All Topics
All Topics
Technology
Technology
Design
Design
Programming
Programming
Science
Science
News
News
Gaming
Gaming
Entertainment
Entertainment
Business
Business
Finance
Finance
Sports
Sports
Health
Health
Food
Food
Travel
Travel
Art
Art
Music
Music
Books
Books
Education
Education
Politics
Politics
Personal
Personal
No algorithm. No AI slop. No ads. Just RSS. Pro-human. Indie writers. Real journalism. Open web. Chronological. Hand toasted.

Quantifying Friendship: What 1.2 Million Messages Reveal About Connection and Decay

By

Vadim Drobinin

4d ago· 23 min readenInsight

Summary

A deeply personal essay about using data science and personal analytics to measure and understand friendship quality over time. The author imported 1.2 million messages from multiple social platforms into an Obsidian vault, using local LLM inference to analyze decay curves, vocabulary shifts, directional sentiment, and conflict rates in their relationships. The piece reflects on whether quantifying friendships can truly capture their meaning, inspired by Tim Urban's "Life in Weeks" grid, and grapples with the tension between data-driven measurement and the lived, emotional experience of being a friend.

Key quotes

· 3 pulled
The grid suggests it's the events that matter - jobs, trips, schools, marriages - and those are easy to mark. But they hardly tell how I felt during those weeks, or what I was like to the people around.
I started tracking things partly because of it - I wanted the grid to mean something, not just count down.
The biometric data is an odd representation of how fulfilling my life has been.
Snippet from the RSS feed
Importing 1.2 million messages from Telegram, VK, Instagram, Facebook, and Twitter into a structured Obsidian vault with local LLM inference - to measure how my friendships work with decay curves, vocabulary shifts, directional sentiment, and conflict rat

You might also wanna read