AI Wizards at CheckThat! 2025: Enhancing Transformer-Based Embeddings with Sentiment for Subjectivity Detection in News Articles

TL;DR

This paper enhances transformer-based classifiers for subjectivity detection in news articles by integrating sentiment scores, improving performance across multiple languages and achieving top rankings in the CLEF 2025 CheckThat! challenge.

Contribution

It introduces a sentiment-augmented architecture for transformer classifiers, demonstrating significant performance improvements in multilingual subjectivity detection tasks.

Findings

Sentiment integration boosts classifier performance.

Achieved top ranking for Greek language.

Effective handling of class imbalance through threshold calibration.

Abstract

This paper presents AI Wizards' participation in the CLEF 2025 CheckThat! Lab Task 1: Subjectivity Detection in News Articles, classifying sentences as subjective/objective in monolingual, multilingual, and zero-shot settings. Training/development datasets were provided for Arabic, German, English, Italian, and Bulgarian; final evaluation included additional unseen languages (e.g., Greek, Romanian, Polish, Ukrainian) to assess generalization. Our primary strategy enhanced transformer-based classifiers by integrating sentiment scores, derived from an auxiliary model, with sentence representations, aiming to improve upon standard fine-tuning. We explored this sentiment-augmented architecture with mDeBERTaV3-base, ModernBERT-base (English), and Llama3.2-1B. To address class imbalance, prevalent across languages, we employed decision threshold calibration optimized on the development set. Our experiments show sentiment feature integration significantly boosts performance, especially subjective F1 score. This framework led to high rankings, notably 1st for Greek (Macro F1 = 0.51).