> I'm thinking of adding labels to the stories that fell out of the news cycle along the bottom of the chart.

I think it would be interesting to manually tag various events and then see if there is any temporal correlation between tags of certain types over long periods of time - for example: political scandals may coincidentally be commonly followed shortly by "social" scandals.

LOTS more could be done in this space, especially if one isn't too concerned for their health if you know what I mean.