zlacker

If you're trying to use the SPAM model as some kind of example of success I believe you may have already failed.

In SMTP servers I've managed for clients we typically block anywhere from 80 to 99.999% (yes 10000 blocked to one success) messages. I'd call that MegaModeration if there was such a term.

And if you think email spam is solved then I don't believe you read HN often as there is a common complaint of "Gmail is blocking anything I send, I'm a low volume non-commercial sender"

In addition email filtering is extremely slow to react to new methods, generally taking hours depending on the reporting system.

Lastly, you've not thought about the problem much. How are you going to rapidly detect the difference between a fun meme that spreads virally versus an attack against an individual. Far more often you're going to be blocking something that's not a bad thing.

>>pixl97+(OP)
Fair concerns but I have trained a Naive bayes classifier on twitter data in the past using [1] a social study of categorised tweet to train the classifier and got around 85% accuracy. It was able to detect and properly classify rape threats as abusive but conversations about rape seed oil as non abusive. Considering the small data set and how little entropy there is between samples I consider it pretty useful.

I get that no machine learning is 100% perfect which is why it should be used as an indicator rather than the deciding factor.

I have had issues with gmail blocking emails but as you point out it was always because of ip reputation not over zealous Naive Bayes.

[1] https://demos.co.uk/press-release/staggering-scale-of-social...

>>danger+mI
Training classifiers can also go off the rails under adversarial attack. This commonly showed up in our systems when people sent short emails that were more ambiguous. For example this tends to cause problems where malevolent users adopt dogwhistles co-opting the language of the attacked group. The attacked group commonly becomes the ones getting banned/blocked in these cases