In the world of public misinformation, there are many cases where the information is not false or fabricated, but rather has been manipulated using more subtle techniques such as word replacements, omissions and argument distortion. These techniques can have the effect of influencing the reader’s frame of mind towards the events reported. We currently lack the necessary tools to uncover such manipulations automatically.

In this presentation, I will show some initial work done and the direction I want to take for my ongoing research. The discussion will first cover similarity methods that are used to find related articles and sentences and highlight the differences in texts. Then the second part will present an initial screening of linguistic signals that can expose the underlying media framing, such as word choices that try to convey causality, importance and judgements.

Watch the webcast replay >>