Not All Pretraining are Created Equal: Threshold Tuning and Class Weighting for Imbalanced Polarization Tasks in Low-Resource Settings
Not on the map. Why?
Abstract (arXiv)
This paper describes my submission to the Polarization Shared Task at SemEval-2025, which addresses polarization detection and classification in social media text. I develop Transformer-based systems for English and Swahili across three subtasks: binary polarization detection, multi-label target type classification, and multi-label manifestation identification. The approach leverages multilingual and African language-specialized models (mDeBERTa-v3-base, SwahBERT, AfriBERTa-large), class-weighted loss functions, iterative stratified data splitting, and per-label threshold tuning to handle severe class imbalance. The best configuration, mDeBERTa-v3-base, achieves 0.8032 macro-F1 on validation for binary detection, with competitive performance on multi-label tasks (up to 0.556 macro-F1). Error analysis reveals persistent challenges with implicit polarization, code-switching, and distinguishing heated political discourse from genuine polarization.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 16 of its 30 references that are in the map. First posted on arXiv 8 Mar 2026.
Builds on
16 of 30 references.
References · 16
- 2017Attention Is All You Needcited by 59,932
- 2020Language Models are Few-Shot Learnerscited by 32,199
- 2015Rethinking the Inception Architecture for Computer Visioncited by 5,451
- 2019DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lightercited by 4,243
- 2019Unsupervised Cross-lingual Representation Learning at Scalecited by 3,907
- 2021SimCSE: Simple Contrastive Learning of Sentence Embeddingscited by 2,168
- 2020DeBERTa: Decoding-enhanced BERT with Disentangled Attentioncited by 2,157
- 2015Improving Neural Machine Translation Models with Monolingual Datacited by 784
- 2019How multilingual is Multilingual BERT?cited by 642
- 2017A systematic study of the class imbalance problem in convolutional neural networkscited by 510
- 2020MAD-X: An Adapter-Based Framework for Multi-Task Cross-Lingual Transfercited by 443
- 2020HateBERT: Retraining BERT for Abusive Language Detection in Englishcited by 206
4 more
- 2022Adapting Pre-trained Language Models to African Languages via Multilingual Adaptive Fine-Tuningcited by 149
- 2020Directions in Abusive Language Training Data: Garbage In, Garbage Outcited by 139
- 2019Multilingual and Multi-Aspect Hate Speech Analysiscited by 133
- 2017A Network Perspective on Stratification of Multi-Label Datacited by 37
Built on by
Not cited yet.