JRE Recommender

Overview

Tagged and analyzed 2,000+ Joe Rogan Experience episodes by guest, topic, and user interest, then built a Telegram bot and a React web app that surface the episodes a listener would want.

The Problem

With 2,000+ episodes covering everything, finding the right JRE episode is hard. Nothing out there matched guests and topics against what a listener wanted.

My Role

Sole author. Built the pipeline from episode tagging and data cleaning through the recommendation logic, the Telegram bot, and the Flask-backed React interface.

Key Features

• —Dataset of 2,000+ episodes tagged by guest, topic cluster, and content type
• —Recommendation engine matching user interests to relevant episodes
• —Telegram bot interface with 150+ active users/month
• —React + Flask web interface for browsing and filtering
• —Pandas-based data pipeline for episode processing and tag management

Challenges

Creating a tag taxonomy broad enough to be useful and specific enough to return relevant results. Too coarse and recommendations are random; too granular and nothing matches.

What I Learned

Next time I'd let users correct the tags. I wrote the taxonomy alone, so every recommendation rested on my own guess about what counts as a topic.