Identifying Misinformation from Website Screenshots

Can the look and the feel of a website give information about the trustworthiness of an article? In this paper, we propose to use a promising, yet neglected aspect in detecting the misinformativeness: the overall look of the domain webpage. To capture this overall look, we take screenshots of news articles served by either misinformative or trustworthy web domains and leverage a tensor decomposition based semi-supervised classification technique. The proposed approach i.e., VizFake is insensitive to a number of image transformations such as converting the image to grayscale, vectorizing the image and losing some parts of the screenshots. VizFake leverages a very small amount Figure 1: Creating a tensor-based model out of news articles' of known labels, mirroring realistic and practical scenarios, screenshots and decomposing the tensor using CP/PARAFAC into where labels (especially for known misinformative articles), latent factors and then creating a nearest neighbor graph based on are scarce and quickly become dated. The F1 score of the similarity of latent patterns and leveraging belief propagation VizFake on a dataset of 50k screenshots of news articles to propagate very few known labels throughout the graph. As illustrated, spanning more than 500 domains is roughly 85% using only the F1 score of both real and fake classes is roughly 85% using 5% of ground truth labels. Furthermore, tensor representations just 5% of known labels. Moreover, VizFake has exploratory of VizFake, obtained in an unsupervised manner, allow capabilities for unsupervised clustering of screenshots.