@inproceedings{azizov-etal-2024-safari,
title = "{SAFARI}: Cross-lingual Bias and Factuality Detection in News Media and News Articles",
author = "Azizov, Dilshod and
Mujahid, Zain and
AlQuabeh, Hilal and
Nakov, Preslav and
Liang, Shangsong",
editor = "Al-Onaizan, Yaser and
Bansal, Mohit and
Chen, Yun-Nung",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2024",
month = nov,
year = "2024",
address = "Miami, Florida, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.findings-emnlp.712",
pages = "12217--12231",
abstract = "In an era where information is quickly shared across many cultural and language contexts, the neutrality and integrity of news media are essential. Ensuring that media content remains unbiased and factual is crucial for maintaining public trust. With this in mind, we introduce SAFARI (CroSs-lingual BiAs and Factuality Detection in News MediA and News ARtIcles), a novel corpus of news media and articles for predicting political bias and the factuality of reporting in a multilingual and cross-lingual setup. To the best of our knowledge, this corpus is unprecedented in its collection and introduces a dataset for political bias and factuality for three tasks: (i) media-level, (ii) article-level, and (iii) joint modeling at the article-level. At the media and article levels, we evaluate the cross-lingual ability of the models; however, in joint modeling, we evaluate on English data. Our frameworks set a new benchmark in the cross-lingual evaluation of political bias and factuality. This is achieved through the use of various Multilingual Pre-trained Language Models (MPLMs) and Large Language Models (LLMs) coupled with ensemble learning methods.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="azizov-etal-2024-safari">
<titleInfo>
<title>SAFARI: Cross-lingual Bias and Factuality Detection in News Media and News Articles</title>
</titleInfo>
<name type="personal">
<namePart type="given">Dilshod</namePart>
<namePart type="family">Azizov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zain</namePart>
<namePart type="family">Mujahid</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hilal</namePart>
<namePart type="family">AlQuabeh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Preslav</namePart>
<namePart type="family">Nakov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shangsong</namePart>
<namePart type="family">Liang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2024</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yaser</namePart>
<namePart type="family">Al-Onaizan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohit</namePart>
<namePart type="family">Bansal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yun-Nung</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Miami, Florida, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In an era where information is quickly shared across many cultural and language contexts, the neutrality and integrity of news media are essential. Ensuring that media content remains unbiased and factual is crucial for maintaining public trust. With this in mind, we introduce SAFARI (CroSs-lingual BiAs and Factuality Detection in News MediA and News ARtIcles), a novel corpus of news media and articles for predicting political bias and the factuality of reporting in a multilingual and cross-lingual setup. To the best of our knowledge, this corpus is unprecedented in its collection and introduces a dataset for political bias and factuality for three tasks: (i) media-level, (ii) article-level, and (iii) joint modeling at the article-level. At the media and article levels, we evaluate the cross-lingual ability of the models; however, in joint modeling, we evaluate on English data. Our frameworks set a new benchmark in the cross-lingual evaluation of political bias and factuality. This is achieved through the use of various Multilingual Pre-trained Language Models (MPLMs) and Large Language Models (LLMs) coupled with ensemble learning methods.</abstract>
<identifier type="citekey">azizov-etal-2024-safari</identifier>
<location>
<url>https://aclanthology.org/2024.findings-emnlp.712</url>
</location>
<part>
<date>2024-11</date>
<extent unit="page">
<start>12217</start>
<end>12231</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T SAFARI: Cross-lingual Bias and Factuality Detection in News Media and News Articles
%A Azizov, Dilshod
%A Mujahid, Zain
%A AlQuabeh, Hilal
%A Nakov, Preslav
%A Liang, Shangsong
%Y Al-Onaizan, Yaser
%Y Bansal, Mohit
%Y Chen, Yun-Nung
%S Findings of the Association for Computational Linguistics: EMNLP 2024
%D 2024
%8 November
%I Association for Computational Linguistics
%C Miami, Florida, USA
%F azizov-etal-2024-safari
%X In an era where information is quickly shared across many cultural and language contexts, the neutrality and integrity of news media are essential. Ensuring that media content remains unbiased and factual is crucial for maintaining public trust. With this in mind, we introduce SAFARI (CroSs-lingual BiAs and Factuality Detection in News MediA and News ARtIcles), a novel corpus of news media and articles for predicting political bias and the factuality of reporting in a multilingual and cross-lingual setup. To the best of our knowledge, this corpus is unprecedented in its collection and introduces a dataset for political bias and factuality for three tasks: (i) media-level, (ii) article-level, and (iii) joint modeling at the article-level. At the media and article levels, we evaluate the cross-lingual ability of the models; however, in joint modeling, we evaluate on English data. Our frameworks set a new benchmark in the cross-lingual evaluation of political bias and factuality. This is achieved through the use of various Multilingual Pre-trained Language Models (MPLMs) and Large Language Models (LLMs) coupled with ensemble learning methods.
%U https://aclanthology.org/2024.findings-emnlp.712
%P 12217-12231
Markdown (Informal)
[SAFARI: Cross-lingual Bias and Factuality Detection in News Media and News Articles](https://aclanthology.org/2024.findings-emnlp.712) (Azizov et al., Findings 2024)
ACL