When You Fall in Love, This Is What Facebook Sees
“During the 100 days before the relationship starts, we observe a slow but steady increase in the number of timeline posts shared between the future couple.”
Like The Atlantic? Subscribe to the Daily, our free weekday email newsletter.
Facebook might understand your romantic prospects better than you do.
In a blog post published yesterday, the company’s team of data scientists announced that statistical evidence hints at budding relationships before the relationships start.
As couples become couples, Facebook data scientist Carlos Diuk writes, the two people enter a period of courtship, during which timeline posts increase. After the couple makes it official, their posts on each others’ walls decrease—presumably because the happy two are spending more time together.
In the post on Facebook’s data science blog, Diuk gives hard numbers:
During the 100 days before the relationship starts, we observe a slow but steady increase in the number of timeline posts shared between the future couple. When the relationship starts (“day 0”), posts begin to decrease. We observe a peak of 1.67 posts per day 12 days before the relationship begins, and a lowest point of 1.53 posts per day 85 days into the relationship. Presumably, couples decide to spend more time together, courtship is off, and online interactions give way to more interactions in the physical world.
You can see these data in the chart above. The number of wall posts climbs and climbs—until it tumbles when things become official.
The Facebook Data Science team has been releasing information all week about what the company’s massive trove of data reveals about relationships, from how long they last to how love correlates to religion and age. This is my favorite post of theirs, though—it shows something you grasp, I think, if you’ve ever seen a Facebook couple come into being.
Diuk also writes that, even though the number of wall posts goes down once the relationship starts, the wall posts becomes happier.
“We observe a general increase [in sentiment] after the relationship’s ‘day 0,’ with a dramatic increase in days 0 and 1!” he says. Here’s a chart describing that change:
Facebook
Sentiment analysis, as described above, is a far from perfect science. Robots are not very good at sarcasm. But it’s often interesting.
The data science team took other measures to improve its data. To weed out Facebook faux-relationships, it only looked at couples who “declared an anniversary date*” *between April 2010 and October 2013, not just those who changed their relationship status. For the sentiment analysis, it focused only on English-speaking users.
Latest Video
## When Art Becomes an Exercise in Vulnerability
A massive sculpture in Denmark becomes a way for people to collaborate and connect.
About the Author
Most Popular
Presented by
There aren’t many people like Michael Wear in today’s Democratic Party. The former director of Barack Obama’s 2012 faith-outreach efforts is a theologically conservative evangelical Christian. He is opposed to both abortion and same-sex marriage, although he would argue that those are primarily theological positions, and other issues, including poverty and immigration, are also important to his faith.
During his time working for Obama, Wear was often alone in many of his views, he writes in his new book, Reclaiming Hope. He helped with faith-outreach strategies for Obama’s 2008 campaign, but was surprised when some state-level officials decided not to pursue this kind of engagement: “Sometimes—as I came to understand the more I worked in politics—a person’s reaction to religious ideas is not ideological at all, but personal,” he writes.
“It’s all just an attempt to delegitimize Donald Trump.” That’s the argument you hear from Trump supporters each time new information comes to light about how hard Russian spy services worked to damage Hillary Clinton. You heard it again on Thursday.
The Trump supporters are 100 percent right: The information is delegitimizing. The president-elect of the United States reportedly owes his office in considerable part to illegal clandestine activities in his favor conducted by a hostile, foreign spy service. It’s hard to imagine a crisis of presidential legitimacy more extreme than that. But that’s no argument against airing this information. It’s precisely why the information must be aired.
Vladimir Putin took a fearful risk. If the Electoral College had taken a slightly different bounce on November 8, Putin would now be facing an enraged President-elect Hillary Clinton. Putin had every reason to expect that he probably would end up facing a President Clinton. Yet he took the gamble anyway, apparently doing something none of his Soviet predecessors had ever dared to do: mount a clandestine espionage and disinformation campaign on behalf of one candidate for U.S. president, and against another.
Over the next few weeks, The Atlantic will be publishing a series of responses to Ta-Nehisi Coates’s story “My President Was Black.” Readers are invited to send their own responses to hello@theatlantic.com, and we will post a sample of your feedback. You can read other responses to the story from Atlantic readers and contributors here.
I deeply dislike the man whose victory may vacate––who in some sense already has vacated––Obama’s legacy. I dislike that man as much as I can dislike anyone I never have and never will meet, and I condemn a great deal of what his partisans imagine he stands for.
But I have never hated President Obama. Not even a little. I found him frustrating and wrongheaded. And of course I wanted him to lose, twice. But I never doubted his basic honor, nor failed to appreciate the import of the very fact of his presidency. I watched with—is there such a thing as begrudging awe?—the jubilee in Chicago in 2008. I retweeted tiny Virginia McLaurin, born ten years before the 19th amendment and 45 before Brown vs. Board, dancing with the Obamas in the Blue Room. The breath caught in my throat when the little boy asked if he could touch the hair.
In the waning days of President Barack Obama’s administration, he and his wife, Michelle, hosted a farewell party, the full import of which no one could then grasp. It was late October, Friday the 21st, and the president had spent many of the previous weeks, as he would spend the two subsequent weeks, campaigning for the Democratic presidential nominee, Hillary Clinton. Things were looking up. Polls in the crucial states of Virginia and Pennsylvania showed Clinton with solid advantages. The formidable GOP strongholds of Georgia and Texas were said to be under threat. The moment seemed to buoy Obama. He had been light on his feet in these last few weeks, cracking jokes at the expense of Republican opponents and laughing off hecklers. At a rally in Orlando on October 28, he greeted a student who would be introducing him by dancing toward her and then noting that the song playing over the loudspeakers—the Gap Band’s “Outstanding”—was older than she was.
Facebook might understand your romantic prospects better than you do.
In a blog post published yesterday, the company’s team of data scientists announced that statistical evidence hints at budding relationships before the relationships start.
As couples become couples, Facebook data scientist Carlos Diuk writes, the two people enter a period of courtship, during which timeline posts increase. After the couple makes it official, their posts on each others’ walls decrease—presumably because the happy two are spending more time together.
In the post on Facebook’s data science blog, Diuk gives hard numbers:
During the 100 days before the relationship starts, we observe a slow but steady increase in the number of timeline posts shared between the future couple. When the relationship starts (“day 0”), posts begin to decrease. We observe a peak of 1.67 posts per day 12 days before the relationship begins, and a lowest point of 1.53 posts per day 85 days into the relationship. Presumably, couples decide to spend more time together, courtship is off, and online interactions give way to more interactions in the physical world.
How do you advertise a car that journalists describe as “sturdy, if drab”?
That was the question faced by Subaru of America executives in the 1990s. After the company’s attempts to reinvigorate sales—by releasing its first luxury car and hiring a hip ad agency to introduce it to the public—failed, it changed its approach. Rather than fight larger car companies over the same demographic of white, 18- to 35-year-olds living in the suburbs, executives decided to market their cars to niche groups—such as outdoorsy types who liked that Subarus could handle dirt roads.
In many ways, 2016 has been the strongest year, economically, since the mid-2000s, or even the late 1990s. Unemployment was low. Wages were increasing. The markets hit new highs. Consumer confidence rose. Yet Donald Trump unseated the incumbent party and won the presidential election promoting economic pessimism and promising restoration: He swore to Make America Great Again, describing the country as falling behind, workers as jilted, growth as anemic, and the current period of expansion as a sham.
How could a message like Trump’s take hold in an economy like that? The answer is that it did not take hold with everyone—or, more to the point, everywhere. In ways that have been overlooked and under-appreciated for years, the strength of the post-recession recovery has varied dramatically not just from income bracket to income bracket, but from place to place as well. And it so happens that the places left behind are also places that wield outsized political power—enough power to vault the loser of the popular vote to the presidency and to make the economic story of 2016 more about stagnation, failure, and the dissolution of the American dream than it was about the headline economic numbers.
Gone are the days of explaining what a podcast is: The arrival of money to the form and a continued increase in listenershas led to another banner year and the premiere of hundreds of shows to suit any listener’s audio preferences. Whether it’s entrepreneurial advice, video game breakdowns, or candid looks at celebrities, if you know what you want, there’s likely a show that offers exactly that. Finding them, though, can be a trial-by-fire enterprise that requires serious listening hours. The following shows don’t require you to love a certain movie or have a particular sense of humor. They don’t force you to become best friends with the host or listen to five episodes before you pick up on the “in” jokes. We’ve chosen the 50 best podcasts of 2016 based on their innovation this year, consistent high quality, excellence within their genre, and of course, entertainment value.
Michael McFaul, Barack Obama’s ambassador to Russia from 2012 to 2014, has a blunt assessment of the actions that his former boss took against the Russian government this week. The sanctions on Russian intelligence officers and organizations, along with the expulsion of Russian intelligence officials and closing of Russian compounds in the United States, is “not going to change” Russian President Vladimir Putin’s behavior, he told me shortly after the measures were announced. Obama’s retaliation—at least the retaliation that the U.S. government has made public—isn’t sufficient to deter the Kremlin from interfering in future U.S. elections, he said.
But in naming and punishing specific Russian agencies and individuals over the hack and leaks of Democratic emails, the president has, McFaul hopes, put to rest the “debate about whether the Russians were interfering in our presidential election.” Which is why he’s so frustrated by Donald Trump’s continued insistence that the country “move on” from the Russian cyber campaign. That campaign represents a threat to the sovereignty President Trump will be sworn to protect, he said. One message of Obama’s actions, McFaul added, is that this threat didn’t disappear on Election Day, and it won’t disappear on Inauguration Day. The standard way to understand a threat is to evaluate intent and capability to cause harm. And in the cyber domain, McFaul explained, Russia has both in spades. What distinguishes Putin from other world leaders is that he’s “not afraid to use this stuff.”
In 1995, if you had told Toby Spribille that he’d eventually overthrow a scientific idea that’s been the stuff of textbooks for 150 years, he would have laughed at you. Back then, his life seemed constrained to a very different path. He was raised in a Montana trailer park, and home-schooled by what he now describes as a “fundamentalist cult.” At a young age, he fell in love with science, but had no way of feeding that love. He longed to break away from his roots and get a proper education.
At 19, he got a job at a local forestry service. Within a few years, he had earned enough to leave home. His meager savings and non-existent grades meant that no American university would take him, so Spribille looked to Europe.
- In a short animation, Barack Obama speaks with Ta-Nehisi Coates about his road to the White House.