Li Xin, Lu Peixin, Hu Lianting, Wang XiaoGuang, Lu Long
School of Information Management, Wuhan University, Wuhan, China.
Multimed Tools Appl. 2022;81(14):19341-19349. doi: 10.1007/s11042-021-11065-x. Epub 2021 Jun 2.
Social media has become a popular means for people to consume and share news. However, it also enables the extensive spread of fake news, that is, news that deliberately provides false information, which has a significant negative impact on society. Especially recently, the false information about the new coronavirus disease 2019 (COVID-19) has spread like a virus around the world. The state of the Internet is forcing the world's tech giants to take unprecedented action to protect the "information health" of the public. Despite many existing fake news datasets, comprehensive and effective algorithms for detecting fake news have become one of the major obstacles. In order to address this issue, we designed a self-learning semi-supervised deep learning network by adding a confidence network layer, which made it possible to automatically return and add correct results to help the neural network to accumulate positive sample cases, thus improving the accuracy of the neural network. Experimental results indicate that our network is more accurate than the existing mainstream machine learning methods and deep learning methods.
社交媒体已成为人们获取和分享新闻的一种流行方式。然而，它也使得假新闻广泛传播，即故意提供虚假信息的新闻，这对社会产生了重大负面影响。特别是最近，关于2019年新型冠状病毒病（COVID-19）的虚假信息在全球像病毒一样传播。互联网的现状迫使全球科技巨头采取前所未有的行动来保护公众的“信息健康”。尽管现有许多假新闻数据集，但用于检测假新闻的全面有效的算法已成为主要障碍之一。为了解决这个问题，我们通过添加一个置信度网络层设计了一个自学习半监督深度学习网络，这使得能够自动返回并添加正确结果以帮助神经网络积累正样本案例，从而提高神经网络的准确性。实验结果表明，我们的网络比现有的主流机器学习方法和深度学习方法更准确。
