Thanks for the article! Very clear, informative, and transparent. Here are a few questions:

• From 2009 until mid-2018, comments could be flagged as "offensive". Happened for ~0.1% of all comments. Now we can flag comments as "unfriendly or unkind". When was the new flag introduced? (I guess in mid-2018?) How many comments are flagged as "unfriendly or unkind"? In your study with moderators and other users, the median person classified ~3.5% as "unfriendly". What was the average "unfriendly" flag percentage in that study? Did you try to measure how much of the difference between ~0.1% and ~3.5% is due to "unfriendly" being a broader criterion than "offensive"?

• Are you trying (or planning) to measure how the percentage of unfriendly comments affects user experience? Is there a correlation (which might indicate causation) between percentage of unfriendly comments and percentage of users who say they perceive Stack Overflow as unfriendly or unwelcoming?

• In my personal experience a scientific study (n=1) I found that I care more about how my contributions to a platform (e.g. Stack Overflow, Wikipedia, a forum...) are received (get upvotes, are deleted, get useful responses, ...) than about the tone of comments. Are you measuring how such experiences affect the impression of friendliness/unfriendliness of SO? If it turns out that users perceive downvotes, close votes or having their questions deleted as unfriendly, are you going to discourage such votes / actions?

Thanks for the article! Very clear, informative, and transparent. Here are a few questions:

• From 2009 until mid-2018, comments could be flagged as "offensive". Happened for ~0.1% of all comments. Now we can flag comments as "unfriendly or unkind". When was the new flag introduced? (I guess in mid-2018?) How many comments are flagged as "unfriendly or unkind"? In your study with moderators and other users, the median person classified ~3.5% as "unfriendly". What was the average "unfriendly" flag percentage in that study? Did you try to measure how much of the difference between ~0.1% and ~3.5% is due to "unfriendly" being a broader criterion than "offensive"?

• Are you trying (or planning) to measure how the percentage of unfriendly comments affects user experience? Is there a correlation (which might indicate causation) between percentage of unfriendly comments and percentage of users who say they perceive Stack Overflow as unfriendly or unwelcoming?

• In my personal experience a scientific study (n=1) I found that I care more about how my contributions to a platform (e.g. Stack Overflow, Wikipedia, a forum...) are received (get upvotes, are deleted, get useful responses, ...) than about the tone of comments. Are you measuring how such experiences affect the impression of friendliness/unfriendliness of SO? If it turns out that users perceive downvotes, close votes or having their questions deleted as unfriendly, are you going to discourage such votes / actions?

• What are the numbers for comments that got flagged both by humans and the robot in the two periods?