RevAnalyzer leverages machine learning for efficient review analysis. It provides insights into customer feedback while enabling heavy customization of the process. Try it out.

Demo

rev-analyzer_demo.mp4

Run Locally

Clone the project

  git clone https://github.com/Asterikss/rev-analyzer.git
  cd rev-analyzer

Create a new environment

• Venv

  • Linux

  python -m venv rev-analyzer
  source env_name/bin/activate

  • Windows

  python -m venv rev-analyzer
  env_name\Scripts\activate

• Conda

  conda create --name rev-analyzer python=3.10
  conda activate rev-analyzer

Install dependencies

  pip install -r requirements.txt

Run the app

  streamlit run 1_🔬_Analyzer.py

*The app needs to be run from the root of the project
*Best viewed at 125% browser zoom (assuming 1920x1080) *If this line from requirements.txt fails: https://github.com/explosion/spacy-models/releases/download/en_core_web_sm-3.6.0/en_core_web_sm-3.6.0.tar.gz#egg=en_core_web_sm, or you want to download it via the command line instead, be sure to run python -m spacy download en_core_web_sm, otherwise, you will encounter an error.

In the works

Custom LSTM model with frozen pre-trained 100-dim embeddings