Few-shot Hate Speech Detection Based on the MindSpore Framework

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Qin, Zhenkai, Wu, Dongze, Liu, Yuxin, Yang, Guifang
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913803345592320
author Qin, Zhenkai
Wu, Dongze
Liu, Yuxin
Yang, Guifang
author_facet Qin, Zhenkai
Wu, Dongze
Liu, Yuxin
Yang, Guifang
contents The proliferation of hate speech on social media poses a significant threat to online communities, requiring effective detection systems. While deep learning models have shown promise, their performance often deteriorates in few-shot or low-resource settings due to reliance on large annotated corpora. To address this, we propose MS-FSLHate, a prompt-enhanced neural framework for few-shot hate speech detection implemented on the MindSpore deep learning platform. The model integrates learnable prompt embeddings, a CNN-BiLSTM backbone with attention pooling, and synonym-based adversarial data augmentation to improve generalization. Experimental results on two benchmark datasets-HateXplain and HSOL-demonstrate that our approach outperforms competitive baselines in precision, recall, and F1-score. Additionally, the framework shows high efficiency and scalability, suggesting its suitability for deployment in resource-constrained environments. These findings highlight the potential of combining prompt-based learning with adversarial augmentation for robust and adaptable hate speech detection in few-shot scenarios.
format Preprint
id arxiv_https___arxiv_org_abs_2504_15987
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Few-shot Hate Speech Detection Based on the MindSpore Framework
Qin, Zhenkai
Wu, Dongze
Liu, Yuxin
Yang, Guifang
Computation and Language
Computers and Society
The proliferation of hate speech on social media poses a significant threat to online communities, requiring effective detection systems. While deep learning models have shown promise, their performance often deteriorates in few-shot or low-resource settings due to reliance on large annotated corpora. To address this, we propose MS-FSLHate, a prompt-enhanced neural framework for few-shot hate speech detection implemented on the MindSpore deep learning platform. The model integrates learnable prompt embeddings, a CNN-BiLSTM backbone with attention pooling, and synonym-based adversarial data augmentation to improve generalization. Experimental results on two benchmark datasets-HateXplain and HSOL-demonstrate that our approach outperforms competitive baselines in precision, recall, and F1-score. Additionally, the framework shows high efficiency and scalability, suggesting its suitability for deployment in resource-constrained environments. These findings highlight the potential of combining prompt-based learning with adversarial augmentation for robust and adaptable hate speech detection in few-shot scenarios.
title Few-shot Hate Speech Detection Based on the MindSpore Framework
topic Computation and Language
Computers and Society
url https://arxiv.org/abs/2504.15987