tl;dr: Search a suspicious news online, retrieve images and compare if there are similar ones creating relations between news, mainly (try to) reconstruct the timeline by using metadata.
Paper: ICMEW 2015 or personal pdf
Cecilia Pasquini, Carlo Brunetta, Andrea F. Vinci, Valentina Conotter, Giulia Boato
The widespread of social networking services allows users to share and quickly spread an enormous amount of digital contents. Currently, a low level of security and trustworthiness is applied to such information, whose reliability cannot be taken for granted due to the large availability of image editing software which allow any user to easily manipulate digital contents.
This has a huge impact on the deception of users, whose opinion can be seriously influenced by altered media.
In this work, we face the challenge of verifying online news by analyzing the images related to the particular news article. Our goal is to create an empirical system which helps in verifying the consistency of visually and semantically similar images used within different news articles on the same topic.