An Explainable DistilBERT-BiLSTM-Attention Framework for Binary and Multi-Class Hate Speech Detection

arXiv cs.CL Papers
hate-speech-detection explainable-ai distilbert bilstm attention-mechanism text-classification

Summary

This paper proposes an explainable hate speech detection framework integrating DistilBERT embeddings, BiLSTM, and an attention mechanism, achieving high F1-scores on benchmark datasets for both binary and multi-class classification.

arXiv:2609.28703v1 Announce Type: new Abstract: Hate speech on social media poses serious risks to social harmony, mental well-being, and public safety, making its timely and accurate detection essential for content moderation systems. Most existing studies focus on binary classification, evaluated their frameworks on a single dataset, and provide limited insight into how decisions are made, which limits their real-world applicability. In addition, limited work is done on the explainability of their predictive inference. To address these challenges, this study proposes a multilevel and explainable hate speech detection framework. The proposed model integrates DistilBERT (Distilled Bidirectional Encoder Representations from Transformers) embeddings with a Bi-LSTM (Bidirectional Long Short-Term Memory) model, and an attention mechanism to capture both contextual meaning and sequential dependencies in text. To enhance trust and transparency, LIME (Local Interpretable Model-agnostic Explanations) is employed to explain model predictions by highlighting influential textual features. The framework is evaluated on two benchmark datasets using both binary and multi-class classification to examine robustness and generalization. In addition, an ablation study is presented to highlight the significance of various components of proposed framework. For binary classification, the proposed model achieves F1-scores of 96.78% on the Davidson dataset and 99.53% on the SMHS dataset. In the multi-class setting, it attains F1-scores of 97.00% and 94.99% on the Davidson and SMHS datasets, respectively, outperforming existing baseline approaches. The results demonstrate that multilevel evaluation improves the reliability that the proposed framework effectively balances performance and efficiency. This makes the framework suitable for practical hate speech moderation systems that require accurate, generalizable, and explainable decisions.
Original Article
View Cached Full Text

Cached at: 09/25/26, 09:14 AM 

# An Explainable DistilBERT-BiLSTM-Attention Framework for Binary and Multi-Class Hate Speech Detection
Source: [https://arxiv.org/abs/2609.28703](https://arxiv.org/abs/2609.28703)
[View PDF](https://arxiv.org/pdf/2609.28703)

> Abstract:Hate speech on social media poses serious risks to social harmony, mental well\-being, and public safety, making its timely and accurate detection essential for content moderation systems\. Most existing studies focus on binary classification, evaluated their frameworks on a single dataset, and provide limited insight into how decisions are made, which limits their real\-world applicability\. In addition, limited work is done on the explainability of their predictive inference\. To address these challenges, this study proposes a multilevel and explainable hate speech detection framework\. The proposed model integrates DistilBERT \(Distilled Bidirectional Encoder Representations from Transformers\) embeddings with a Bi\-LSTM \(Bidirectional Long Short\-Term Memory\) model, and an attention mechanism to capture both contextual meaning and sequential dependencies in text\. To enhance trust and transparency, LIME \(Local Interpretable Model\-agnostic Explanations\) is employed to explain model predictions by highlighting influential textual features\. The framework is evaluated on two benchmark datasets using both binary and multi\-class classification to examine robustness and generalization\. In addition, an ablation study is presented to highlight the significance of various components of proposed framework\. For binary classification, the proposed model achieves F1\-scores of 96\.78% on the Davidson dataset and 99\.53% on the SMHS dataset\. In the multi\-class setting, it attains F1\-scores of 97\.00% and 94\.99% on the Davidson and SMHS datasets, respectively, outperforming existing baseline approaches\. The results demonstrate that multilevel evaluation improves the reliability that the proposed framework effectively balances performance and efficiency\. This makes the framework suitable for practical hate speech moderation systems that require accurate, generalizable, and explainable decisions\.

## Submission history

From: Muhammad Shahid Iqbal Malik Dr\. \[[view email](https://arxiv.org/show-email/b543df37/2609.28703)\] **\[v1\]**Wed, 23 Sep 2026 18:39:07 UTC \(808 KB\)

Similar Articles

Applied Explainability for Large Language Models: A Comparative Study

arXiv cs.CL

A comparative study evaluating three explainability techniques (Integrated Gradients, Attention Rollout, SHAP) on fine-tuned DistilBERT for sentiment classification, highlighting trade-offs between gradient-based, attention-based, and model-agnostic approaches for LLM interpretability.