Valuation of Emotionality and Osgood Factors in Fiction Prose using Machine-Generated Dictionaries (On the Material of the Strugatsky Brothers Trilogy about M. Kammerer)

Abstract

The relevance of the work lies in the fact that Osgood factors and emotive characteristics of the text can be extrapolated from the russian fiction prose, as the most adequate type of author's and reader's expression, to the assessment of moods in society in a specifically given period. To analyse them, we need deep-learning neural networks capable of assessing positivity and other factors taking into account the context - with the help of dictionaries based on the survey of informants and machine extrapolation. From a methodological point of view, we used a dictionary with positivity ratings for russian language words CartaSlovSent, as well as data from multilingual NRC VAD, Hedonometer dictionaries to identify categories of valence, dominance and arousal in texts. To construct a series of average text positivity, all word forms contained in the selected dictionary were found and the values of their positivity ratings were averaged. The results of the study showed that in the Strugatsky brothers' trilogy about Maxim Kammerer, "The Inhabited Island" with the corresponding descriptive negative narrative related to the image of the planet Saraksh is the most indicative for positivity ratings. At the same time, throughout the trilogy, Osgood factors are spread throughout the text according to the development of plot and compositional elements. "The Beetle in the Anthill" and "Waves Extinguish the Wind" are similar in the degree of expression of Osgood factors, including due to a similar dominant chronotope.