Twitter conversations predict the daily confirmed COVID-19 cases

TL;DR

This study demonstrates that Twitter conversations, analyzed through a sentiment-involved topic-based approach, can significantly improve COVID-19 case forecasting accuracy, providing valuable early warning signals during pandemic waves.

Contribution

Introduces a novel sentiment-involved topic-based latent variable methodology for incorporating Twitter data into COVID-19 forecasting models, validated with Australian data.

Findings

Latent social media variables Granger-cause COVID-19 cases.

Inclusion of social media variables improves forecast accuracy by ~50%.

Provides a large-scale geotagged COVID-19 Twitter dataset, MegaGeoCOV.

Abstract

As of writing this paper, COVID-19 (Coronavirus disease 2019) has spread to more than 220 countries and territories. Following the outbreak, the pandemic's seriousness has made people more active on social media, especially on the microblogging platforms such as Twitter and Weibo. The pandemic-specific discourse has remained on-trend on these platforms for months now. Previous studies have confirmed the contributions of such socially generated conversations towards situational awareness of crisis events. The early forecasts of cases are essential to authorities to estimate the requirements of resources needed to cope with the outgrowths of the virus. Therefore, this study attempts to incorporate the public discourse in the design of forecasting models particularly targeted for the steep-hill region of an ongoing wave. We propose a sentiment-involved topic-based latent variables search methodology for designing forecasting models from publicly available Twitter conversations. As a use case, we implement the proposed methodology on Australian COVID-19 daily cases and Twitter conversations generated within the country. Experimental results: (i) show the presence of latent social media variables that Granger-cause the daily COVID-19 confirmed cases, and (ii) confirm that those variables offer additional prediction capability to forecasting models. Further, the results show that the inclusion of social media variables introduces 48.83--51.38% improvements on RMSE over the baseline models. We also release the large-scale COVID-19 specific geotagged global tweets dataset, MegaGeoCOV, to the public anticipating that the geotagged data of this scale would aid in understanding the conversational dynamics of the pandemic through other spatial and temporal contexts.