A Multi-Modal Deep Learning Model for Fake News Detection
Budget: $10 – $30 USD
In this project, we will build a multi-modal deep learning model for fake news (tweets) detection on
social media by using both textual (tweets) and visual inputs (images). This proposed model aims to
deal with the automatic detection of manipulation and misuse in Web multimedia content, which lays
the basis for a future generation of tools that could assist media professionals in the process of social
media information verification.
The problem we aim to solve is the following: "Given a tweet and the accompanying multimedia item
(image or video) from an event that has the profile to be of interest in the international news, return a
binary decision representing verification of whether the multimedia item reflects the reality of the event
in the way purported by the tweet."
social media by using both textual (tweets) and visual inputs (images). This proposed model aims to
deal with the automatic detection of manipulation and misuse in Web multimedia content, which lays
the basis for a future generation of tools that could assist media professionals in the process of social
media information verification.
The problem we aim to solve is the following: "Given a tweet and the accompanying multimedia item
(image or video) from an event that has the profile to be of interest in the international news, return a
binary decision representing verification of whether the multimedia item reflects the reality of the event
in the way purported by the tweet."