About the project
Event extraction using deep-learning based Large Language Models (LLMs) for Natural Language Processing (NLP) of social media posts focussing on environmental impact events such as pollution, wildfires and flooding. During this project you will collaborate with the world renowed at Royal Botanic Gardens, Kew (Kew Gardens).
Monitoring risks to natural habitats, such as pollution, wildfire, flooding and invasive species outbreaks, is a critical element for protecting and sustaining biodiversity. Often an event is observed well after damage to biodiversity has been done. Social media and Natural Language Processing (NLP) offers opportunities to use AI for 24/7 review of localized public posts from concerned citizens and volunteer environmentalists.
You will explore novel Event Extraction algorithms using deep-learning based Large Language Models (LLMs) applied to social media posts about instances of habitat and environmental impact. Initial ideas include combining Relation-Aware Prototyping with LLM location augmentation to explore prototyping hyper-local location refinement of environmental events and their associated image or videos context within social media posts.
During this project you will collaborate with the world renowned at Royal Botanic Gardens, Kew (Kew Gardens) who will provide an impact pathway for your work, and be part of growing team of PhD students and post-doctoral researchers exploring cutting edge Natural Language Processing (NLP) technology.
You will join the School of Electronics and Computer Science within the University of Southampton, ranked in the top 100 universities worldwide (QS worldwide ranking 2024). We will support the development of your future career and give you opportunities including teaching assistantships, professional networking via leading organizations such as Alan Turing Institute, £31M RAI UK ecosystem, and access to Future Worlds to explore commercialisation of your research.
