Social media play an important role in the daily life of people around the globe and users have emerged as an active part of news distribution as well as production. The threatening pandemic of COVID-19 has been the lead subject in online discussions and posts, resulting to large amounts of related social media data, which can be utilised to reinforce the crisis management in several ways. Towards this direction, we propose a novel framework to collect, analyse, and visualise Twitter posts, which has been tailored to specifically monitor the virus spread in severely affected Italy. We present and evaluate a deep learning localisation technique that geotags posts based on the locations mentioned in their text, a face detection algorithm to estimate the number of people appearing in posted images, and a community detection approach to identify communities of Twitter users. Moreover, we propose further analysis of the collected posts to predict their reliability and to detect trending topics and events. Finally, we demonstrate an online platform that comprises an interactive map to display and filter analysed posts, utilising the outcome of the localisation technique, and a visual analytics dashboard that visualises the results of the topic, community, and event detection methodologies.
The main contribution of this paper is a novel framework that consists of a set of state-of-the-art components that analyse data mined from Twitter and a user interface that shows how all these components together support the monitoring of social media activity relevant to COVID-19 crisis in Italy.
This contribution can also be broken down to the following points:
• We perform a real-time, keyword-based collection of English and Italian tweets about the COVID-19 pandemic in Italy, in contrast to other works that focus on U.S.A or exclusively on English posts.
• We present and evaluate a deep learning-based localisation technique to automatically geotag tweets, based on locations mentioned in their text instead of the limited geo-information provided by Twitter.
• We apply additional analysis on the textual and visual content of tweets, in order to identify places at risk and cases of overcrowding, detect trending topics and influential accounts in user communities, and discover events before or during virus outbreaks.
• We demonstrate an online platform that visualises the collected and analysed tweets in multi-level aspects. An interactive map illustrates tweets, using the outcomes of our localisation technique and face detection, along with clustering and filtering capabilities. A visual analytics dashboard encapsulates the results of the tweets analysis and assists end-users to gain high-level valuable knowledge from the identification of trending topics, events and formed user communities.
The paper “A social media analytics platform visualising the spread of COVID-19 in Italy via exploitation of automatically geotagged tweets” has been published in Online Social Networks and Media journal on 30 April 2021. S. Andreadis, G. Antzoulatos, T. Mavropoulos, P. Giannakeris, G., Tzionis, N., Pantelidis, K. Ioannidis, A. Karakostas, I. Gialampoukidis, S. Vrochidis, I. Kompatsiaris from the Multimodal Data Fusion and Analytics Group (M4D) of Multimedia Knowledge and Social Media Analytics Lab (MKLab) at ITI/CERTH, propose a novel framework to collect and analyse data mined from Twitter posts, so as to monitor the COVID-19 virus spread in Italy. 7SHIELD’s face detection tool counts persons in Twitter images so as to detect crowded places, supporting the mitigation and response plans.