IMDb Sentiment Analysis Model

Model Details

Description

This model is a fine-tuned BERT (bert-base-uncased) for classifying IMDb movie reviews as positive or negative sentiment.

Model type: Transformer-based classifier
Language: English
Fine-tuned from: bert-base-uncased

Sources

Dataset: IMDb Dataset
Original Paper: Maas et al., "Learning Word Vectors for Sentiment Analysis", ACL 2011.

Usage

Direct Use

Sentiment classification for movie reviews.

Out-of-Scope Use

Not suitable for analyzing emotions beyond binary classification.

Training Details

Data

Dataset: IMDb Movie Reviews (stanfordnlp/imdb)
Train Size: 2000 reviews
Test Size: 2000 reviews

Training

Epochs: 5
Batch Size: 8
Optimizer: AdamW
Learning Rate: 5e-5

Evaluation

Results

Metric	Score
Accuracy	88.8%
F1 Score	88.0%

Citation

If you use this model, please cite the original dataset:

@InProceedings{maas-EtAl:2011:ACL-HLT2011,
  author    = {Maas, Andrew L. and Daly, Raymond E. and Pham, Peter T. and Huang, Dan and Ng, Andrew Y. and Potts, Christopher},
  title     = {Learning Word Vectors for Sentiment Analysis},
  booktitle = {Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies},
  month     = {June},
  year      = {2011},
  address   = {Portland, Oregon, USA},
  publisher = {Association for Computational Linguistics},
  pages     = {142--150},
  url       = {http://www.aclweb.org/anthology/P11-1015}
}