The Road to Recovery: sensing public opinion towards reopening measures with social media data in post-lockdown cities

Abstract

The Covid-19 pandemic has resulted in cities around the world implementing lockdown measures, causing unprecedented disruption to urban life often extending over several months. With the spread of Covid-19 now being relatively contained, many cities have started to ease their lockdown restrictions by phases, aiming to return to normal or to enter a new normal. Following the phased recovery strategy proposed by the UK government following the first national lockdown, this paper utilises Greater London as its case study, selecting three main reopening measures (i.e., schools, shops and hospitality reopening). This paper applies sentiment analysis and topic modelling to explore public opinions expressed via Twitter. Our findings reveal that public attention towards the reopening measures reached a peak before the date of policy implementation. The attitudes expressed in discussing reopening measures changed from negative to positive. Regarding the discussed topics related to reopening measures, we find that citizens are more sensitive to early-stage reopening than later ones. This study provides a time-sensitive approach for local authorities and city managers to rapidly sense public opinion. Governments and policymakers can make use of the tool presented herein and utilise it in leading their post-lockdown cities into an adaptive, inclusive and smart recovery.

Haifeng Niu

Research Associate

I am a Research Associate at the Lab of Interdisciplinary Spatial Analysis, Department of Land Economy, University of Cambridge, currently leading spatial analysis work in the European Union’s Horizon 2020-funded project Emotional Cities(WP4). My expertise includes urban big data mining, spatial data science, geo-visualisation, and urban sensing and modelling. I have a strong interest in how the intersection of machine learning & AI and urban big data better supports urban planning, policy-making and smart management.