RideKE is a new code-switched Kenyan tweet dataset for ride-hailing sentiment and emotion, where XLM-R performs best on sentiment but all models struggle with emotion classification.
My ride is taking an unfamiliar route, and I’m getting worried. Is this safe? #Fear
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
RideKE: Leveraging Low-Resource, User-Generated Twitter Content for Sentiment and Emotion Detection in Kenyan Code-Switched Dataset
RideKE is a new code-switched Kenyan tweet dataset for ride-hailing sentiment and emotion, where XLM-R performs best on sentiment but all models struggle with emotion classification.