Work

OZemi at SemEval-2026 Task 9: A Cross-Lingual Approach to Online Text Polarization Classification Using Multilingual Models and Adaptive Loss Formulation

Year: 2026

Type: conference-paper

Abstract: We propose a unified multilingual approach that addresses multiple languages and subtasks efficiently.Our system combines multilingual models with data-level techniques and a classweighted cross-entropy loss to mitigate data imbalance across languages, subtasks, and categories.Results show consistent performance across languages, achieving macro F1 scores above 70% in most languages for Subtask 1, with our highest rank for Persian (1st out of 44).These results suggest that the proposed framework provides a flexible foundation for multilingual and multi-task polarization analysis.

Source: International Workshop on Semantic Evaluation (SemEval)

DOI: 10.18653/v1/2026.semeval-1.27

Authors: Hidetsune Takahashi, Eleale Nusi Tee, Aika Yu, Ruri Furukawa, Sooeun Kim, Shuta Niinomi, Dingyu Zhang, Emily Ohman

Institution: Waseda University

Language: English

Topic: Sentiment Analysis and Opinion Mining

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: hybrid

OpenAlex ID: W7166828320

FWCI:

Cites:

Cited by:

Related to: 10