۱- Introduction

۲- Methods

۳- Literature review

۴- Technical review

۵- Discussion

۶- Conclusion

References

Abstract

A number of works have addressed the question of assessing the status and the quality of the environment through the lens of Online Social Networks (OSNs). These contributions fall in the area of human-centric sensing, area specialized in using what people spontaneously say on social media to detect the occurrence of given events. Research in this area has exhibited interesting results, regardless of the accuracy of sensing operations. In fact, in some cases it is possible to corroborate the information extracted from OSN posts with the ground truth obtained from specialized hardware sensors. In others, the information extracted from OSNs does not reveal true environmental conditions. Nevertheless, OSNs may help shed light on the sensitivity of human beings to a wide variety of environmental phenomena. We here review the work that has been published to this date. In particular, we provide a survey that may benefit both environmental and computer scientists, as this work aims to show where we stand in the understanding of the complex relationship between human beings and the natural environment, when this is mediated by OSNs.

Introduction

Understanding the dynamics and the state of health of the natural environment has always been one of the main interests of people, in all historical times. Almost 2000 years ago, Pliny the Younger wrote a description of the eruption of the Vesuvius which is still nowadays studied by millions of students from all around the world [1]. The interest for the study and analysis of environmental dynamics is as live as ever, as new awareness for its state of health is strong, being an important component of human wellbeing [2]. Nevertheless, such type of interest roots in the one normally exhibited by people for weather forecasts, as well as in the fear which instead natural disasters or pollution hazards trigger. In fact, regardless of the specific phenomenon and where and when people discuss it, assessing the status and predicting the dynamics of the natural world, in any of its aspects, is an age-old problem of statistical inference. Even simply knowing whether it will rain or not on a short notice may attract much attention: harvesting, warfare, trips and outdoor sporting events often depend on it [3].