A valence-trained linear projection of GloVe vectors creates an emotion space in which Plutchik-style emotion arithmetic (Joy+Trust approximates Love) appears more consistent than in raw vectors.
In: Joint European conference on machine learning and knowledge discov- ery in databases
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2019 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Disentangling Latent Emotions of Word Embeddings on Complex Emotional Narratives
A valence-trained linear projection of GloVe vectors creates an emotion space in which Plutchik-style emotion arithmetic (Joy+Trust approximates Love) appears more consistent than in raw vectors.