Sentiment Analysis
Tutorial¶
On the Ludwig medium publication you can find a three part tutorial on Sentiment Analysis with Ludwig:
- Part I (Training models from scratch)
- Part II (Finetuning pretrained models)
- Part III (Hyperparameter Optimization)
| review | sentiment | 
|---|---|
| The movie was fantastic! | positive | 
| Great acting and cinematography | positive | 
| The acting was terrible! | negative | 
ludwig experiment \
  --dataset sentiment.csv \
  --config config.yaml
With config.yaml:
input_features:
    -
        name: review
        type: text
        encoder: 
            type: parallel_cnn
output_features:
    -
        name: sentiment
        type: category