@inproceedings{andelic-etal-2025-makes,
title = "What Makes You {CLIC}: Detection of {C}roatian Clickbait Headlines",
author = "An{\dj}eli{\'c}, Marija and
{\v{S}}ipek, Dominik and
Majer, Laura and
{\v{S}}najder, Jan",
editor = "Piskorski, Jakub and
P{\v{r}}ib{\'a}{\v{n}}, Pavel and
Nakov, Preslav and
Yangarber, Roman and
Marcinczuk, Michal",
booktitle = "Proceedings of the 10th Workshop on Slavic Natural Language Processing (Slavic NLP 2025)",
month = jul,
year = "2025",
address = "Vienna, Austria",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.bsnlp-1.14/",
doi = "10.18653/v1/2025.bsnlp-1.14",
pages = "116--123",
ISBN = "978-1-959429-57-9",
abstract = "Online news outlets operate predominantly on an advertising-based revenue model, compelling journalists to create headlines that are often scandalous, intriguing, and provocative {--} commonly referred to as clickbait. Automatic detection of clickbait headlines is essential for preserving information quality and reader trust in digital media and requires both contextual understanding and world knowledge. For this task, particularly in less-resourced languages, it remains unclear whether fine-tuned methods or in-context learning (ICL) yield better results. In this paper, we compile clic, a novel dataset for clickbait detection of Croatian news headlines spanning a 20-year period and encompassing mainstream and fringe outlets. Furthermore, we fine-tune the BERTi{\'c} model on the task of clickbait detection for Croatian and compare its performance to LLM-based ICL methods with prompts both in Croatian and English. Finally, we analyze the linguistic properties of clickbait. We find that nearly half of the analyzed headlines contain clickbait, and that finetuned models deliver better results than general LLMs."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="andelic-etal-2025-makes">
<titleInfo>
<title>What Makes You CLIC: Detection of Croatian Clickbait Headlines</title>
</titleInfo>
<name type="personal">
<namePart type="given">Marija</namePart>
<namePart type="family">Anđelić</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dominik</namePart>
<namePart type="family">Šipek</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Laura</namePart>
<namePart type="family">Majer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Šnajder</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 10th Workshop on Slavic Natural Language Processing (Slavic NLP 2025)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jakub</namePart>
<namePart type="family">Piskorski</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pavel</namePart>
<namePart type="family">Přibáň</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Preslav</namePart>
<namePart type="family">Nakov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Roman</namePart>
<namePart type="family">Yangarber</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Michal</namePart>
<namePart type="family">Marcinczuk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Vienna, Austria</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">978-1-959429-57-9</identifier>
</relatedItem>
<abstract>Online news outlets operate predominantly on an advertising-based revenue model, compelling journalists to create headlines that are often scandalous, intriguing, and provocative – commonly referred to as clickbait. Automatic detection of clickbait headlines is essential for preserving information quality and reader trust in digital media and requires both contextual understanding and world knowledge. For this task, particularly in less-resourced languages, it remains unclear whether fine-tuned methods or in-context learning (ICL) yield better results. In this paper, we compile clic, a novel dataset for clickbait detection of Croatian news headlines spanning a 20-year period and encompassing mainstream and fringe outlets. Furthermore, we fine-tune the BERTić model on the task of clickbait detection for Croatian and compare its performance to LLM-based ICL methods with prompts both in Croatian and English. Finally, we analyze the linguistic properties of clickbait. We find that nearly half of the analyzed headlines contain clickbait, and that finetuned models deliver better results than general LLMs.</abstract>
<identifier type="citekey">andelic-etal-2025-makes</identifier>
<identifier type="doi">10.18653/v1/2025.bsnlp-1.14</identifier>
<location>
<url>https://aclanthology.org/2025.bsnlp-1.14/</url>
</location>
<part>
<date>2025-07</date>
<extent unit="page">
<start>116</start>
<end>123</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T What Makes You CLIC: Detection of Croatian Clickbait Headlines
%A Anđelić, Marija
%A Šipek, Dominik
%A Majer, Laura
%A Šnajder, Jan
%Y Piskorski, Jakub
%Y Přibáň, Pavel
%Y Nakov, Preslav
%Y Yangarber, Roman
%Y Marcinczuk, Michal
%S Proceedings of the 10th Workshop on Slavic Natural Language Processing (Slavic NLP 2025)
%D 2025
%8 July
%I Association for Computational Linguistics
%C Vienna, Austria
%@ 978-1-959429-57-9
%F andelic-etal-2025-makes
%X Online news outlets operate predominantly on an advertising-based revenue model, compelling journalists to create headlines that are often scandalous, intriguing, and provocative – commonly referred to as clickbait. Automatic detection of clickbait headlines is essential for preserving information quality and reader trust in digital media and requires both contextual understanding and world knowledge. For this task, particularly in less-resourced languages, it remains unclear whether fine-tuned methods or in-context learning (ICL) yield better results. In this paper, we compile clic, a novel dataset for clickbait detection of Croatian news headlines spanning a 20-year period and encompassing mainstream and fringe outlets. Furthermore, we fine-tune the BERTić model on the task of clickbait detection for Croatian and compare its performance to LLM-based ICL methods with prompts both in Croatian and English. Finally, we analyze the linguistic properties of clickbait. We find that nearly half of the analyzed headlines contain clickbait, and that finetuned models deliver better results than general LLMs.
%R 10.18653/v1/2025.bsnlp-1.14
%U https://aclanthology.org/2025.bsnlp-1.14/
%U https://doi.org/10.18653/v1/2025.bsnlp-1.14
%P 116-123
Markdown (Informal)
[What Makes You CLIC: Detection of Croatian Clickbait Headlines](https://aclanthology.org/2025.bsnlp-1.14/) (Anđelić et al., BSNLP 2025)
ACL