Air Pollution has been a growing menace in developing countries like India, China due to rapid and often unplanned urbanization. To take necessary measures, an effective ambient air monitoring system needs to be present that can provide a city-wide fine-grained air quality map. The existing ambient air quality static monitoring stations incur high installation & maintenance costs and suffer from sparse coverage. On the other hand, in the recent years, there has been active participation of social media users in creating awareness as well as feeding pollution-related information via several micro-blogging platforms like Twitter, Sina-Weibo, etc. The objective of this work is to exploit the presence of such pollution related micro-blogs, combine and associate them with pollution data sensed by static monitoring stations to obtain an authentic air quality map with higher coverage. Here, we reveal some interesting initial exploratory results on inferring air quality using Twitter data. The underlying challenges to model such associations have also been highlighted.
[1]
Victor O. K. Li,et al.
An Extended Spatio-Temporal Granger Causality Model for Air Quality Estimation with Heterogeneous Urban Big Data
,
2017,
IEEE Transactions on Big Data.
[2]
Yu Zheng,et al.
U-Air: when urban air quality inference meets big data
,
2013,
KDD.
[3]
Yong Yu,et al.
A comparative study of users' microblogging behavior on sina weibo and twitter
,
2012,
UMAP.
[4]
Wei Jiang,et al.
Using Social Media to Detect Outdoor Air Pollution and Monitor Air Quality Index (AQI): A Geo-Targeted Spatiotemporal Analysis Framework with Sina Weibo (Chinese Twitter)
,
2015,
PloS one.