CLOSE
Original image
Getty Images

4 Things Facebook Has Learned From Your Relationship Status

Original image
Getty Images

Facebook has a lot of data about its users, and it also has a data science division dedicated to transforming all that data into interesting information. In 2014, the company publicized a series of studies around the topic of love. While many of the results match up well with our expectations (e.g., people tend to marry within their religion), not all of them were so obvious. Here are some things Facebook has learned from looking at your relationship status.

1. The age difference between same-sex couples is larger

It was not too surprising to find that in male-female pairings the male is generally older (by an average of 2.4 years), or that in countries that scored worse on an index of gender equality, the age gap was wider (5.09 years in Egypt). However, despite the fact that same-sex couples don't have to contend with the same cultural expectations about gender and age, the age gap tended to be wider for those couples, reaching an average of 8 or 9 years at points.

2. People break up in the summer


So you've both changed your statuses and made it official. How long is it likely to stay that way? Facebook found that the biggest predictor of how likely you are to stay together is how long you've been together already. For each month that passes, the probability of breaking up decreases. Not so surprising. But there were some interesting cyclical effects related to the timing of breakups, as seen on the graph. Summer seems to be the time for breakups. The extra large increase in breakups for the summer of 2011, may have something to do with the economic recovery.

3. If you want to get into a relationship, Colorado Springs is the place to be


It might seem like the best place for a single person to find a relationship would be a city where there were lots of other single people, but that's not necessarily the case. Cities that had the most single people (Detroit, Los Angeles, New York, Miami, and Memphis) also had low rates of relationship formation. Colorado Springs had the highest rate of relationship formation, followed by El Paso, Louisville, Fort Worth, and San Antonio. As Facebook data scientist Mike Develin put it, " in a city where everyone is paired up, the incentive to pair up is even stronger, while cities like New York and Miami are places that people go to be single."

4. Getting dumped can really kick start your Facebook interactions

The data science team looked at people "who were on the receiving end of a separation"—they had been in a relationship for at least four weeks when their partner switched their relationship status to "Single." The number of interactions, including messages, posts, and comments received, showed a big spike on the day of separation, followed by an overall increased level of interaction that lasted for weeks afterwards. Facebook friends may not be the same thing as real-world friends, but they sure can come through for you when you need a boost.

Original image
iStock // Ekaterina Minaeva
arrow
technology
Man Buys Two Metric Tons of LEGO Bricks; Sorts Them Via Machine Learning
May 21, 2017
Original image
iStock // Ekaterina Minaeva

Jacques Mattheij made a small, but awesome, mistake. He went on eBay one evening and bid on a bunch of bulk LEGO brick auctions, then went to sleep. Upon waking, he discovered that he was the high bidder on many, and was now the proud owner of two tons of LEGO bricks. (This is about 4400 pounds.) He wrote, "[L]esson 1: if you win almost all bids you are bidding too high."

Mattheij had noticed that bulk, unsorted bricks sell for something like €10/kilogram, whereas sets are roughly €40/kg and rare parts go for up to €100/kg. Much of the value of the bricks is in their sorting. If he could reduce the entropy of these bins of unsorted bricks, he could make a tidy profit. While many people do this work by hand, the problem is enormous—just the kind of challenge for a computer. Mattheij writes:

There are 38000+ shapes and there are 100+ possible shades of color (you can roughly tell how old someone is by asking them what lego colors they remember from their youth).

In the following months, Mattheij built a proof-of-concept sorting system using, of course, LEGO. He broke the problem down into a series of sub-problems (including "feeding LEGO reliably from a hopper is surprisingly hard," one of those facts of nature that will stymie even the best system design). After tinkering with the prototype at length, he expanded the system to a surprisingly complex system of conveyer belts (powered by a home treadmill), various pieces of cabinetry, and "copious quantities of crazy glue."

Here's a video showing the current system running at low speed:

The key part of the system was running the bricks past a camera paired with a computer running a neural net-based image classifier. That allows the computer (when sufficiently trained on brick images) to recognize bricks and thus categorize them by color, shape, or other parameters. Remember that as bricks pass by, they can be in any orientation, can be dirty, can even be stuck to other pieces. So having a flexible software system is key to recognizing—in a fraction of a second—what a given brick is, in order to sort it out. When a match is found, a jet of compressed air pops the piece off the conveyer belt and into a waiting bin.

After much experimentation, Mattheij rewrote the software (several times in fact) to accomplish a variety of basic tasks. At its core, the system takes images from a webcam and feeds them to a neural network to do the classification. Of course, the neural net needs to be "trained" by showing it lots of images, and telling it what those images represent. Mattheij's breakthrough was allowing the machine to effectively train itself, with guidance: Running pieces through allows the system to take its own photos, make a guess, and build on that guess. As long as Mattheij corrects the incorrect guesses, he ends up with a decent (and self-reinforcing) corpus of training data. As the machine continues running, it can rack up more training, allowing it to recognize a broad variety of pieces on the fly.

Here's another video, focusing on how the pieces move on conveyer belts (running at slow speed so puny humans can follow). You can also see the air jets in action:

In an email interview, Mattheij told Mental Floss that the system currently sorts LEGO bricks into more than 50 categories. It can also be run in a color-sorting mode to bin the parts across 12 color groups. (Thus at present you'd likely do a two-pass sort on the bricks: once for shape, then a separate pass for color.) He continues to refine the system, with a focus on making its recognition abilities faster. At some point down the line, he plans to make the software portion open source. You're on your own as far as building conveyer belts, bins, and so forth.

Check out Mattheij's writeup in two parts for more information. It starts with an overview of the story, followed up with a deep dive on the software. He's also tweeting about the project (among other things). And if you look around a bit, you'll find bulk LEGO brick auctions online—it's definitely a thing!

Original image
iStock
arrow
Weird
Creative Bar Owners in India Build Maze to Skirt New Liquor Laws
June 20, 2017
Original image
iStock

Facing a complicated legal maze, a bar in the southern Indian state of Kerala decided to construct a real one to stay in business, according to The Times of India. Aiswarya Bar, a watering hole that sits around 500 feet from a national highway, was threatened in 2016 after India's Supreme Court banned alcohol sales within 1640 feet of state and country-wide expressways to curb drunk driving. Instead of moving or ceasing operation, Aiswarya Bar's proprietors got creative: They used prefabricated concrete to construct a convoluted pathway outside the entrance, which more than tripled the distance from car to bar.

Aiswarya Bar's unorthodox solution technically adhered to the law, so members of the State Excise Administration—which regulates commodities including alcohol—initially seemed to accept the plan.

"We do [not] measure the aerial distance but only the walking distance," a representative told The Times of India. "However, they will be fined for altering the entrance."

Follow-up reports, though, indicate that the bar isn't in the clear quite yet. Other officials reportedly want to measure the distance between the bar and the highway, and not the length of the road to the bar itself.

Amid all the bureaucratic drama, Aiswarya Bar has gained global fame for both metaphorically and literally circumnavigating the law. But as a whole, liquor-serving establishments in India are facing tough times: As Quartz reports, the alcohol ban—which ordered bars, hotels, and pubs along highways to cancel their liquor licenses by April 1, 2017—has resulted in heavy financial losses, and the estimated loss of over 1 million jobs. Aiswarya Bar's owner, who until recently operated as many as nine local bars, is just one of many afflicted entrepreneurs.

Some state governments, which receive a large portion of their total revenue from liquor sales, are now attempting to downgrade the status of their state and national highways. To continue selling liquor in roadside establishments, they're rechristening thoroughfares as "urban roads," "district roads," and "local authority roads." So far, the jury's still out on whether Kerala—the notoriously heavy-drinking state in which Aiswarya Bar is located—will become one of them.

[h/t The Times of India]

SECTIONS
BIG QUESTIONS
arrow
BIG QUESTIONS
WEATHER WATCH
BE THE CHANGE
JOB SECRETS
QUIZZES
WORLD WAR 1
SMART SHOPPING
STONES, BONES, & WRECKS
#TBT
THE PRESIDENTS
WORDS
RETROBITUARIES