DataBees at SemEval-2026 Task 9: Detecting Multilingual, Multicultural and Multievent Online Polarization
Year: 2026
Type: conference-paper
Abstract: This paper describes our submission to SemEval-2026 Task 9, Subtask 1: Multilingual Text Classification Challenge -Polarization Detection.Our focus is on how classical and transformer-based models compare when applied to multilingual polarization detection.We aim to understand where each type tends to do well and where it breaks down, particularly once you move from high-resource to low-resource settings.Our experimental setup evaluates classical machine learning models (TFIDF with Naive Bayes, Logistic Regression, and Linear SVM) alongside languagespecific transformer models across multiple languages.For Arabic, Bengali, German, Italian, and Spanish, we leveraged both multilingual and monolingual pre-trained transformers such as mBERT, XLM-R, AraBERTv2, BanglaBERT, and BETO.We compare individual classical and transformer-based models to identify which modeling choices work best for each language.Our results varied substantially across languages.We achieved our best leaderboard rankings in Bengali (6th out of 48 teams) and Italian (6th out of 43 teams), while performance was lower in Arabic (33rd out of 44), German (41st out of 44), and Spanish (46th out of 48).The study highlights the value of comparing classical and transformer-based approaches for multilingual polarization detection and identifies language-specific challenges for future improvement.
Institution: Sri Sivasubramaniya Nadar College of Engineering
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: hybrid
OpenAlex ID: W7166831003