@inproceedings{maggini-etal-2026-ihpp,
title = "{IHPP}: A Paragraph-Level Dataset for Investigating the Pragmatics of Hyperpartisan {I}talian News",
author = {Maggini, Michele Joshua and
Bassi, Davide and
Valente, Angelo and
Dias, Ga{\"e}l and
Gamallo, Pablo},
editor = "Piperidis, Stelios and
Bel, N{\'u}ria and
van den Heuvel, Henk and
Ide, Nancy and
Krek, Simon and
Toral, Antonio",
booktitle = "Proceedings of the Fifteenth Language Resources and Evaluation Conference",
month = may,
year = "2026",
address = "Palma de Mallorca, Spain",
publisher = "ELRA Language Resource Association",
url = "https://aclanthology.org/2026.lrec-1.157/",
doi = "10.63317/2sabeivqu9dt",
pages = "1998--2011",
abstract = "This study investigates the linguistic composition of hyperpartisan paragraphs in Italian news on climate change, Ukraine war, and immigration by publicly disclosing the dataset to ensure reproducibility. We introduce a new corpus, \textbf{IHPP}, of 356 articles, for a total of 4,861 paragraphs annotated for hyperpartisan news detection at the paragraph level and enriched with span-level annotations of six semantic-pragmatic linguistic traits: \textit{figurative speech}, \textit{irony/sarcasm}, \textit{epithet}, as well as \textit{hyperbolic} and \textit{loaded language}. We hypothesized that these traits, while violating Gricean maxims, are key mechanisms of hyperpartisan rhetoric. To test this, we fine-tuned a set of mono- and multilingual BERT models for hyperpartisan detection and evaluated their incorporation in the embedding space. Then, we applied explainable techniques, e.g. Integrated Gradients and SHAP to analyze how models allocate attribution to normal and linguistic-trait tokens. Our result show that loaded language is the most discriminative trait. The dataset is released: \url{https://github.com/MichJoM/IHPP-Climate}."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="maggini-etal-2026-ihpp">
<titleInfo>
<title>IHPP: A Paragraph-Level Dataset for Investigating the Pragmatics of Hyperpartisan Italian News</title>
</titleInfo>
<name type="personal">
<namePart type="given">Michele</namePart>
<namePart type="given">Joshua</namePart>
<namePart type="family">Maggini</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Davide</namePart>
<namePart type="family">Bassi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Angelo</namePart>
<namePart type="family">Valente</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gaël</namePart>
<namePart type="family">Dias</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pablo</namePart>
<namePart type="family">Gamallo</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 Fifteenth Language Resources and Evaluation Conference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Núria</namePart>
<namePart type="family">Bel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Henk</namePart>
<namePart type="family">van den Heuvel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nancy</namePart>
<namePart type="family">Ide</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Simon</namePart>
<namePart type="family">Krek</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Antonio</namePart>
<namePart type="family">Toral</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA Language Resource Association</publisher>
<place>
<placeTerm type="text">Palma de Mallorca, Spain</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This study investigates the linguistic composition of hyperpartisan paragraphs in Italian news on climate change, Ukraine war, and immigration by publicly disclosing the dataset to ensure reproducibility. We introduce a new corpus, IHPP, of 356 articles, for a total of 4,861 paragraphs annotated for hyperpartisan news detection at the paragraph level and enriched with span-level annotations of six semantic-pragmatic linguistic traits: figurative speech, irony/sarcasm, epithet, as well as hyperbolic and loaded language. We hypothesized that these traits, while violating Gricean maxims, are key mechanisms of hyperpartisan rhetoric. To test this, we fine-tuned a set of mono- and multilingual BERT models for hyperpartisan detection and evaluated their incorporation in the embedding space. Then, we applied explainable techniques, e.g. Integrated Gradients and SHAP to analyze how models allocate attribution to normal and linguistic-trait tokens. Our result show that loaded language is the most discriminative trait. The dataset is released: https://github.com/MichJoM/IHPP-Climate.</abstract>
<identifier type="citekey">maggini-etal-2026-ihpp</identifier>
<identifier type="doi">10.63317/2sabeivqu9dt</identifier>
<location>
<url>https://aclanthology.org/2026.lrec-1.157/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>1998</start>
<end>2011</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T IHPP: A Paragraph-Level Dataset for Investigating the Pragmatics of Hyperpartisan Italian News
%A Maggini, Michele Joshua
%A Bassi, Davide
%A Valente, Angelo
%A Dias, Gaël
%A Gamallo, Pablo
%Y Piperidis, Stelios
%Y Bel, Núria
%Y van den Heuvel, Henk
%Y Ide, Nancy
%Y Krek, Simon
%Y Toral, Antonio
%S Proceedings of the Fifteenth Language Resources and Evaluation Conference
%D 2026
%8 May
%I ELRA Language Resource Association
%C Palma de Mallorca, Spain
%F maggini-etal-2026-ihpp
%X This study investigates the linguistic composition of hyperpartisan paragraphs in Italian news on climate change, Ukraine war, and immigration by publicly disclosing the dataset to ensure reproducibility. We introduce a new corpus, IHPP, of 356 articles, for a total of 4,861 paragraphs annotated for hyperpartisan news detection at the paragraph level and enriched with span-level annotations of six semantic-pragmatic linguistic traits: figurative speech, irony/sarcasm, epithet, as well as hyperbolic and loaded language. We hypothesized that these traits, while violating Gricean maxims, are key mechanisms of hyperpartisan rhetoric. To test this, we fine-tuned a set of mono- and multilingual BERT models for hyperpartisan detection and evaluated their incorporation in the embedding space. Then, we applied explainable techniques, e.g. Integrated Gradients and SHAP to analyze how models allocate attribution to normal and linguistic-trait tokens. Our result show that loaded language is the most discriminative trait. The dataset is released: https://github.com/MichJoM/IHPP-Climate.
%R 10.63317/2sabeivqu9dt
%U https://aclanthology.org/2026.lrec-1.157/
%U https://doi.org/10.63317/2sabeivqu9dt
%P 1998-2011
Markdown (Informal)
[IHPP: A Paragraph-Level Dataset for Investigating the Pragmatics of Hyperpartisan Italian News](https://aclanthology.org/2026.lrec-1.157/) (Maggini et al., LREC 2026)
ACL