Guilt by Association: Emotion Intensities in Lexical Representations

TL;DR

This paper investigates how word vector representations can be used to estimate emotion intensity scores for words, demonstrating that they outperform existing emotion lexicons in correlating with human ratings.

Contribution

It introduces and compares unsupervised, supervised, and self-supervised methods for extracting emotion intensities from word vectors, highlighting their effectiveness.

Findings

Word vectors correlate highly with human emotion ratings.

They outperform existing emotion lexicons in accuracy.

Self-supervised methods show promising results.

Abstract

What do word vector representations reveal about the emotions associated with words? In this study, we consider the task of estimating word-level emotion intensity scores for specific emotions, exploring unsupervised, supervised, and finally a self-supervised method of extracting emotional associations from word vector representations. Overall, we find that word vectors carry substantial potential for inducing fine-grained emotion intensity scores, showing a far higher correlation with human ground truth ratings than achieved by state-of-the-art emotion lexicons.