Mining climate change awareness on twitter: A pageRank network analysis method

Abstract

Climate change is one of this century’s greatest unbalancing forces that affect our planet. Mining the public awareness is an essential step towards the assessment of current climate policies, dedication of sufficient resources, and construction of new policies for business planning. In this paper, we present an exploratory data mining method that compares two types of networks. The first type is constructed from a set of words collected from a Climate Change corpus, which we consider as ground-truth (i.e., base of comparison). The other type of network is constructed from a reasonably large data set of 72 million tweets; it is used to analyze the public awareness of climate change on Twitter. The results show that the social-language used on Twitter is more complex than just single word expressions. While the term climate and the hashtag (#climate) scored a lower rank, complex terms such as (“Climate Change”) and (“Climate Engineering”) were more dominant using hashtags. More interestingly, we found the (#ClimateChange) hashtag is the top ranked term, among all other features, used on Twitter to signal climate familiarity expressions. This is indeed striking evidence that demonstrates a great deal of awareness and provides hope for a better future dealing with Climate Change issues.