Trang Tran

Hi, thank you for the quick response! I'm looking at the leaderboard on IEMOCAP [here](https://paperswithcode.com/sota/emotion-recognition-in-conversation-on). But in particular, several works most commonly cited evaluate using F1 on all 6 emotion...

@bagustris : In the table you pointed to, you're comparing different datasets though, not the different versions of IEMOCAP, unless I'm misunderstanding something. In any case, I wouldn't be surprised...

In a similar vein, it would be great to see some counterexamples (i.e. experiments that do significant testing but use the wrong test) -- like you mentioned in the paper's...