22 3 / 2010
Data Mining For My Own Kinsey Report
Turns out you can do some pretty nifty (… or just geeky) things with Google Spreadsheets. Google will give you number of search engine results for that particular query. Spent the weekend updating proposals and adjusting KPI’s for clients; I was still in a numbers nerd mode while taking a break while playing with it. You program in some variable phrase and another column for value of that variable. The value doesn’t necessary have to be a number, but you can if you want it to plot out a graph easier. Very interesting to run “I never…” and put in “whatever” action and compare it to “How to…” with “whatever” action. Yes, you can put in “whatever” NSFW action in there, and get higher number of results than for more PG actions. ”I never been in a threesome” had way more search engine results that “I never got a tatoo” or “I never ate a dog” (hey, I live in Asia). Anyways, I thought I’d data mine and compare “I lost my virginity at x” to “I’m a x year old virgin.”
I was surprised to see that people searched for “I lost my virginity at 15” the most and “at 14” was higher than “at 22.” Kids are getting busy a lot younger these days. While “I’m a 20 year old virgin” had the most results.
Then I also was curious to see how many boyfriends a girl claims vs how many girlfriends a guy claims…
Most girls said they had 4 boyfriends, while guys say 2 girlfriends. Most people has had in between 2-6 sexual partners. Not precise by any means, but does help you see trends.
You can run queries like “My IQ is”, “I make $”, “I’m a ‘x’ cup”, “I run ‘x’ miles everyday”, “I have ‘x’ cats”, “I did ‘x’ shots”, “I’m a ‘x’ waist” and other useless trivial knowledge queries.
