Publication
Title
Joint emotion label space modeling for affect lexica
Author
Abstract
Emotion lexica are commonly used resources to combat data poverty in automatic emotion detection. However, vocabulary coverage issues, differences in construction method and discrepancies in emotion framework and representation result in a heterogeneous landscape of emotion detection resources, calling for a unified approach to utilizing them. To combat this, we present an extended emotion lexicon of 30,273 unique entries, which is a result of merging eight existing emotion lexica by means of a multi-view variational autoencoder (VAE). We showed that a VAE is a valid approach for combining lexica with different label spaces into a joint emotion label space with a chosen number of dimensions, and that these dimensions are still interpretable. We tested the utility of the unified VAE lexicon by employing the lexicon values as features in an emotion detection model. We found that the VAE lexicon outperformed individual lexica, but contrary to our expectations, it did not outperform a naive concatenation of lexica, although it did contribute to the naive concatenation when added as an extra lexicon. Furthermore, using lexicon information as additional features on top of state-of-the-art language models usually resulted in a better performance than when no lexicon information was used.
Language
English
Source (journal)
Computer speech and language. - London
Publication
London : 2022
ISSN
0885-2308
DOI
10.1016/J.CSL.2021.101257
Volume/pages
71 (2022) , 20 p.
Article Reference
101257
ISI
000761599000003
Medium
E-only publicatie
Full text (Publisher's DOI)
Full text (publisher's version - intranet only)
UAntwerpen
Publication type
Subject
External links
Web of Science
Record
Identifier
Creation 06.11.2023
Last edited 25.04.2024
To cite this reference