Jack Dorsey Shed Some Light on How Twitter Uses Machine Learning, Deep Learning on Its Timeline

Twitter CEO Jack Dorsey discussed how the social network is using machine learning and deep learning to populate its timeline during the company’s annual shareholders’ meeting conference call Monday. Dorsey said showing Twitter users what’s happening and delivering them the news of the day is the social network’s “singular job,” and he discussed changes to the timeline over the past year-and-a-half: This is where people spend almost all of their time on Twitter. This is where they get all of their news, see everything that's going on, see what people think about what's going on. And for the longest time, it just hasn't been personalized. It's been completely ordered by recency. So if you weren't there to catch it while it happens, you probably missed it. We took a big step last year when we started injecting a lot more relevance into the timeline, so that when you came back to Twitter, you saw what mattered and you saw it really, really quickly and it was custom-tailored for you. That doesn't mean that everything else goes away. It just means that we're going to make sure that we're honoring people's time, and we're delivering that content to them that matters to them as fast as possible and in a meaningful way. This is also the first time we really applied machine learning to the timeline. And we've gotten better and better at applying machine learning and deep learning, which are both disciplines within a broader discipline called AI, artificial intelligence, that allows us to deeply personalize the experience for each individual. He then went into more detail on the use of machine learning and deep learning when it comes to Twitter’s timeline: There's lots of room to better this timeline, and the team has a very significant road map ahead to get this more and more relevant and to get it better and better. When you're not in the application, we want to make sure that we are the first place that you see on something that matters, and the way to reach you is actually a notification. So we've been applying a lot of deep learning to notifications to alert you to exactly what's going on, what matters and kind of like being a little bird that flies on your shoulder and tells you, "Hey, this is happening, this is going on." You go into the app and you see exactly what's happening and, more important, see what people think about it, as well. We have some of the greatest deep learning experts in the world, and a lot of their work is making this better every single day. One example of this that shows some of the potential that we have is not too long ago, there was a protest that started in the Embarcadero and made its way up to Civic Center. And it took about an hour to get up right in front of these offices. And I heard the protest, I looked out the window and I saw all these protesters. And then I went to Twitter and then I searched and I looked for that protest, and we had people tweeting about the start of the protest an hour prior. Now we could have been much faster to notify people and notify me in particular that that was happening and that it was coming my way. That is the power of what we have. And that's just one event that's happening in the physical world. You can imagine that for any topic, anything that you care about, we can deliver you the news first about what's going on and why it's important. Image courtesy of Jack Dorsey’s Twitter account.

Social Pro Daily

Jack Dorsey Shed Some Light on How Twitter Uses Machine Learning, Deep Learning on Its Timeline

The CEO said delivering the news of the day is Twitter's 'singular job'

David Cohen

About

Subscriptions

Events

Publications

WORK SMARTER - LEARN, GROW AND BE INSPIRED.

Subscribe today!

David Cohen