Newspapers](https://aclanthology.org/2026.nakbanlp-1.2/) (Barakat & Barakat, NakbaNLP 2026)
ACL