Twitter data analysis to understand societal response to air quality

Abstract

Air quality is recognized to be major risk factor for human health globally. Critical to addressing this important public health issue is the effective dissemination of air quality data, information about adverse health effects, and the necessary mitigation measures. The ability of people to understand air quality information and take actions to protect their health is not clear. Recent studies have shown that even when public get data on air quality and understand its importance, they do not exhibit a pro-environmental behavior to address the problem. All existing studies on public attitude and response to air quality are based on offline studies, with a limited number of survey participants and over limited number of geographical locations. For a larger survey size and global set of locations, we analyzed Twitter data collected over a period of nearly two years. We identify a limited number of hashtags (3) that can best correlate the frequency of tweets with local air quality (PM2.5) in three major cities around the world: Paris, London, and New Delhi. Using tweets with just these three hashtags, we determined that people's response to air quality in the three cities was nearly identical when considering relative changes in air pollution. Using machine learning algorithms, we determined that health concerns dominated public response when air quality degraded, with the strongest increase in concern being in New Delhi, where pollution levels are the highest amongst the three cities studied. The public call for political solutions when air quality worsens is consistent with similar findings with offline surveys in other cities. Our approach will allow for global analysis of public response to air quality and aid public health officials respond appropriately.