Sentiment Analysis Models

This repository contains multiple trained sentiment analysis models for binary sentiment classification (Positive / Negative).

Repository Structure

Sentiment/
│
├── BERT/
├── Bi_LSTM/
├── Linear_Svm/
├── Logistic_Regression/
├── Lstm/
├── Naive Bayes/
├── XGBoost/
└── Notebooks/

Available Models

BERT
LSTM
Bi-LSTM
Logistic Regression
Linear SVM
Naive Bayes
XGBoost

Using the BERT Model

from transformers import pipeline

classifier = pipeline(
    "text-classification",
    model="Sudheer17/Sentiment/BERT"
)

result = classifier("I love this movie!")

print(result)

Example Output

[{'label': 'Positive', 'score': 0.9848}]

Example Inputs

I love this movie!

This is the worst experience ever.

The service was average.

Notes

The BERT model can be loaded directly using the Hugging Face Transformers library.
Classical Machine Learning and Deep Learning models are stored in their respective folders.
Use the appropriate tokenizer and preprocessing pipeline when working with non-BERT models.

Requirements

transformers
torch
tensorflow
scikit-learn
joblib
numpy
pandas

Install them using:

pip install transformers torch tensorflow scikit-learn joblib numpy pandas

License

This repository is released under the MIT License.

Downloads last month: -; Downloads are not tracked for this model. How to track