Scholarlink

<p>In recent years, deep learning methods have successfully addressed many fake news issues. Investing in fake news detection has become essential, especially for individuals and managers, as each new protection technique is quickly circumvented to target new victims. This study leverages several factors to detect and counter fake content. It uses extended Bidirectional Encoder Representations from Transformers (BERT), with a Natural Language Processing (NLP) tool to analyze text context, as well as a hybrid bidirectional CNN-BLSTM model, particularly suited to analyzing temporal sequences, to identify fabricated information. By integrating context, this model aims to improve detection accuracy. The performance of this approach was evaluated using separate datasets, demonstrating that the proposed model–a context-aware combination of CNN and BLSTM–outperforms other existing approaches.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Avoiding, detecting & fighting false content via educational awareness, in sustainability

  • 期刊论文

  • 发表日期：

    2026年1月27日

查看全文
  • Zair Bouzidi,
  • Abdelmalek Boudries

摘要

In recent years, deep learning methods have successfully addressed many fake news issues. Investing in fake news detection has become essential, especially for individuals and managers, as each new protection technique is quickly circumvented to target new victims. This study leverages several factors to detect and counter fake content. It uses extended Bidirectional Encoder Representations from Transformers (BERT), with a Natural Language Processing (NLP) tool to analyze text context, as well as a hybrid bidirectional CNN-BLSTM model, particularly suited to analyzing temporal sequences, to identify fabricated information. By integrating context, this model aims to improve detection accuracy. The performance of this approach was evaluated using separate datasets, demonstrating that the proposed model–a context-aware combination of CNN and BLSTM–outperforms other existing approaches.