Astrophysicists and social scientists are working together on a new project designed to make finding and using data easier for researchers in the future.
The University of Portsmouth has won £200,000 funding for the data science project, which is being funded by the Economic and Social Research Council (ESRC).
The goal is to see how useful AI and machine learning can be for social science research. Humphrey Southall, Professor of Geography at the University of Portsmouth and project leader, said: "Traditional data services have predominantly catered to large-scale data science, often leaving mainstream social scientists struggling to locate smaller, yet crucial, datasets for their research.
"This project aims to shift the focus towards "small data," ensuring that experts in economics, sociology, and social policy can effortlessly find and utilise specific data points, such as the number of seats won by a political party in a particular election, for direct quotation and analysis."
The project aims to build a prototype tool using new machine learning technologies to simplify and accelerate access to data for mainstream social scientists.
The team behind the project will be using the database behind a Vision of Britain through Time, which includes maps, statistical trends and historical descriptions from 1801 until now, and ChatGPT, as the basis for the prototype.
Traditional data services have predominantly catered to large-scale data science, often leaving mainstream social scientists struggling to locate smaller, yet crucial, datasets for their research.
Humphrey Southall, Professor of Geography and project leader
Academics from the School of the Environment, Geography and Geosciences will provide the data and social science expertise, and data experts from the University's Institute of Cosmology and Gravitation (ICG) will provide the technical expertise, including the use of ChatGPT.
The project will start by investigating how experts who study society and human behaviour are currently finding and using statistics and other secondary data to inform their research.
Project manager Dr Paula Aucott, said: "This will help us understand current strategies for data discovery and identify the gaps in existing services.
"Our vision is to create a more user-friendly and efficient data discovery process that supports the diverse needs of social scientists, enabling them to conduct high-quality research with ease."
Dr Xan Morice-Atkinson, Research Software Engineer from the ICG, said: "I'm really excited to apply data science skills I've gained within astronomy and industry to completely new data sources. Working across domains with experts in different areas like sociology is really important - it allows us in astronomy to learn more about the world around us, but also sociologists to take advantage of our in-house data science skills."
