DE / Done
AI - Sentiment Hub
Overview
Live sentiment dashboard over scraped news on AI, blockchain, finance, forex, and investing. BERT and VADER score each article, React shows the trends, FastAPI serves them, and PostgreSQL with Supabase stores everything, deployed on Render.
Challenge
Building an efficient ETL pipeline to scrape and process raw news data from News API, integrating BERT and VADER models for accurate sentiment analysis, and creating a responsive dashboard backed by a Swagger-documented API and PostgreSQL/Supabase storage.
Result
Delivered a working app where an ETL pipeline scrapes news, scores sentiment, and serves it through interactive dashboards and Swagger-documented endpoints.
Key Statistics
News API
Data Source
AI, Blockchain, Finance, Forex, Investment
Topics Analyzed
BERT, VADER
Sentiment Models
Render
Deployment Platform
Technologies
Programming
-
Python
Frontend
-
React JS
Backend
-
FastAPI -
Swagger
Database
-
PostgreSQL -
Supabase
Deployment
-
Render
Machine Learning
- BERT
- VADER
Gallery
Sentiment Dashboard
Screenshot of the main dashboard displaying real-time sentiment trends for selected topics.
Project Overview
Overview section highlighting the ETL pipeline and sentiment analysis workflow.
Analytics View
Analytics page showing detailed sentiment breakdowns using BERT and VADER models.
API Documentation
Swagger interface for the FastAPI backend, documenting endpoints for sentiment data retrieval.
