Google’s spam sorting has more than 30 percent false positives: Linux chief

Linux kernel supremo Linus Torvalds has written an open letter to Google’s Gmail team mentioning the amount of hardships he had to go through because of the faulty spam filtering algorithm on Gmail. He has mentioned that he had to go through over 3,000 emails in his spam folder to only figure out that there were almost 30 per cent false positives. More than 1,200 mails were found to genuine and he had to go through each one of them to mark them as ‘not spam’.

A report on The Register mentions the Google-Linus story. The kernel expert uses Gmail to go about most of his business, coordinating his Linux Kernel development from his herd of global developers. He has also mentioned that the Gmail spam filter has caused him a disaster.

Just a few days ago, Google claimed that their spam filter is efficient enough and reports false positives down to less than 0.05 per cent. However, Linus claims in the opposite direction stating that almost 30 per cent of his emails were marked as spam. "It's actually at the point where I'm noticing missing messages in the email conversations I see, because Gmail has been marking emails in the middle of the conversation as spam. Things that people replied to and that contained patches and problem descriptions," Torvalds wrote.

Linus states that the issue seems more recent, as early as July 13, because he has been subscribing to thousands of mailing lists and only recently they are being marked as spam, even in between an existing email thread. "The problem really is that clear, that I can tell pretty much when it started," he wrote.

Linus made a statement to Google, mentioning, "You dun goofed. Badly. Get your shit together, because a 20 per cent error rate for spam detection is making your spam filter useless."