Evaluation in social media discourse

The way crises are discussed influences both personal and collective thinking (Seeger & Sellnow 2016). Therefore, it is essential to understand how the global health crisis of Covid-19 was represented on social media where different attitudes and emotions collide. Moreover, better grasping how people perceived the pandemic is vital for managing future health crises and other societal upheavals (Lindholm et al. 2023). In this study, we analyse how various discourse topics, i.e., themes, related to the Covid-19 pandemic were evaluated by Twitter users. We also examine the evaluative images that emerged from these discussions. With evaluation, we refer to expressions of language user’s attitudes and emotions through language (Bednarek 2010). Evaluative images, on the other hand, are created when these discourse topics and evaluations intersect. To tackle the vast amounts of data generated on social media, we employ the combination of the unsupervised machine learning method of topic modelling and the discourse analytical approach of evaluative parameters to study a large corpus of 374,978 Finnish tweets from January 2020 to August 2021. The results of our corpus-assisted discourse analysis reveal 35 distinct discourse topics, encompassing themes such as health, protective measures, briefings and support services. In addition, evaluative expressions of emotivity, mental state, importance and necessity are involved. From this analysis, two primary evaluative images emerge i) a focus on consistent responsibility and emotional reactions and ii) support for the groups most affected by the pandemic. These images reflect the situation’s complexity necessitating profound accountability and support across different layers of society.