The Food Sentiment Observatory

Social media and other forms of online content have enormous potential as a way to understand people's opinions and attitudes, and as a means to observe emerging phenomena - such as disease outbreaks. How might policy makers use such new forms of data to better assess existing policies and help formulate new ones?

This one year demonstrator project was a partnership between computer science academics at the University of Aberdeen and officers from Food Standards Scotland which aimed to answer this question. Food Standards Scotland is the public-sector food body for Scotland created by the Food (Scotland) Act 2015. It regularly provides policy guidance to ministers in areas such as food hygiene monitoring and reporting, food-related health risks, and food fraud.

The project has developed a software tool (the Food Sentiment Observatory) that has been used to explore the role of data from social media sources in three policy areas selected by Food Standards Scotland. Each area was explored during a policy sprint, in which tools and techniques from the Open Policy Making Toolkit were used to identify relevant policy questions; if necessary, the data collection and analysis features of The Observatory were then extended, before being used to explore the identified questions in the context of social media content. The areas explored were:

• review of attitudes to the differing food hygiene information systems used in Scotland and the other UK nations (April - August 2017);
• study focusing on discussions of illness related food to understand the effectiveness of monitoring and decision making protocols (September 2017 - January 2018);
• understanding the potential role of social media data in responding to existing, new and emerging forms of food crime (February - July 2018).

The Observatory integrates a number of existing software tools (developed in our recent research) to allow us to mine large volumes of data to identify important textual signals, extract opinions held by individuals or groups, and crucially, to document these data processing operations - to aid transparency of policy decision-making. Given the amount of noise appearing in user-generated online content (such as fake restaurant reviews) we also investigated methods to extract meaningful and reliable knowledge, to better support policy making.