Sentiment Analysis
Last updated
Last updated
Supported Labeling Types: Row Labeling
Sentiment analysis will provide a simple classification between “Positive” or “Negative”.
The model used for sentiment analysis is sourced from . This model is a fine-tuned checkpoint of DistilBERT-base-uncased, specifically trained on the SST-2 dataset.
The model is using a distilled version developed by Hugging Face based on the Text Classification task pipeline.
The model reaches an accuracy of 91.3% on the development set.
The model hosted locally within the Datasaur Intelligence container.
This model is primarily used for sentiment classification and also be used for topic classification.
The raw model supports masked language modeling and next sentence prediction, though it is primarily intended for fine-tuning on downstream tasks.
Trained on Stanford Sentiment Treebank () corpora which contains 67,349 movie review excerpts with human-annotated sentiment labels.
To explore additional fine-tuned versions for different tasks, check out the .