Sensing Pollution on Online Social Networks: A Transportation Perspective

Abstract

Transportation policy and planning strategies, as well as Intelligent Transportation Systems (ITS), can all play important roles in decreasing pollution levels and their negative effects. Interestingly, limited effort has been devoted to exploring the potential of social network analysis in such context. Social networks provide direct feedback from people and, hence, potentially valuable information. A post telling how a person feels about pollution at a given time at a given location, could be useful to policy-makers, planners or environmentally-aware ITS designers. This work verifies the feasibility of sensing air pollution from social networks and of integrating such information with real sensors feeds, unveiling how people advertise such phenomenon, acting themselves as smart objects, and how online posts relate to true pollution levels. This work explores a new dimension in pollution sensing for the benefit of environmental and transportation research in future smart cities, confronting over 1,500,000 posts and pollution readings obtained from governmental on-the-field sensors over a one-year span.