Google Blocks Spam Using AI Tools - InformationWeek

InformationWeek is part of the Informa Tech Division of Informa PLC

This site is operated by a business or businesses owned by Informa PLC and all copyright resides with them.Informa PLC's registered office is 5 Howick Place, London SW1P 1WG. Registered in England and Wales. Number 8860726.

Software // Information Management
11:13 AM

Google Blocks Spam Using AI Tools

Google taps its AI advancements, including neural networks, to help Gmail combat spam and block malicious email.

10 Great Websites For Learning Programming
10 Great Websites For Learning Programming
(Click image for larger view and slideshow.)

Google champions its own antispam powers. The company claims that less than .1% percent of email in the average Gmail inbox is spam, and that the amount of wanted mail landing in the spam folder is even lower, at less than .05%. Still, that hasn't stopped the company from fine-tuning its artificial intelligence (AI) tools to stop spam.

The company revealed some of the new ways it is supporting the senders of wanted mail, including the launch of Gmail Postmaster Tools. It's also using the latest Google smarts to filter out spam

These tools help qualified high-volume senders to analyze their email by showing data on delivery errors, spam reports, and reputation, so they can diagnose any hiccups, study best practices, and help the company's mail app route messages to the right inbox.

"Gmail users get lots of important email from companies like banks and airlines—from monthly statements to ticket receipts -- but sometimes these wanted messages are mistakenly classified as spam," Sri Harsha Somanchi, Google's product manager for Gmail, wrote in a blog post. "When this happens, you might have to wade through your spam folder to find that one important email (yuck!). We can help senders to do better."

(Image: alengo/iStockphoto)

(Image: alengo/iStockphoto)

In addition to the Postmaster Tools, the company also unveiled improved intelligence developed for the company's Search and Now applications to make the spam filter smarter in a number of ways.

Advances in machine learning mean the spam filter can now reflect individual preferences, so that users who love weekly newsletters aren't confused with those who loathe them.

On an even more sophisticated level, the spam filter now uses an artificial neural network -- the same AI technology that's been blowing minds with reconfigured classic works of art -- to detect and block the sneaky spam that could pass for wanted mail.

The overall notion of machine learning and AI has been making a lot of news lately, while some notable visionaries, including Bill Gates, harbor doubts. Others have praised the technology's potential for creating jobs.

[Apple has high expectations for its next device. See Apple's New iPhone Order Will Be Massive.]

Anyway, back to the more mundane challenges of cleaning up a Gmail inbox. Google is also deploying new machine learning signals that help the application figure out whether a message actually came from its sender and keep bogus email at bay -- things that could help stamp out insidious phishing scams.

Unwanted or useless email continues to be a major problem for many US businesses and their employees -- the biggest hindrance to everyday email use, according to 45% of those surveyed in a June GFI report, is spam.

Nathan Eddy is a freelance writer for InformationWeek. He has written for Popular Mechanics, Sales & Marketing Management Magazine, FierceMarkets, and CRN, among others. In 2012 he made his first documentary film, The Absent Column. He currently lives in Berlin. View Full Bio

We welcome your comments on this topic on our social media channels, or [contact us directly] with questions about the site.
Comment  | 
Print  | 
More Insights
Newest First  |  Oldest First  |  Threaded View
User Rank: Apprentice
7/12/2015 | 4:58:10 AM
Re: Controversy
Well, I think Google should make a choice (but I think it's already done for next few years), spammers works for Google but they are also their major challenge. It's to a too big search engin to be safe. You cannot control all of web actors and some of them believe that we still are in 1990 ! 
User Rank: Ninja
7/11/2015 | 1:31:43 PM
While machine learning may be controversial, it's not going away. Especially when it can help solve the problems of spamming. I'm hoping to see machine learning used to eliminate other negative aspects of technology. Namely, I'd like to see phishing and scamming reduced with the use of AI. That would be cool. 
10 Top Cloud Computing Startups
Cynthia Harvey, Freelance Journalist, InformationWeek,  8/3/2020
How Enterprises Can Adopt Video Game Cloud Strategy
Joao-Pierre S. Ruth, Senior Writer,  7/28/2020
Conversational AI Comes of Age
Guest Commentary, Guest Commentary,  8/7/2020
White Papers
Register for InformationWeek Newsletters
Current Issue
Special Report: Why Performance Testing is Crucial Today
This special report will help enterprises determine what they should expect from performance testing solutions and how to put them to work most efficiently. Get it today!
Flash Poll