There has been some debate about the jittery gauge chart we used in our live election forecast. Rather than replying to dozens of tweets I decided to wrap this up in an old-fashioned blog post™. Feel free to add your thoughts to the comments.
It’s ok to use word clouds if your goal is to encourage reading of a large set of otherwise unrelated words that are connected to one or two interesting values (and word count in a text doesn’t qualify as interesting).
— gregor aisch (@driven_by_data) January 29, 2015
This I tweeted yesterday and now I feel that if I encourage the (dangerous) use of word clouds, I have to explain this exception in a little more detail. Why is it sometimes ok to use a widely rejected visualization method, and most times not?