I love the idea, but I'm a little bit surprised that you manage to have an accurate prediction with so few data and so much parameters.
I've try once to do something like that, I've ended with something extremly simple. The score of a news was: a bonus for the number of likes, a malus for the number of days, and a bonus/malus per domain. The domain bonus was auto adjusted when I readed a news.
Nonetheless, the best function in this reader was to remove the links I had already open. This allowed, each time I browsed the page, to only have new links to explore.
Nice.
You should add a really simple sample in the front page to explain how to play in a few word (or an image of a solved puzzle). It take me some time to understand that one cell equals one letter.
Ok there is a "How to play", but who read the faq?^^
The voucher do not cover alcoholic beverages [1]. That and the difficulty to code after drinking do that peoples generally do not drink during lunch. But yes, Frenchs take their time for lunch :)
It seems cool. Have you consider letting us trying the demo without asking for credential? The login form have stop me since I do not want to be contacted by your sales.
Probably because the "rust" keywoard hasn't yet the minimum mass to enter in the graph. It has only 6,000 questions* while only the tags with more than 20,000 are plotted.