Guilt by Association: Emotion Intensities in Lexical Representations
This work addresses the challenge of accurately capturing fine-grained emotional content in words for applications in natural language processing and sentiment analysis, representing a strong specific gain rather than a foundational breakthrough.
The study tackled the problem of estimating word-level emotion intensity scores by exploring methods to extract emotional associations from word vector representations, finding that word vectors achieve a far higher correlation with human ground truth ratings than state-of-the-art emotion lexicons.
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.