【摘要】 社交媒体改变了人们获取信息的方式，但也助长了错误信息在网络上的产生和传播。如何准确且快速地检测出社交媒体上的错误信息以净化网络环境，是一个重要的研究议题。本文从信息生态理论出发，分别从内容、用户和传播三个角度来阐述当前错误信息检测所关注的问题以及对应的检测方法，对近年来国内外的相关研究成果进行了系统梳理。现有的检测方法已经利用深度学习等技术取得了较好的检测结果。但是，由于错误信息爆发初期相关数据较少，有关早期检测的研究尚不多见；能够实现有效迁移和预训练的大规模基准数据集仍有待构建；从用户入手的信息挖掘有待进一步深入研究。更多还原

【Abstract】 Social media has dramatically improved the efficiency of information access, but it has also contributed to the generation and dissemination of misinformation on the Internet. The accurate and quick detection of misinformation to improve the online information environment is an important issue. Inspired by the Information Ecology Theory, this paper expounds on the current problems and relevant detection methods of misinformation from the three perspectives of content,users, and dissemination. Existing detection methods have achieved state-of-the-art results by deep learning methods. However, because of the lack of relevant data in the early stages, studies on the early detection of misinformation are still rare.Additionally, large-scale benchmark datasets for transfer learning and pre-training tasks are yet to be constructed. Moreover, information mining from users needs to be further evaluated.更多还原