README.md

metadata

datasets:
  - sem_eval_2018_task_1
language:
  - ar
metrics:
  - accuracy
library_name: transformers
pipeline_tag: text-classification
tags:
  - transformers
  - emotion
  - BERT

Model Card for Model ID

This model aims at classifying arabic text into its corresponding set of emotions by fine-tuning a variant of BERT pre-trained on arabic twitter data.

Model Sources [optional]

• Repository: https://github.com/TomoyeSaa/Emotion-Detection-for-Arabic-Language

Evaluation

Jaccard accuracy is the main eval metric and the model achieved 56.12%