2 Comments
User's avatar
Prince's avatar

I was glad to read "this all sounds common sense" right after I thought it 😄 just one question, do u know how that final social status clustering (5 groups) was done?

Expand full comment
Tommy Thompson's avatar

In the paper Lim discusses running n-dimensional clustering against four key 'features' they identified: Engagement Index, Tie Strength Index, Trader/Gamer Index, and Critic/Compliment index. These four features are groupings of key metrics extrapolated using Principle Component Analysis.

Expand full comment