Keywords: statistical modeling, machine learning, software development, climate change
For the climate, flying to New York is worse than taking a long shower. But is it 10 times worse or 1000 times worse? The carbon footprint of our actions have been widely analyzed and quantified, but it does not mean that people are well aware of their impact. In this project, we aim at understanding the perception that people have of their actions and how does it compare to the actual carbon footprint of such actions. This could help climate scientist, sociologists, communicators, and people in general to improve climate communication and climate action.
The project consists of two parts: 1. develop an app to collect data from users, and 2. implement and analyze a model of user perception.
To collect data, we aim at developing a web app, ideally adaptable to iOS and Android. The app interface will display (i) pairwise examples of different actions (e.g., taking the plane and taking a shower) and (i) a slider to measure the impact ratio between the two actions. A summary of the answers and a comparison with the actual impact will be displayed at the end of a session.
The data collection is crucial to the model. We aim at developing a model of user perception, which will enable us to understand how user perceive their actions. The model also enables active learning in order to minimize the number of comparisons that a user must perform. This helps obtain useful data more quickly.
Please send your transcript and your CV to (victor.kristof@epfl.ch)[victor.kristof@epfl.ch].