Natural language processing of social network data for the evaluation of agricultural and rural policies

Abstract

Global sustainable development challenges affect the agricultural sector, and many innovations aimed at addressing these challenges have been introduced in the agri-food sector. In this complex context, new agricultural policies are being implemented in Europe. Their success depends on their potential to adapt to new realities, responding to the opinions and demands of the European population. Given the rapid rise of social media as an important part of people's daily lives, public administrations have introduced digitalization and communication strategies through social media sites. Social media can provide policymakers with large amounts of data on user opinions. Given the value of social media as a rich source of data on public views and opinions, the aim of this paper is twofold: (i) to use natural language processing (NLP) to identify the events that have led to negative or positive opinion about European Common Agricultural Policy (CAP) reform and (ii) to evaluate the ability of NLP to study users' opinions on Twitter/X. The findings show that issues such as Brexit, the European Green Deal, the role of CAP in the environment, livestock farming, food safety, and illegal practices and corruption in the distribution of CAP funds have crucial implications for the design and application of the new CAP. Moreover, the study also suggests that NLP techniques can provide opportunities to integrate agricultural policies and instruments in the agri-food sector by assessing society's opinions. Sentiment analysis, even considering its limitations, could support sound and inclusive policymaking approaches anticipating public opinion in cases of risk of social unrest.