Investigating the structure of emotions by analyzing similarity and association of emotion words
Fumitaka Iwaki, Tatsuji Takahashi
TL;DR
This work addresses the validity of Plutchik's wheel of emotion by constructing semantic networks from similarity and association judgments over 48 emotion words and applying modular decomposition of Markov chains (MDMC) to detect communities. By comparing network-derived communities to the wheel with normalized mutual information, the study finds broad alignment but notable local deviations, such as re-clustering of certain derived emotions with neighboring groups. It reveals that association data exhibit higher locality and globality than similarity and that MDMC can reveal multi-resolution structures, including low-resolution splits that diverge from the wheel. The findings suggest that emotion structure is better captured by network representations than by strict circular models and have implications for natural human-agent interaction and multi-language validation of emotion schemas.
Abstract
In the field of natural language processing, some studies have attempted sentiment analysis on text by handling emotions as explanatory or response variables. One of the most popular emotion models used in this context is the wheel of emotion proposed by Plutchik. This model schematizes human emotions in a circular structure, and represents them in two or three dimensions. However, the validity of Plutchik's wheel of emotion has not been sufficiently examined. This study investigated the validity of the wheel by creating and analyzing a semantic networks of emotion words. Through our experiments, we collected data of similarity and association of ordered pairs of emotion words, and constructed networks using these data. We then analyzed the structure of the networks through community detection, and compared it with that of the wheel of emotion. The results showed that each network's structure was, for the most part, similar to that of the wheel of emotion, but locally different.