Transformer-Based Model for Multilingual Hope Speech Detection

TL;DR

This paper evaluates transformer-based models, RoBERTa and XLM-RoBERTa, for multilingual hope speech detection in English and German, demonstrating their effectiveness in improving NLP task performance.

Contribution

It compares the performance of monolingual and multilingual transformer models for hope speech detection across English and German languages.

Findings

RoBERTa achieved 0.818 F1-score for English

XLM-RoBERTa achieved 0.786 F1-score for German

Transformer models significantly enhance hope speech detection performance

Abstract

This paper describes a system that has been submitted to the "PolyHope-M" at RANLP2025. In this work various transformers have been implemented and evaluated for hope speech detection for English and Germany. RoBERTa has been implemented for English, while the multilingual model XLM-RoBERTa has been implemented for both English and German languages. The proposed system using RoBERTa reported a weighted f1-score of 0.818 and an accuracy of 81.8% for English. On the other hand, XLM-RoBERTa achieved a weighted f1-score of 0.786 and an accuracy of 78.5%. These results reflects the importance of improvement of pre-trained large language models and how these models enhancing the performance of different natural language processing tasks.