The monitoring of work towards the SDGs is essential to assess progress and obstacles to realise our shared agenda.
A large amount of SDG documents created by governments, universities, as well as private and public entities are often assessed by the UN to measure progress, usually requiring expert labelling. However, annual SDG progress reports are becoming more common beyond the UN (for example in academia, to evaluate the contribution of research/teaching to this agenda), aiming to identify challenges and achievements.
In this project we propose to create an automatic tool for SDG labelling based on Artificial Intelligence (AI), which can save time in expert querying, facilitating this labelling. Additionally, we propose to leverage the power of cutting-edge AI-based language models. These models are usually trained on the whole internet before being fine tuned on a task (such as SDG tagging). As such, they bring an enormous level of expertise that could reduce the bias in expert labels, as well as represent the interconnectedness of our SDGs.
Our final objective is to build an online tool (web app and API) for querying the model, which has a wide range of use cases in research and education.
Dr Perez-Ortiz is an Assistant Professor at the Centre for Artificial Intelligence at UCL. She isprogram co-founder and Deputy Director of a new MSc program on AI for Sustainable Development, which engages the new generations of engineers in developing responsible and innovative AI technologies for people and the planet. She teaches two modules related to AI and the intersection of the UN’s SDG agenda, as well as how to build responsible and ethical AI systems. Her research is fully interdisciplinary, actively collaborating with psychologists, medical doctors, social scientists, educators, agronomists and climate scientists alike. Every summer, Perez-Ortiz leads a group of MSc students to complete their dissertation in the technology for sustainable development domain, creating new technologies for identifying illegal deforestation/fishing, enabling the energy transition, designing tools to understand the impact of policies, etc. Perez-Ortiz has more than 12 years of experience doing theoretical and applied AI research (h-index 21), with a focus on environmental AI and educational recommender systems. Perez-Ortiz has collaborated in fruitful research with the European Space Agency, the HumaneAI network, the Knowledge 4 All Foundation, Apple, Google’s DeepMind, Spotify and multiple European and American universities.
Sahan Bulathwela is a Research Assistant contributing to multiple large projects on the topic of “AI for Education”. His contributions to the area, published in esteemed research venues, span multiple topics connected to this grant, namely text-tagging, recommender systems and natural language processing. Before joining UCL, he worked in several research roles in the industry where he gained experience in creating data products in a big data landscape. He has experience managing engineering teams to build API and web services.
John Shawe-Taylor is Professor of AI at UCL, Director of the UCL MSc on AI for Sustainable Development, Director of the International Research Center on Artificial Intelligence under the auspices of UNESCO and UNESCO Chair in AI. His foundational work in AI has attracted around 85.000 citations, making him one of the most featured and prolific researchers in the field.
Dr Wayne Holmes is a learning sciences and innovation researcher at the UCL Institute of Education, as well as a consultant researcher on AI and education for UNESCO. Wayne brings a critical studies perspective to the connections between AI and education, and their ethical, human
and social justice implications.