Universal Joy A Data Set and Results for Classifying Emotions Across Languages

Sotiris Lamprinidis, Federico Bianchi, Daniel Hardt, Dirk Hovy

Abstract: While emotions are universal aspects of hu- man psychology, they are expressed differ- ently across different languages and cultures. We introduce a new data set of over 530k anonymized public Facebook posts across 18 languages, labeled with five different emo- tions. Using multilingual BERT embeddings, we show that emotions can be reliably inferred both within and across languages. Zero-shot learning produces promising results for low- resource languages. Following established the- ories of basic emotions, we provide a detailed analysis of the possibilities and limits of cross- lingual emotion classification. We find that structural and typological similarity between languages facilitates cross-lingual learning, as well as linguistic diversity of training data. Our results suggest that there are commonal- ities underlying the expression of emotion in different languages. We publicly release the anonymized data for future research.