Unsupervised Fake News Detection Based on Autoencoder

Abstract

With the development of social networks, the spread of fake news brings great negative effects to people's daily life, and even causes social panic. Fake news can be regarded as an anomaly on social networks, and autoencoder can be used as the basic unsupervised learning method. So, an unsupervised fake news detection method based on autoencoder (UFNDA) is proposed. This paper firstly considers some forms of news in social networks, integrates the text content, images, propagation, and user information of publishing news to improve the performance of fake news detection. Next, to obtain the hidden information and internal relationship between features, Bidirectional GRU(Bi-GRU) layer and Self-Attention layer are added into the autoencoder, and then reconstruct residual to detect fake news. The experimental results compared with the existence of other four methods, on two real-world datasets, show that UFNDA obtains the more positive results.

A cooperative deep learning model for fake news detection in online social networks

“…To improve this performance, the work by Han et al ( 2021 ) proposes the use of a two-stream network for fake news detection. Similarly the work by Li et al ( 2021 ) uses unsupervised fake news detection method based on auto encoder, and the work by Jiang et al ( 2021 ) proposes an ensemble method of stacking of logistic regression, decision tree, k-nearest neighbor, random forest, and support vector machine (SVM). All of these approaches achieved an accuracy of over 85%, for verification of real-time generated news.…”

A survey on outlier explanations

“…The spreading of fake news can be regarded as an anomalous behavior in social networks [ 58 , 101 ]. Fake news tends to have poor grammar, contain bad language, and refer to vague or untraceable sources.…”

“…They can also be used as input features for a fake news detection algorithm. For example, in [ 58 ], Li et al categorize the factors into four feature types: (i) text content features , such as number of positive sentiment words, whether the news contains question marks, etc. ; (ii) propagation features , such as number of comments, number of likes, and number of retweets; (iii) image feature indicating whether the image in the article is tampered; and (iv) user features , which are features related to the users who publish the news, such as account age, follower–friend ratio, number of tweets, etc.…”

English Text Recognition Deep Learning Framework to Automatically Identify Fake News

“…Content-only strategies focus on analyzing the content of the news (e.g., vocabulary, syntax) and detecting patterns through natural language processing methods. However, to produce satisfactory results, a predefined scope is required, which is difficult to achieve in the case of fake news because of its diversity [ 12 ]. Network-based approaches extract information from different networks created by users who interact with the news, such as diffusion or relationship networks.…”