[2510.17018] CoGate-LSTM: Prototype-Guided Feature-Space Gating for Mitigating Gradient Dilution in Imbalanced Toxic Comment Classification

Computer Science > Computation and Language arXiv:2510.17018 (cs) [Submitted on 19 Oct 2025 (v1), last revised 7 Apr 2026 (this version, v2)] Title:CoGate-LSTM: Prototype-Guided Feature-Space Gating for Mitigating Gradient Dilution in Imbalanced Toxic Comment Classification Authors:Noor Islam S. Mohammad View a PDF of the paper titled CoGate-LSTM: Prototype-Guided Feature-Space Gating for Mitigating Gradient Dilution in Imbalanced Toxic Comment Classification, by Noor Islam S. Mohammad View PDF HTML (experimental) Abstract:Toxic text classification for online moderation remains challenging under extreme class imbalance, where rare but high-risk labels such as threat and severe_toxic are consistently underdetected by conventional models. We propose CoGate-LSTM, a parameter-efficient recurrent architecture built around a novel cosine-similarity feature gating mechanism that adaptively rescales token embeddings by their directional similarity to a learned toxicity prototype. Unlike token-position attention, the gate emphasizes feature directions most informative for minority toxic classes. The model combines frozen multi-source embeddings (GloVe, FastText, and BERT-CLS), a character-level BiLSTM, embedding-space SMOTE, and weighted focal loss. On the Jigsaw Toxic Comment benchmark, CoGate-LSTM achieves 0.881 macro-F1 (95% CI: [0.873, 0.889]) and 96.0% accuracy, outperforming fine-tuned BERT by 6.9 macro-F1 points (p < 0.001) and XGBoost by 4.7, while using only 7.3M parameter...