SentimentAI, is an AI tool designed to analyze text data or transcribed raw dialogue from client-approved design reviews. It generates a comprehensive summary, including keyword extraction, sentiment analysis, and design categorization, allowing designers to pinpoint specific elements for refinement. Our target audiences are UX/UI and product designers, particularly those that interface with various clients such as those at an agency or through freelance. The tool can be hosted on a live web server so that users can access it from different devices.
- Clone this repository
git clone https://github.com/cakkrie/SentimentAI - Download the dependencies for this project though pip
pip install flask flask-cors transformers torch torchvision keybert sentence-transformers scikit-learn - Run the python Flask app
python backend.py - Host the index.html on a live server, you may do this through the Go Live addon in VS Code
- Open the app and input the label and text, ensure you are on a web API browser for voice recognition
- index.html - Primary app webpage
- styles.css - Styling for the HTML
- backend.py - Python Flask app for backend server and API calls
- script.js - Sends calls to backend endpoints and updates the frontend