Search:

This base data set is all user submitted, right? It isn't like it was regularly sampled over time, or a complete data set. So I would be careful trying to draw any conclusions comparing different time periods.

This base data set is all user submitted, right? It isn't like it was regularly sampled over time, or a complete data set. So I would be careful trying to draw any conclusions comparing different time periods.

Finally, I'd be interested in one more thing (promise this is it), for each player for each game the percentage of messages with at least one slur.

It is possible that racists die early (I certainly target them), so I'd want to normalize against a player's total messages in a game.

Finally, I'd be interested in one more thing (promise this is it), for each player for each game the percentage of messages with at least one slur.

It is possible that racists die early (I certainly target them), so I'd want to normalize against a player's total messages in a game.

I would be curious to look at this point further:
The top 1.89% of players based on number of slurs used contribute 89.20% of all slurs used

In what percentage of games from the data set are at least one of these 2% of players present in?

EDIT

Nevermind this was answered:

This method filtered out 30.19% of the games from the dataset (3257 out of 10790)

So 30% of games had one of these 2% in it.

I would be curious to look at this point further:
The top 1.89% of players based on number of slurs used contribute 89.20% of all slurs used

In what percentage of games from the data set are at least one of these 2% of players present in?

EDIT

Nevermind this was answered:

This method filtered out 30.19% of the games from the dataset (3257 out of 10790)

So 30% of games had one of these 2% in it.

This is good work. Like some of your prior work, this doesn't necessarily line up with my experience. I'd be curious to run a similar analysis on my own replays.

How are you identifying slurs?

I'd also note you aren't including player selected names themselves.

Additionally, I'd note that while you identify a small number of games with high slur rates, being in one of those games pretty much ruins it.

This is good work. Like some of your prior work, this doesn't necessarily line up with my experience. I'd be curious to run a similar analysis on my own replays.

How are you identifying slurs?

I'd also note you aren't including player selected names themselves.

Additionally, I'd note that while you identify a small number of games with high slur rates, being in one of those games pretty much ruins it.