In China, haze weather has become a major public concern and is frantically discussed by the public. Many people express their views, opinions, or complaints on social media. Effectively extracting this useful information may help to improve our understanding of how the public perceive and respond to haze, and could potentially contribute to environmental policy-making. In this paper, we study how the public perceive haze during haze weather and how this perception changes with seasons based on comment data from a major social media platform in China, Weibo, and using several social network methods, including perceptual keyword cloud mapping, complex network topology characteristics, and social perception analysis. The results showed that the public's perception was focused on the causes of haze in spring, enjoyment of life and travel in summer, measures to prevent haze in autumn, and the adverse effects of haze on human health in winter.
Keywords: complex network; data mining; semantic analysis; social public environment perception.