The analysis of polarized content on social networks is crucial for understanding public discourse; however, research on low-resource languages such as Urdu remains limited. In this work, we address two complementary subtasks of polarization analysis in Urdu social media text. First, we formulate polarization classification across multiple social dimensions as a multi-label task, including political, religious, racial/ethnic, gender/sexual, and other. We fine-tune XLM-RoBERTa for multi-label classification with language-specific preprocessing, duplicate filtering, and data augmentation to handle class imbalance. The proposed model achieves a Macro F1-score of 0.758 for social-dimension polarization classification.Second, we perform polarization manifestation identification, focusing on how polarization is expressed in text through six manifestations: stereotype, vilification, dehumanization, extreme language, lack of empathy, and invalidation. Using the same transformer-based framework with imbalance-aware training, our system achieves a Macro F1-score of 0.72 on the official test set. These results demonstrate the effectiveness of multilingual transformer models for multi-dimensional polarization analysis in low-resource Urdu text.

This paper addresses polarization detection in Urdu, a low-resource language characterized by complex morphology and insufficient annotated data. We formulate the task as a binary classification problem of social media posts into polarized and non-polarized categories. Our approach is based on Urdu-BERT, a language-specific transformer model combined with language-specific preprocessing, duplicate removal, and data augmentation to mitigate class imbalance and improve generalization. Experimental results show that the fine-tuned Urdu-BERT outperforms TF-IDF-based lexical machine learning baselines and achieves strong performance relative to multilingual transformer baselines. The findings indicate that language-specific pretrained transformers, when combined with appropriate preprocessing and augmentation strategies, provide an effective and generalizable framework for low-resource Urdu polarization detection.