Detecting deception, disinformation, and crowd manipulation on social media through machine learning, natural language processing and artificial intelligence

Recently, due to the widespread effects of “fake news”, a form of propaganda that is intentionally designed to mislead the reader, there has been a significant research effort to automate the process of detection of misinformation in social media. Although existing methods for automatic fake news detection are promising, distinguishing between true and false news is a hard task even for a human, and there is considerable scope for performance improvement. The main goal of this project is to design novel deep neural network models and architectures to detect deception, disinformation, and crowd manipulation on social networks. The project will be conducted in collaboration with researchers from Nexalogy, a company with state-of-the-art artificial intelligence for processing social media data in English, French, Russian and Korean. The aim is to deploy the developed models in the enterprise interface for augmentation of Nexalogy’s social media discovery and analysis platforms.

Faculty Supervisor:

Mark Coates

Student:

Arezou Amini

Partner:

Nexalogy

Discipline:

Engineering - computer / electrical

Sector:

Information and cultural industries

University:

McGill University