/sentom

Topic Modeling from Sentiment using BERTopic, Streamlit, and Snowflake

Primary LanguagePythonMIT LicenseMIT

sentom

Streamlit Snowflake Python PyTorch

Sentom (sentiment-topic-modeling) is a simple web application that allows you to do topic modeling on sentiment review using BERTopic. This application is built using Streamlit and Snowflake.

Features 💡

Using Sentom, you can:

  • Do topic modeling on sentiment review
  • See the top keywords for each topic

Prerequisites 📋

Installation 🛠

  • Clone the repository:
git clone https://github.com/putuwaw/sentom.git
  • Install the requirements:
pip install -r requirements.txt

  • Create secret.toml file in .streamlit folder and fill it with your Snowflake credentials. See Documentation for more information.

  • Run the application:

streamlit run Home.py

License 📝

This project is licensed under the MIT License. See the LICENSE file for details.

Acknowledgements 🙏

BERTopic is a topic modeling technique that leverages hugs transformers and c-TF-IDF to create dense clusters allowing for easily interpretable topics whilst keeping important words in the topic descriptions Thank you to the developers and contributors of this open-source tool. Learn more about BERTopic here.