Carbon neutrality refers to the actions that people and organisations can take to curb or reverse global warming. However finding what actions is available and should be take is not so easy: the media and online information sources are laiden with corporate jargons and sometimes conflicting information. From the perspective of individuals, the information on carbon neutrality consist of three key parts. The first is government legislation and debates on climate and environment; the second part is the news and social media for selecting and interpreting the legislative measures. The third is linking the legislative information to actionable things in ones’ daily lives.
This project aims to design computational tools for summarising information from official and media sources in order for citizens to make informed decisions about their community and their day-to-day practices on reducing carbon footprint.
- Solid background in data science, computational social science, or applied machine learning.
- Solid knowledge of text and natural language processing, knowledge and hands-on experience with machine learning on text a plus, e.g. COMP4650/6490 or equivalent; COMP3670/6670 or equivalent.
- Experience in collecting and processing online text data a plus, e.g. webpages, parliamentary bills and debates, news articles.
- Comfortable prototyping data collection systems and machine learning algorithms, python or R.
- Strong ability to extract statistical information from data, and critique the meaningfulness and correctness of data and plots.
- Able to communicate technical ideas clearly, and work effectively in a research team.