Prediction of COVID-19 tweeting: classification based on graph neural networks

Milan Petrovic, Andrea Hrelja, Ana Meštrović

Keywords: graph convolutional networks, node classification, social networks

Abstract: This paper presents the application of graph neural networks (GNNs) to the task of node classification. GNNs have been shown to be useful in various classification tasks where data and the relationships between them can be represented using graphs. This research aims to develop a classifier that can identify two possible classes of Twitter nodes: COVID and nonCOVID. COVID nodes refer to Twitter users (nodes) that post tweets related to COVID-19 and nonCOVID are users (nodes) that do not post tweets about COVID-19. For that purpose, in the first step, we implement a pipeline that enables the automatic, continuous collection of data from Twitter and network construction. In the second step, we prepare the data and train a graph convolutional networks(GCN) classifier. We compare GCN and multilayer perceptron (MLP) in terms of standard measures: precision, recall, F1 and accuracy. The results show that GCN performs better than MLP in the task of node classification.

Dual Submission: This paper was already submissed on conference Mipro (http://www.mipro.hr/)