Master of Philosophy
School of Computing and Information Technology
Social media is not only a way to share information among a group of people but also an emerging source of rich primary data that can be crowdsourced for good. The primary function of social media is to allow people to network near real-time, yet the repository of amassed data can also be applied to decision support systems in response to extreme weather events.
The megacity of Jakarta, Indonesia has the greatest number of Twitter users of any city worldwide. Furthermore, the city experiences seasonal flooding during the annual monsoon seasons, which endangers human health, damages civic infrastructure and causes large economic loss. In this study, the use of social media data is examined as a way to help government organisations respond to flooding in a timely manner.
Tweets from two previous monsoons related to flooding were collected and analysed using the hashtag (#) “banjir”. Additionally, government data sources on the location of flood events in the city over the same period were collected. By analysing the relationship between the tweets and the flood events, this study aims to create “trigger metrics” of flooding based on Twitter activity. Such trigger metrics have the advantage of being able to provide a situational overview of flood conditions in near real-time, as opposed to formal government flood maps which are only produced on a six-hourly schedule. The aim is to provide continuous intelligence, rather than discrete intervals of decision-making capability.
The theory of this thesis demonstrated is to enhance the capacity to understand and promote the resilience of cities to both extreme weather events due to climate change and to long-term infrastructure transformation with the process of climate adaptation. To understand the full potential of Twitter as a real-time indicator for flooding, this research aims to quantify the temporal relationship between tweets related to flooding, and flood events in the city of Jakarta, Indonesia. This research can also provide methodological support to make social media a real time crowd-sourcing tool during extreme weather events. Past Twitter data and the real observed flooding events are used as the basis for modelling the urban flooding event in its totality.
To advance the comprehensive understanding of the relationship between flood events and Twitter activity in Jakarta and the modelling of urban flood using geo-social intelligence, this research will quantify the relationship using three stages. Each stage is characterised by an experiment, the results of which are presented and interpreted. This thesis presents the background of the research topic, literature review, research methodology, process of analysis and statistical analysis of results based on these experiments, and a discussion of the outcomes of the research.
Yang, Kun, Urban flood modelling using geo-social intelligence, Master of Philosophy thesis, School of Computing and Information Technology, University of Wollongong, 2017. https://ro.uow.edu.au/theses1/47