You can add location information to your Tweets, such as your city or precise location, from the web and via third-party applications. You always have the option to delete your Tweet location history. Learn more
0 is not (necessarily) special -- not all charts need a y axis that starts at 0. Likewise, a ML model with 80% validation accuracy is not "pretty accurate" -- you shouldn't compare to 0%, you should compare to a common-sense baseline (that baseline may be arbitrarily high!)https://twitter.com/charlesarthur/status/999916180029587457 …
A common-sense baseline would the best score you could get on your validation dataset without actually looking at the individual samples. If you're looking at an imbalanced binary classification task, with 90% of your samples in class A and 10% B, then your baseline is 90% acc.
In that case a model that scores 92% is 100% more accurate than one that scores 91%. Don't start the comparison charts at 0!
And many tasks are hard for humans. I want to know baseline human performance, in addition to imbalanced data impact. Let's not forget about learning efficiency metrics while we are at it.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.
