TorchSenti

Sentiment Analysis Library for Research with PyTorch

TorchSenti provides sentiment analysis datasets from a simple one (positive/negative labels) to fine-grained one (aspect-based). TorchSenti is compatible with PyTorch to develop model and use pre-trained model to benchmark your work with other researchers.

Features

- Text Cleansing e.g removing hyperlinks
- WordPiece Tokenization with tagging for aspect extraction
- Entity metrics for aspect detection

Dataset Available

- **Sentiment Analysis**
    - IMDB Movie Reviews
    - Pros and Cons
    - Movie Review
    - Trip Advisor
    - City Search Data
    - Yelp Review
- **Aspect-based Sentiment Analysis**
    - SemEval 2014 Task 4 (ToDo)
    - SemEval 2015 Task 12 (ToDo)
    - SemEval 2016 Task 5 (ToDo)

Installation

You can install TorchSenti using pip

    pip install torchsenti

from source

    git clone https://github.com/jakartaresearch/pytorch-sentiment.git
    cd pytorch-sentiment
    python setup.py install

Getting Started

Contributors