Cyclone Amphan made landfall in South Asia on May 20, 2020. It was the most damaging storm in the history of the Indian Ocean, rendering hundreds of thousands of people homeless, ravaging agricultural lands and causing billions of dollars in damage. How were people affected by the storm? What were the responses of individuals, governments, corporates and NGOs? How was it covered by local, national and international media, as opposed to individuals' accounts? Who has created the dominant narratives of Cyclone Amphan; and whose voices go unheard? We aim to use online data -- such as Twitter posts, news headlines and research publications -- to analyze people's experiences of Cyclone Amphan.
People often think of extreme weather events (and climate change more widely) in abstract, meteorological terms: rain, wind, weather, heat, etc. However, extreme weather events are experienced by people and have complex social, political and economic dimensions. For instance, discourse around Cyclone Amphan has been linked to migration, COVID-19, gender, corruption and more.
How might we use online data to raise the visibility of people's lived experiences of extreme weather events? What might it tell us about the ways in which narratives about extreme weather events are formed? Most importantly, how can we use this knowledge to match people's needs with demand-driven, context-specific responses (e.g. humanitarian aid, funding, research)?
This project has three parts: 1) collect online data pertaining to Cyclone Amphan, 2) analyze the online data using natural language processing and 3) build an online dashboard with interactive data visualizations.
Our research questions are flexible, depending on the volunteers' interests and skillsets and the data that's collected. In general, however, we see three areas that are ripe for exploration: 1) What were people’s experiences of and responses to Cyclone Amphan? Who was posting, where, what and when? For instance, we could compare the experiences of people in rural versus urban areas. 2) Why are people saying these things about Cyclone Amphan (discourse analysis)? What biases or vested interests influence narratives of Cyclone Amphan? 3) Who’s getting the most attention in their characterizations of Cyclone Amphan? Who’s shaping the dominant narrative; and whose experiences go unheard?
First and foremost, IWMI strives for its research to be demand-driven. This project gets to the heart of this: it leverages online data sources to understand how people are affected by extreme weather events and what they need, rather than listening primarily to "experts." While we're using Cyclone Amphan as a proof-of-concept for now, we hope to eventually create a research tool that enables users -- from governments to donors to development organizations -- to tap into online discourse about water-related issues. This data would ideally serve as additional inputs as users prepare context-specific research and/or interventions in response to extreme weather events.
Secondly, as a research-for-development organization based in the Global South, data science has not historically been our strong suit. Last year, however, we launched a new strategy that places a greater emphasis on digital innovations. This project will be one of our first projects that leverages online data sources and uses techniques like natural language processing. We hope it will show our colleagues the many potential applications of data science for natural resource management, build our capacity and inspire future efforts.
Michelle Ng (Digital Innovations Analyst) and Rachel von Gnechten (Research Analyst) are leading this project with support from Simon Langan (Director of Digital Innovations and Country Manager, Sri Lanka).
Michelle Ng (Digital Innovations Analyst) and Rachel von Gnechten (Research Analyst) are the point people within IWMI for this project. They can draw on additional support from any IWMI staff, from social scientists to hydrologists to irrigation engineers, as needed.