Logo Lanfrica
  • Home
  • Atlas
  • Insights
  • Docs
  • Sign in

© 2026 Lanfrica. All rights reserved. All copyrights of the resources shown on the Lanfrica website belong to the original copyright holders, unless explicitly stated otherwise.

rasyosef/amharic-sentiment

Domain:

natural language processing

Record type:

dataset
Creator:
ras
Host:
This dataset contains 2781 cleaned Amharic Tweets, labeled as having either positive or negative sentiment. This dataset can be used to train a sentiment classification model. github.com The following models were finetuned using this dataset. The reported precision, recall, and f1 metrics are macro averages.

Visit

huggingface.co

Tasks

sentiment analysistext classification

Languages

Amharic

Similar

rasyosef/amharic-sentiment-classificationrasyosef/bert-medium-amharic-finetuned-sentimentrasyosef/bert-amharicrasyosef/gpt2-small-amharicrasyosef/amharic-sentences-corpusrasyosef/amharic-llama-preferences

rasyosef/amharic-sentiment-classification

notebooks to finetune Amharic BERT and RoBERTa models for sentiment classification ### Amharic Sent

rasyosef/bert-medium-amharic-finetuned-sentiment

rasyosef/bert-amharic

BERT transformer models pretrained on amharic text # BERT Amharic This repo contains 4 BERT transf

rasyosef/gpt2-small-amharic

rasyosef/amharic-sentences-corpus

This dataset is compiled by Yimam et al. (2021) at LT Group, University of Hamburg, Germany. It comp

rasyosef/amharic-llama-preferences