Event-driven timeseries analysis and the comparison of public reactions\n on COVID-19

The rapid spread of COVID-19 has already affected human lives throughout the\nglobe. Governments of different countries have taken various measures, but how\nthey affected people lives is not clear. In this study, a rule-based and a\nmachine-learning based models are applied to answer the above question using\npublic tweets from Japan, USA, UK, and Australia. Two polarity timeseries\n(meanPol and pnRatio) and two events, namely "lockdown or emergency (LED)" and\n"the economic support package (ESP)", are considered in this study. Statistical\ntesting on the sub-series around LED and ESP events showed their positive\nimpacts to the people of (UK and Australia) and (USA and UK), respectively\nunlike Japanese people that showed opposite effects. Manual validation with the\nrelevant tweets showed an agreement with the statistical results. A case study\nwith Japanese tweets using supervised logistic regression classifies tweets\ninto heath-worry, economy-worry and other classes with 83.11% accuracy.\nPredicted tweets around events re-confirm the statistical outcomes.\n