The AI tool is based on state-of-the-art deep learning techniques, and incorporates emotional and psychographic features in order to detect disinformation and conspiracy theories. This tool efficiently explains its decision-making at the time of the detection of disinformation and conspiracy theories, explaining the persuasion strategies that have been employed in conspiracy messages to gain new supporters for conspiracy theories or to generate doubt in audiences.
The demo is deployed in an Azure's CPU-only free server. For a live/faster demo, please, contact with francisco.rangel@symanto.com
Derived from the demo, we developed ✒️ExplainInk: a framework to compute efficient token attribution for text classifiers: