Co-Move: COVID-19 and Inter-Region Human Mobility Analysis and Prediction

Abstract

Humans relocate for a variety of reasons, including employment, study, tourism, family, and health. However, in COVID-19, the government imposed restrictions such as lockdowns, travel bans, and quarantine regulations, preventing many people from traveling for work, study, or leisure; thus, human mobility exhibits distinct patterns than ordinary movements. In this article, we analyze the effect of COVID-19 on interregion human mobility using curated Twitter data and propose a framework named Co-Move for human mobility prediction. There were three challenges in predicting mobility: 1) heterogenous data; 2) short and long-term periodic patterns; and 3) complex intercorrelation. To address these challenges, the framework comprises parallel multiscale convolution and long short-term memory components. Extensive experiments on real-life mobility datasets show the mean square error (MSE) of 0.0179, RMSE of 0.129, mean absolute error (MAE) of 0.1075, and outperform baseline models.