Skip to content

Latest commit

 

History

History
7 lines (4 loc) · 467 Bytes

README.md

File metadata and controls

7 lines (4 loc) · 467 Bytes

ShonaSenti

In this repository we provide the first Shona sentiment analysis corpus and corresponding python scripts to process it.

  • Corpus of Shona tweets for training and testing sentiment analysis systems, labelled with 3 sentiment classes (negative, neutral, positive) and 5 sentiment classes (very negative, negative, neutral, positive and very positive).

  • Scripts for fetching tweets, processing, language detection, and pre-labelling with emojis.