In-house research – Christophe Bruchansky – Toronto, April 2017
Political footprints are vector-based representations of a political discourse in which each vector represents a word. They are computed using machine learning technologies, which allows for more independent political analysis. They can be used to compare value systems that underlie any public discourse.Why doing this?
The media and public’s attention on quick-to-understand and ready-made political postures, without much time given on underlying political value systems.
Root cause that this project is addressing
The relative objectivity of polls and social media trends makes them easier to comment than political discourses themselves. Commenting political ideas might be seen as too dangerous or hard to justify and is often left to journalists with a partisan agenda.
How is this project aiming to tackle the issue?
It is hoped that political footprints could help researchers and journalists in their effort to conduct more objective political discourse analysis.
How is this project avoiding to impose any personal view?
By making public the method being used, by encouraging independent contributions, and by eliciting technical, cultural, and philosophical assumptions being made to obtain the results.