Predicting Emotion Intensity in Polish Political Texts: Comparing Supervised Models and Large Language Models in a Resource-Poor Language

This exploration has yielded important findings in political sciences (Mintz et al., 2022), sociology (Bericat, 2016; Turner & Stets, 2006), economics (Loewenstein, 2000), anthropology (Lutz & White, 1986), organizational research (Diener et al., 2020) as well other fields of social (Kleef, 2018) and psychological sciences (Derks et al., 2008). While investigating this role of emotions, many researchers concentrate on the question of whether an emotion is present, focusing on the categorical aspects of emotions (Fritz et al., 2009; Saarimäki et al., 2016; Siedlecka & Denson, 2019; Tanaka-Matsumi et al., 1995). However, beyond the sole presence or absence of emotions, there is also their intensity, which was early recognized as necessary to understand human behaviors (Brehm, 1999; Plutchik, 1965). People often describe emotions like anger, sadness, or happiness in varying degrees, from none at all to very intense, and research indicates that emotion intensity is crucial in cognitive processing, social behavior, and communication within groups (Frijda et al., 1992; Niedenthal & Brauer, 2012; Reisenzein, 1994).