@inproceedings{albaqawi-etal-2026-llm,
title = "{LLM}-Based Financial Sentiment Analysis in {A}rabic: Evidence from Saudi Markets",
author = "Albaqawi, Mona H. and
Albalkhi, Eman M. and
Albaiti, Joud A. and
Lopedoto, Enrico",
editor = "Al-Khalifa, Hend and
El-Haj, Mo and
Ezzini, Saad",
booktitle = "The 7th Workshop on Open-Source {A}rabic Corpora and Processing Tools ({OSACT}7) with 5 Shared Tasks",
month = may,
year = "2026",
address = "Palma, Mallorca (Spain)",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.osact-1.2/",
doi = "10.63317/3hsd9iyq472z",
pages = "14--24",
abstract = "Investor sentiment significantly influences financial markets, yet Arabic financial sentiment analysis remains limited by linguistic complexity and scarce domain-specific resources. This paper presents an LLM-based framework for large-scale Arabic financial sentiment analysis tailored to the Saudi market. We construct an 84K-sample Arabic Financial Sentiment Corpus integrating official financial news and social media data. The proposed pipeline includes preprocessing, deduplication, entity linking, conditional summarization, and five-class sentiment labeling using a multi-model consensus strategy to enhance reliability. We benchmark multiple large language models against traditional lexicon-based and fine-tuned transformer baselines. GPT-5 achieves the strongest class-balanced performance (Macro-F1 = 0.829), substantially outperforming conventional approaches. For summarization, Allam demonstrates the best trade-off between quality, hallucination control, and cost efficiency. Additional analyses examine cost{--}quality trade-offs and the impact of summarization on sentiment consistency. The results establish new benchmarks for Arabic financial sentiment classification and demonstrate the effectiveness of scalable LLM-based pipelines for domain-specific Arabic NLP."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="albaqawi-etal-2026-llm">
<titleInfo>
<title>LLM-Based Financial Sentiment Analysis in Arabic: Evidence from Saudi Markets</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mona</namePart>
<namePart type="given">H</namePart>
<namePart type="family">Albaqawi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eman</namePart>
<namePart type="given">M</namePart>
<namePart type="family">Albalkhi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joud</namePart>
<namePart type="given">A</namePart>
<namePart type="family">Albaiti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Enrico</namePart>
<namePart type="family">Lopedoto</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>The 7th Workshop on Open-Source Arabic Corpora and Processing Tools (OSACT7) with 5 Shared Tasks</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hend</namePart>
<namePart type="family">Al-Khalifa</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">Saad</namePart>
<namePart type="family">Ezzini</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Palma, Mallorca (Spain)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Investor sentiment significantly influences financial markets, yet Arabic financial sentiment analysis remains limited by linguistic complexity and scarce domain-specific resources. This paper presents an LLM-based framework for large-scale Arabic financial sentiment analysis tailored to the Saudi market. We construct an 84K-sample Arabic Financial Sentiment Corpus integrating official financial news and social media data. The proposed pipeline includes preprocessing, deduplication, entity linking, conditional summarization, and five-class sentiment labeling using a multi-model consensus strategy to enhance reliability. We benchmark multiple large language models against traditional lexicon-based and fine-tuned transformer baselines. GPT-5 achieves the strongest class-balanced performance (Macro-F1 = 0.829), substantially outperforming conventional approaches. For summarization, Allam demonstrates the best trade-off between quality, hallucination control, and cost efficiency. Additional analyses examine cost–quality trade-offs and the impact of summarization on sentiment consistency. The results establish new benchmarks for Arabic financial sentiment classification and demonstrate the effectiveness of scalable LLM-based pipelines for domain-specific Arabic NLP.</abstract>
<identifier type="citekey">albaqawi-etal-2026-llm</identifier>
<identifier type="doi">10.63317/3hsd9iyq472z</identifier>
<location>
<url>https://aclanthology.org/2026.osact-1.2/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>14</start>
<end>24</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T LLM-Based Financial Sentiment Analysis in Arabic: Evidence from Saudi Markets
%A Albaqawi, Mona H.
%A Albalkhi, Eman M.
%A Albaiti, Joud A.
%A Lopedoto, Enrico
%Y Al-Khalifa, Hend
%Y El-Haj, Mo
%Y Ezzini, Saad
%S The 7th Workshop on Open-Source Arabic Corpora and Processing Tools (OSACT7) with 5 Shared Tasks
%D 2026
%8 May
%I Association for Computational Linguistics
%C Palma, Mallorca (Spain)
%F albaqawi-etal-2026-llm
%X Investor sentiment significantly influences financial markets, yet Arabic financial sentiment analysis remains limited by linguistic complexity and scarce domain-specific resources. This paper presents an LLM-based framework for large-scale Arabic financial sentiment analysis tailored to the Saudi market. We construct an 84K-sample Arabic Financial Sentiment Corpus integrating official financial news and social media data. The proposed pipeline includes preprocessing, deduplication, entity linking, conditional summarization, and five-class sentiment labeling using a multi-model consensus strategy to enhance reliability. We benchmark multiple large language models against traditional lexicon-based and fine-tuned transformer baselines. GPT-5 achieves the strongest class-balanced performance (Macro-F1 = 0.829), substantially outperforming conventional approaches. For summarization, Allam demonstrates the best trade-off between quality, hallucination control, and cost efficiency. Additional analyses examine cost–quality trade-offs and the impact of summarization on sentiment consistency. The results establish new benchmarks for Arabic financial sentiment classification and demonstrate the effectiveness of scalable LLM-based pipelines for domain-specific Arabic NLP.
%R 10.63317/3hsd9iyq472z
%U https://aclanthology.org/2026.osact-1.2/
%U https://doi.org/10.63317/3hsd9iyq472z
%P 14-24
Markdown (Informal)
[LLM-Based Financial Sentiment Analysis in Arabic: Evidence from Saudi Markets](https://aclanthology.org/2026.osact-1.2/) (Albaqawi et al., OSACT 2026)
ACL