Home // HUSO 2019, The Fifth International Conference on Human and Social Analytics // View article

Towards a Psychologically Grounded Emotion Dictionary for Russian

Authors:
Polina Panicheva
Olga Bogolyubova

Keywords: Emotion dictionary; Russian language; affective language; subjectivity analysis; basic emotions

Abstract:
In Natural Language Processing, there is currently a trend towards analyzing subjective language, one of the important topics being emotion detection from text. There have been a number of successful attempts of developing emotion dictionaries in the English language based on emotion theories well established in psychology. However, such resources in Russian are lacking. In the current work, we propose a roadmap for developing a psychologically grounded emotion dictionary in Russian. Based on the related work overview, we propose an emotion classification theory by Carroll Izard including ten basic emotions as a framework for building emotion dictionary. We outline a number of lexical resources for compiling word candidates for the dictionary. Finally, we describe the annotation procedure by volunteers and experts, and psychometric evaluation to measure internal consistency and external validity of the dictionary. The dictionary will be used in emotion detection tasks, compared to other available lexical resources, and supplemented with context-dependent statistical algorithms.

Pages: 1 to 4

Copyright: Copyright (c) IARIA, 2019

Publication date: June 30, 2019

Published in: conference

ISSN: 2519-8351

ISBN: 978-1-61208-725-2

Location: Rome, Italy

Dates: from June 30, 2019 to July 4, 2019