Emotion during election periods: Deciphering Twitter users’ discourse

Within computational political science, a sentiment expressed in social media has been subject to examination about electoral behaviour, more so because of the cases of the successful use of social media by candidates (Obama) or by companies who tried to manipulate public opinion (e.g., the involvement of the Russian Internet Research Agency and Cambridge Analytica in 2016 Presidential Elections in the USA, or of Cambridge Analytica’s to the UK’s Referendum about Brexit). In this paper we examine a refinement of analysis, moving from sentiment (positive-negative) to emotions, combine opinion mining with social network analysis, and apply it to the tweets posted during the critical elections that took place in Greece in 2015 and 2019. We find support for the relation between some emotions and voting behaviour in other countries but also realize that the intensity of expressing such emotions is perhaps a better indicator of the need for change.