There were so many stories that came out of Rio but what I enjoyed the most from the SmartNews Rio Olympics page were the lesser reported stories that bubbled up on the page. Over the past couple weeks I kept a list of my favorites and below are the best.
ONE: Before the games even started, The Independent’s incredible profile of Yusra Mardini had us rooting for the Olympic’s first refugee team.
TWO: During the opening ceremonies everyone looked sharp but USA Today’s sports site, For The Win, caught wind of the secret hidden in Team Australia’s blazer lining. Elle gave us the skinny on what each athlete got in their swag bag.
SIX: Sharing the thrill of victory is why we all love to watch the Olympics. Deadspin shares a clip of two young Irish rowers doing an interview on Irish television and it’s hard not to get caught up in their youthful exuberance.
SEVEN: No one can forget the fateful collision of Abbey D’Agostino and Nikki Hamblin during the 5000 meter qualifying round. The story of the two helping each other to the line will remain in our hearts as a shining example of Olympic Spirit. The pair was later awarded the prestigious Pierre de Coubertin medal for their behavior – something that The Telegraph tells us has only happened 17 times in Olympic history.
We all saw Steph Curry’s game-winning basket to win against Oklahoma in overtime…in the last second…while running down the court…shooting from a few feet inside half-court…and swishing a three pointer…to tie the NBA record for most three-pointers in a single game.
So this morning we launched a Basketball channel on SmartNews. The stories that make it into this channel are driven by an algorithm that reads through millions of articles each day and “knows” if a story is about basketball and places it there. Part of the challenge of teaching this algorithm is that it takes a training set of articles to “teach” it what collection of words, phrases, and headlines make up a basketball story and uses that pattern when it looks for new stories to add to the collection.
The beauty of this once you get it right is that once it’s working, the discovery process is really almost like magic. As it happens, right when we turned it on, SmartNews immediately discovered a story about Steph Curry in the literary magazine, The Paris Review.
It is in this way, SmartNews discovers new content for it’s readers who may not know what the Paris Review thinks of basketball. And in turn, SmartNews brings a new audience of readers to the Paris Review magazine, an audience beyond their usual core audience. Discovery on both ends, that’s what makes SmartNews an engine for the curious.
So let’s look at that game-winning three-pointer as a work of art. Suffering—as Auden wrote in his study of Brueghel, “Musée des Beaux Arts”—is a “human position” to understand. You might find it at the center of the scene or at the periphery, but even if it’s not front and center, it’s there: “the dreadful martyrdom must run its course / Anyhow in a corner … ” Look to one corner of Curry’s canvas and you’ll spot Andre Roberson, a role player who earns his roster spot playing defense, doing exactly what the textbook tells you to do: he tried to hustle back to the three-point line in order to position himself to defend from there. But Curry’s frame of reference is neither the arc painted on the court, nor Roberson’s, nor the textbook’s. As Roberson backtracked, his body betrayed its doubt about what it should be doing. His are the motions of someone in a high-leverage situation who’s unsure whether to step back or step up, unsure if he’s defending the past or the future.
We all remember the biggest stories of 2015, El Chapo’s escape, Ronda Rousey’s KO, and who can forget The Dress? In the spirit of discovery, we at SmartNews would like to highlight the stories that you might have missed. Following on the hidden gems theme, I took a look at each of the SmartNews categories and looked for the outliers. My somewhat unscientific methodology looked for stories from sources that would not normally appear in the category but were picked up and featured based on a topic analysis, hopefully introducing a source to a new audience that would not normally be exposed to that publication.
GQ describes itself as a men’s fashion and style magazine. When Marshall Sella tests the Bitcoin waters, SmartNews puts his piece in front of the Business readers. Marshall describes his time with Charlie Shrem, an early Bitcoin entrepreneur (bitrepreneur?) whose LinkedIn profile now shows him cooling his heels at Lewisburg Federal Prison.
It’s not often that Scientific American shows up in the Entertainment section. Cindi May’s The Problem with Female Superheroes took a look at how characters such as Storm and Dazzler in the recent X-Men films may be adversely affecting the young audiences who watch them. “Saving the world in spiked heels” may not be giving young girls a realistic expectation of their abilities. We hope the upcoming Dawn of Justice does a better job.
We all cringed when we saw the video of the 12-year-old boy who tripped and punched a hole in the 350-year-old painting valued at $1.5 million. Oliver Holms of The Guardian covers the restoration effort (thankfully it was insured) and points to other mishaps such as when a pair of Qing dynasty Chinese vases and a Picasso did not fare as well. SmartNews placed this one in the Lifestyle section which is where our Art & Culture are featured.
“I thought it was a CIA surveillance device,” said Brett McBay in Modesto, California after instructing his son to shoot his neighbor’s drone from out of the sky with a 12-gauge shotgun. Cyrus Farivar at Ars Technica brought up a number of issues including the right to privacy (the skies around your home) and the respect for private property, (Eric Joe’s homemade hexacopter drone), and of course the right to fire off buckshot into the sky. SmartNews to placed this story into the US category where much of our gun violence stories have been running. Inquiring minds want to know if this Brett McBay of Modesto is the same Brett McBay whose twitter profile states he is the District Representative for a California State Assemblymember.
SB Nation covers sports and, yes, there is a basketball in this bit but it’s used to explain the Magnus Effect from physics and, for that reason, this article showed up in Science.
The Nation likes to dig (and sometimes poke) which usually lands them in the US section for political coverage. Back in May, Dave Zirin asked why mainstream sports sites were not covering the case of NBA player Thabo Sefolosha, who was tackled by NYPD outside a nightclub, injured, and subsequently missed the playoffs with his team. This story introduced Sports readers to The Nation style of media inquiry. Seven months later ESPN published an in-depth investigative piece on this same story.
SmartNews has built a sophisticated, duplicate content filter so that when the latest press release from a presidential candidate, disaster, crime, or culinary sensation hits the proverbial viral loop, the breaking news from multiple outlets does not overwhelm the app and crowd out other stories. SmartNews strives to promote only the best and unique stories to our readers.
But there are times when you want to dig deeper on an issue or read an alternative take. Introducing the Recommended widget.
You can find the Recommended widget at the bottom of the SmartView of any article in the SmartNews app. Swipe left on any article to get to the simplified SmartView of that article. Scroll down to the bottom of the article to get to the Recommended widget.
The first three headlines (in purple) are from the publisher of the original piece (Rolling Stone). If the publisher has continued coverage of the story, you’ll see past stories about the topic giving you deeper context around what you just read. In this example, there is a link to an earlier story about the auction followed by an interview with Ringo Starr and then a piece about The Beatles and their album Rubber Soul.
The bottom two headlines (in green) are culled from our daily crawl of 10 million+ headlines and matched entirely based on a custom SmartNews algorithm. Here we see two other stories about the Ringo Starr auction, one from The Guardian and the second from NME.
How do we do it? That sophisticated de-dupe filter we built to reduce articles that are too much alike? Turn it around and it makes a fantastic related-articles algorithm!
Each article is automatically “read” and key terms, companies, people, and other entities are extracted along with data around the author, publisher, length of the piece and many other factors that are used to make a data representation of the article. When two representations overlap significantly we give them a similarity score. The higher the score, the more similar the two articles are for the purposes of filtering or recommending.
I like to think of the Recommended widget as a jumping off point for further exploration. Headlines 1-3 go deeper into the past with a specific source while headlines 4 & 5 go broader along the same topic but across different publications. Choose your adventure.
The similar articles feature is not new. I use a WordPress plugin on this blog to power the Related box you see below each post. Most news sites have something similar, usually driven by keyword or tag matching, against a limited content set. SmartNews has a more sophisticated matching algorithm across a much broader universe of articles and I think you’ll notice the difference right away.
There are at least two sides to every story. The Planned Parenthood videos were a polarizing topic that monopolized the news cycle several weeks ago. How do you teach an algorithm a point of view? How do you optimize for discovery and strike the right balance for diversity while avoiding duplication?
SmartNews is a news aggregation app driven by machine learning algorithms. The platform is tuned for discovery (as opposed to personalization). After using it regularly, I began collecting screenshots of my favorite examples when the app taught me something new or showed me two items side-by-side that suggested a subtle intelligence.
The science and application of artificial intelligence to personalization is well understood. From Amazon’s people-that-bought-this-also-bought-that to Pandora’s Music Genome Project, software has been recommending what you’ll like next best based on what you’ve liked so far for years.
The new frontier in artificial intelligence is machine learning. Companies such as Spotify and Netflix are hard at work trying to predict future tastes based on an evolving understanding of collective tastes. Sure, learning assumes knowledge of the past, but projecting that learning into the future is much harder as you build a model based on an understanding of something that does not exist. Rather than showing you something we know you’ll like based on what you liked in the past, machine learning discovers things you didn’t know you would like.
First a little context. SmartNews, while deceptively simple, has a lot going on under the hood. At any time, the SmartNews app shows around 250 headlines across 8 categories. These headlines are selected from millions of stories that are scanned each day. In order to ensure that the stories featured in the app are the most important and interesting, a number of things must take place.
After harvesting URLs, the text of each article is run through a classifier that examines things such as the headline, author byline, publication date, images and video embeds. These pieces are analyzed by a semantic engine that extracts data so the algorithm can map the article to a topic cluster and place it into the appropriate subject category. (I wrote about how this is done in an earlier post)
Importance estimation is where we rank an article and determine where it will go in the app relative to other articles. Does it go towards the top of a section or towards the bottom? If the top, does it deserve featured treatment? Maybe it’s so topical it needs to be pushed to the Top page, which is reserved for only the most important stories of the moment.
Finally, diversification ensures there is a good mix of stories in each category. If there are 40 stories about guacamole and peas, here’s where we determine which to show and which to push to the background. If there’s a new development on a story, the update will push its way in and take prominence over an older story.
These are just details to give you context. The most amazing thing to me is when the app surfaces a “hidden gem” that I would not normally run across if I were using an RSS reader hard-coded to a collection of feeds, or a social network that is limited to news shared by my friends.
The best way to appreciate SmartNews as a discovery engine is to use it daily, but if you haven’t had a chance, here are a few more of my favorite Gems below:
While the Center for Medical Progress’ undercover video interviews with Planned Parenthood staffers may have been shocking, the representation of two points of view helped me see both sides of the issue. What was interesting was the Cosmopolitan article (a source I normally do not read) had the best measured rebuttal.
Much of the climate change news ends up in the Science category. As that story grows in relevance to us all, more publications dig into it. If you haven’t read this terrifying Rolling Stone piece, read it now.
Here’s an example of a developing story getting an update. ESPN reports that WWE is cutting its relationship with Hulk Hogan his comments that were offensive. People Magazine follows up with the story of his apology. Oh, also notice that the algorithm put both stories into the Entertain section.
As news of the killing of Cecil the Lion went viral, the algorithm was smart enough to surface a side of the story from a local Minnesota paper.
The screenshot above, more than any of the others, shows the freaky intelligence working behind the scenes. Like those times when an algorithmically generated playlist just nails the transition of one song into the next, drawing the causality between gun violence in the US to how such an environment might have prepared an off-duty soldier to do the right thing shows how a well-designed system can be greater than just the sum of its component parts.
Do you use SmartNews? Have you had the same experience? Send along some of your own Hidden Gems and I’ll add them to the gallery.