@inproceedings{nagiyev-etal-2026-scope,
title = "{SCOPE}: Source Credibility and Outlet Profiling Engine",
author = "Nagiyev, Ilyas and
Baisbay, Miras and
Orel, Daniil and
Nakov, Preslav",
editor = "Agrawal, Sweta and
Abad, Alberto",
booktitle = "Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing: System Demonstrations",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.emnlp-demos.36/",
pages = "359--368",
ISBN = "979-8-89176-461-3",
abstract = "We present SCOPE, a multi-agent system for profiling news media outlets with respect to bias, factuality, and credibility. Given an outlet URL, SCOPE coordinates specialized agents for article acquisition, content analysis, external evidence search, scoring, and report generation. The system follows an MBFC-style methodology while making intermediate evidence and agent outputs inspectable through a structured demonstration interface. On a benchmark of 200 media outlets, SCOPE outperforms LLM-only, article-only, search-only, and media-background-check baselines on most metrics, achieving the lowest bias and factuality MAE, perfect failed-fact-check detection, and the lowest factual error rate. These results suggest that decomposed, evidence-grounded agent workflows can support more transparent and reliable media profiling. Our code is available at https://github.com/mbaisbay/SCOPE, and a live demonstration at https://scope-demo.streamlit.app/."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="nagiyev-etal-2026-scope">
<titleInfo>
<title>SCOPE: Source Credibility and Outlet Profiling Engine</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ilyas</namePart>
<namePart type="family">Nagiyev</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Miras</namePart>
<namePart type="family">Baisbay</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daniil</namePart>
<namePart type="family">Orel</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>
<originInfo>
<dateIssued>2026-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing: System Demonstrations</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sweta</namePart>
<namePart type="family">Agrawal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alberto</namePart>
<namePart type="family">Abad</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Budapest, Hungary</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-461-3</identifier>
</relatedItem>
<abstract>We present SCOPE, a multi-agent system for profiling news media outlets with respect to bias, factuality, and credibility. Given an outlet URL, SCOPE coordinates specialized agents for article acquisition, content analysis, external evidence search, scoring, and report generation. The system follows an MBFC-style methodology while making intermediate evidence and agent outputs inspectable through a structured demonstration interface. On a benchmark of 200 media outlets, SCOPE outperforms LLM-only, article-only, search-only, and media-background-check baselines on most metrics, achieving the lowest bias and factuality MAE, perfect failed-fact-check detection, and the lowest factual error rate. These results suggest that decomposed, evidence-grounded agent workflows can support more transparent and reliable media profiling. Our code is available at https://github.com/mbaisbay/SCOPE, and a live demonstration at https://scope-demo.streamlit.app/.</abstract>
<identifier type="citekey">nagiyev-etal-2026-scope</identifier>
<location>
<url>https://aclanthology.org/2026.emnlp-demos.36/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>359</start>
<end>368</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T SCOPE: Source Credibility and Outlet Profiling Engine
%A Nagiyev, Ilyas
%A Baisbay, Miras
%A Orel, Daniil
%A Nakov, Preslav
%Y Agrawal, Sweta
%Y Abad, Alberto
%S Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing: System Demonstrations
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-461-3
%F nagiyev-etal-2026-scope
%X We present SCOPE, a multi-agent system for profiling news media outlets with respect to bias, factuality, and credibility. Given an outlet URL, SCOPE coordinates specialized agents for article acquisition, content analysis, external evidence search, scoring, and report generation. The system follows an MBFC-style methodology while making intermediate evidence and agent outputs inspectable through a structured demonstration interface. On a benchmark of 200 media outlets, SCOPE outperforms LLM-only, article-only, search-only, and media-background-check baselines on most metrics, achieving the lowest bias and factuality MAE, perfect failed-fact-check detection, and the lowest factual error rate. These results suggest that decomposed, evidence-grounded agent workflows can support more transparent and reliable media profiling. Our code is available at https://github.com/mbaisbay/SCOPE, and a live demonstration at https://scope-demo.streamlit.app/.
%U https://aclanthology.org/2026.emnlp-demos.36/
%P 359-368
Markdown (Informal)
[SCOPE: Source Credibility and Outlet Profiling Engine](https://aclanthology.org/2026.emnlp-demos.36/) (Nagiyev et al., EMNLP 2026)
ACL
- Ilyas Nagiyev, Miras Baisbay, Daniil Orel, and Preslav Nakov. 2026. SCOPE: Source Credibility and Outlet Profiling Engine. In Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing: System Demonstrations, pages 359–368, Budapest, Hungary. Association for Computational Linguistics.