Gmail Wrestling Spam Into Submission

Email used to be the "killer app" at the dawn of the Internet age - some readers may be too young to realize it, but back in the day email was a very cool concept.  Think of the ability to reach out around the world, essentially for free and pretty much instantly at a time when Air Mail or invoking international phone call rates were the only other options.
Of course, the scourge of spam email put a huge dampener on the initial excitement; the whole email thing became a bit of a chore, and then potentially dangerous when suspect links would take people to all manner of "delights" that would steal their personal information or render their PC inoperable in some manner.

We are getting better at spam filtering, even though it still seems a lot like a game of whack-a-mole. The process always seemed to me to be more art than science anyway, and I can recall priming up Bayesian spam filter software with "spam samples" back in the day.

Now, with the benefits of "artificial intelligence", we may be getting a better handle on things. Indeed, Google is touting an impressive percentage of spam being caught due to their implementation in their Gmail application:
Continuing its efforts to bring AI into every little product it has, Google announced today that improvements it made to Gmail's machine learning algorithms help it detect and block spam and phishing messages with an accuracy of 99.9%.
To put things into perspective, the company says spam messages account between 50% and 70% percent of emails Gmail users receive on a daily basis.
We may be starting to see email as it was meant to be again, except that many of us have moved on to texting and social media as the preferred quick method of communicating . . .

No comments :