Emotion topology: extracting fundamental components of emotions from text using word embeddings.

ABSTRACT: This exploratory study examined the potential of word embeddings, an automated numerical representation of written text, as a novel method for emotion decomposition analysis. Drawing from a substantial dataset scraped from a Social Media site, we constructed emotion vectors to extract the dimensions of emotions, as annotated by the readers of the texts, directly from human language. Our findings demonstrated that word embeddings yield emotional components akin to those found in previous literature, offering an alternative perspective not bounded by theoretical presuppositions, as well as showing that the dimensional structure of emotions is reflected in the semantic structure of their text-based expressions. Our study highlights word embeddings as a promising tool for uncovering the nuance

SUBMITTER: Plisiecki H 

PROVIDER: S-EPMC11494860 | biostudies-literature | 2024

REPOSITORIES: biostudies-literature