Climate Arena 2024

Without looking it up, would you know if the "Clean Resource Innovation Network” is an oil and gas lobbying organisation? Lobbyists often hide under unintuitive or misleading affiliations that obscure their origins. The work of uncovering their identities can be time-consuming and challenging.  

This workshop will outline an approach to using web scraping and Large Language Models (LLMs), like those powering ChatGPT, to systematically identify organisations that are affiliated with the fossil fuel industry. These techniques could also be adapted to other climate projects, such as identifying climate misinformation.

The workshop will:

- Describe some of the challenges of web scraping at scale and the technical tools that can be used to address those challenges
- Describe how to design and test a successful LLM prompt
- How to identify the right LLM for the project you want to do
- How to test your approach and validate the results

ps. You should have a Google account to open the link that'll be shared during the session.