GHaLIB: A Multilingual Framework for Hope Speech Detection in Low-Resource Languages

TL;DR

This paper introduces GHaLIB, a multilingual framework leveraging pretrained transformer models to effectively detect hope speech in low-resource languages like Urdu, demonstrating high accuracy and broad applicability across languages.

Contribution

It presents a novel multilingual hope speech detection framework using pretrained transformers tailored for low-resource languages, with strong benchmark results.

Findings

Achieved 95.2% F1-score for Urdu binary classification.

Attained 65.2% F1-score for Urdu multi-class classification.

Demonstrated effectiveness of multilingual models in low-resource language settings.

Abstract

Hope speech has been relatively underrepresented in Natural Language Processing (NLP). Current studies are largely focused on English, which has resulted in a lack of resources for low-resource languages such as Urdu. As a result, the creation of tools that facilitate positive online communication remains limited. Although transformer-based architectures have proven to be effective in detecting hate and offensive speech, little has been done to apply them to hope speech or, more generally, to test them across a variety of linguistic settings. This paper presents a multilingual framework for hope speech detection with a focus on Urdu. Using pretrained transformer models such as XLM-RoBERTa, mBERT, EuroBERT, and UrduBERT, we apply simple preprocessing and train classifiers for improved results. Evaluations on the PolyHope-M 2025 benchmark demonstrate strong performance, achieving F1-scores of 95.2% for Urdu binary classification and 65.2% for Urdu multi-class classification, with similarly competitive results in Spanish, German, and English. These results highlight the possibility of implementing existing multilingual models in low-resource environments, thus making it easier to identify hope speech and helping to build a more constructive digital discourse.