How language-dependent is emotion detection? Evidence from multilingual BERT

Publication type
C1
Publication status
Published
Authors
De Bruyne, L., Singh, P., De Clercq, O., Lefever, E., & Hoste, V.
Series
Proceedings of the 2nd Workshop on Multi-lingual Representation Learning (MRL)
Pagination
76-85
Publisher
Association for Computational Linguistics
Conference
2nd Workshop on Multi-lingual Representation Learning (MRL) (Abu Dhabi, United Arab Emirates (Hybrid))
Download
(.pdf)
View in Biblio
(externe link)

Abstract

As emotion analysis in text has gained a lot of attention in the field of natural language processing, differences in emotion expression across languages could have consequences for how emotion detection models work. We evaluate the language-dependence of an mBERT-based emotion detection model by comparing language identification performance before and after fine-tuning on emotion detection, and performing (adjusted) zero-shot experiments to assess whether emotion detection models rely on language-specific information. When dealing with typologically dissimilar languages, we found evidence for the language-dependence of emotion detection.