数据与计算发展前沿 ›› 2026, Vol. 8 ›› Issue (2): 111-122.

CSTR: 32002.14.jfdc.CN10-1649/TP.2026.02.009

doi: 10.11871/jfdc.issn.2096-742X.2026.02.009

• 技术与应用 • 上一篇    下一篇

基于多层次情感与语义特征融合的虚假新闻检测方法

安真仟(),刘为军*()   

  1. 中国人民公安大学， 侦查学院， 北京 100038
  • 收稿日期:2025-01-15 出版日期:2026-04-20 发布日期:2026-04-23
  • 通讯作者: *刘为军（E-mail: liuweijun@ppsuc.edu.cn）
  • 作者简介:安真仟，中国人民公安大学，博士研究生，主要研究方向为网络安全。
    本文中主要负责论文中模型的实现与文章的写作。
    AN Zhenqian is a Ph.D. candidate at the People’s Public Security University of China. His main research interests include cybersecurity.
    In this paper, he is mainly responsible for the implementation of the model and the writing of the article.
    E-mail: 2023111010@stu.ppsuc.edu.cn|刘为军，中国人民公安大学网络安全与法治协同创新中心教授，侦查学院学术委员会主任，博士生导师，主要研究方向为网络犯罪治理。
    本文中主要负责文章思路与写作的指导。
    LIU Weijun is a professor at the Collaborative Innovation Center for Cybersecurity and Rule of Law at the People’s Public Security University of China, Academic Committee Director of the School of Investigation, and a Ph.D. supervisor. His research interests include the governance of cybercrime.
    In this paper, he is mainly responsible for providing guidance on the overall framework and writing of the paper.
    E-mail: liuweijun@ppsuc.edu.cn
  • 基金资助:
    中国人民公安大学侦查学双一流专项(2023SYL02)

A Fake News Detection Method Based on Multi-Level Sentiment and Semantic Feature Fusion

AN Zhenqian(),LIU Weijun*()   

  1. Institute of Criminal Investigation, China People’s Public Security University, Beijing 100038, China
  • Received:2025-01-15 Online:2026-04-20 Published:2026-04-23

RichHTML

1

PDF

9

摘要：

【目的】 随着互联网的快速发展和生成式人工智能技术的迅猛进步，虚假新闻传播问题日益严峻，如何高效、准确开展虚假新闻检测成为学界关注的热点问题。传统虚假新闻检测方法主要依赖于新闻文本的语义特征，忽视了对文本其他维度特征以及评论等信息的深入挖掘。【方法】 本文提出基于BERT-SentiMHCA（Bidirectional Encoder Representations from Transformer-Sentiment Features with Multi-Head Cross Attention）的虚假新闻检测方法，在考虑新闻正文语义特征的基础上，综合考虑正文、评论的情感特征，及二者情感相似度，通过多头自注意力机制和多头交叉注意力机制实现多层次特征有效融合，融合多层次文本与情感特征以提升虚假新闻检测的准确性与鲁棒性。具体方法包括：（1）使用预训练语言模型BERT提取新闻文本的深层语义表示；（2）构建情感分类器，分别提取正文及评论的情感特征；（3）设计融合模块，通过注意力机制实现特征融合并采用神经网络分类器构建虚假新闻检测模型。【结论】 在四个公开虚假新闻数据集上的实验结果表明，本文提出的BERT-SentiMHCA模型在准确率、精确率、召回率和F1值等评价指标上，较多个主流基线模型分别实现了较为明显的性能提升。结果验证了本文方法在多层次文本特征提取方面的能力，能够显著提升虚假新闻检测的性能。

关键词: 虚假新闻检测, 情感特征, BERT, 特征融合

Abstract:

[Objective] With the rapid development of the internet and the accelerated advancement of generative artificial intelligence technologies, the spread of fake news has become increasingly severe. Detecting fake news efficiently and accurately has emerged as a critical research focus in academia. Traditional fake news detection methods primarily rely on semantic features of news texts, while neglecting in-depth exploration of features from other dimensions of the text as well as information such as user comments. [Methods] This paper proposes a fake news detection method based on BERT-SentiMHCA (Bidirectional Encoder Representations from Transformer-Sentiment Features with Multi-Head Cross Attention) model. Building on semantic features of news content, the method comprehensively integrates sentiment features of both news content and user comments, as well as their sentimen similarity. Through multi-head self-attention and multi-head cross-attention mechanisms, it achieves effective fusion of multi-level features, combining textual and emotional characteristics to enhance the accuracy and robustness of fake news detection. The specific methodology includes: (1) utilizing the pre-trained language model BERT to extract deep semantic representations of news texts; (2) constructing sentiment classifiers to extract sentiment features from both news content and comments; (3) designing a fusion module that integrates features via attention mechanisms and employs a neural network classifier to build the fake news detection model. [Conclusions] Experimental results on four public fake news datasets demonstrate that the proposed BERT-SentiMHCA model achieves notable performance improvements in terms of accuracy, precision, recall, and F1-score compared to several mainstream baseline models. These results validate the capability of the proposed method in multi-level textual feature extraction, significantly enhancing the performance of fake news detection.

Key words: fake news detection, sentiment features, BERT, feature fusion