Classifying COVID-19 Disinformation on Twitter using a Convolutional Neural Network

Disinformation regarding COVID-19 is spreading rapidly on social media platforms and can cause undesirable consequences for people who rely on such content. To combat disinformation, several platform providers have implemented intelligent systems to detect disinformation and provide measurements that apprise users of the quality of information being disseminated on social media platforms. For this purpose, intelligent systems employing deep learning approaches are often applied, hence, their effectivity requires closer analysis. The study begins with a thorough literature review regarding the concept of disinformation and its classification. This paper models and evaluates a disinformation detector that uses a convolutional neural network to classify samples of social media content. The evaluation of the proposed deep learning model showed that it performed well overall in discriminating the fake-labelled tweets from the real-labelled tweets; the model yielded an accuracy score of 97.2%, a precision score of 95.7% and a recall score of 99.8%. Consequently, the paper contributes an effective disinformation detector, which can be used as a tool to combat the substantial volume of disinformation scattered throughout social media platforms. A more standardised feature extraction for disinformation cases should be the subject of subsequent research.