ראה/ראי עוד מ-‏‎Facebook Data Science‎‏ על ידי התחברות לפייסבוק
שלח/י הודעה לדף זה, קבל/י מידע על אירועים קרובים ועוד. אם אין לך חשבון פייסבוק, את/ה יכול/ה ליצור חשבון כדי לראות עוד מדף זה.
ראה/ראי עוד מ-‏‎Facebook Data Science‎‏ על ידי התחברות לפייסבוק
שלח/י הודעה לדף זה, קבל/י מידע על אירועים קרובים ועוד. אם אין לך חשבון פייסבוק, את/ה יכול/ה ליצור חשבון כדי לראות עוד מדף זה.
לא עכשיו
In August 2016 many people participated in listing their first seven jobs on Facebook using the hashtags #firstsevenjobs or #first7jobs. As sometimes happens with internet trends, this one spread unevenly over the globe, providing a glimpse both into the universality of first jobs, but also interesting differences between different countries.
As many people set their professional goals for the ...
...
By Annie Franco, Justin Grimmer, Monica Lee, and Solomon Messing

Independence Day is an occasion to celebrate our democratic freedoms. Chief among them is our right to participate in the democratic process. The most recognizable form of political participation happens on Election Day, when we go to the polls to select o...
המשך/המשיכי לקרוא

By Monica Lee and Bogdan State


In an increasingly mobile world, Facebook is an important way many fathers and children connect with one another. So on this Father's Day, we celebrate fathers by analyzing over 141 million father-child relationships in 28 countries that are maintained in part on Facebook. Specifically, we look at fathers' and childr...en's distance from one other geographically and communicatively. We find that children tend to move away from their fathers as they grow up, and that middle-aged children communicate more with their fathers on Facebook than do other age groups. Analyzing the distance between fathers and children inspires us to think about how we can know fathers better. So we conclude with a brief look at the cultural interests of fathers on Facebook. Perhaps it can serve as next year's Fathers' Day shopping guide for those of us who don't keep in touch with Dad as much as we should.

Geographical Distance from Dad

First, we looked at how far from their fathers children at different ages live. Unsurprisingly, most children seem to move away from home in their twenties. Children in their teens tend to live very close to their fathers, whereas children in their twenties and thirties are increasingly likely to live far away from their parents.

Once they reach their mid thirties, however, daughters' likelihood of living far from their fathers stabilizes; sons' likelihood does as well, but it rises once again as they reach their late 50s. Overall, fathers and daughters stay geographically closer to one another than fathers and sons. Fathers and daughters live, on average, just under 800 km apart when daughters settle into their adult homes during their mid-thirties. By comparison, fathers and sons live just under 1000 km apart as the sons reach their mid-thirties.


Communicating with Dad

Next, we examined how much fathers and children of different ages interact with each other. It turns out that communicative distance tends to contrast geographical distance. Below is the public messaging rate (comments and posts as a percentile score) between fathers and children over three months.


While geographical distance between fathers and children is greater among children who are in their twenties and thirties than among teenagers, father-child Facebook interaction rates are also greater. In general, fathers and daughters keep in touch more than fathers and sons do. For nearly every age group, the interaction rate between fathers and daughters is around 5% higher than that between fathers and sons. Interaction is most frequent for father-daughter pairs where the daughter is around 40 years old; at this age the average daughter's interaction rate with her father is near the 59th percentile. Interaction is most frequent for father-son pairs where the son is around 50 years old; at this age the average son's interaction rate with her father is near the 53rd percentile.


What to get Dad on Fathers' Day

As children get older, they become more likely to live far away from their fathers, and maybe few children keep in touch with Dad as much as they'd like. So it's no surprise that finding a good Fathers' Day gift is always difficult. But data science might help us figure out what to get dad this year. In the space of this blog post, it's hard for us to say much about your dad in particular, but there are certain things that dads in the U.S. tend to agree on. Listed below are the top ten music, movie, TV, sports, and entertainment pages most liked by dads in the following age groups, where number of likes is normalized by the page's overall popularity among U.S. users.



U.S. dads in their 30s are much more likely to enjoy contact sports, action-packed TV shows, and familial humor than the average American. Dads in their 40s tend to also enjoy sports and familial humor, but in addition, they disproportionately like Hard Rock Music—bands from the 1980s when they were youths. Accordingly, Classic Rock bands from the 70s dominate the interest list of dads in their 50s, who also seem to like Western movies and golf. Westerns and golf are also popular among dads in their 60s, who in contrast tend to like Blues-y and Southern Rock from the 1960s and early 1970s. U.S. dads in their 70s disproportionately enjoy Country music, Western movies, and Christian topics. Finally, dads in their 80s are much like those in their 70s—Country music and Christian faith. So depending on your dad's age, maybe you should get him some football tickets, concert tickets, golf clubs, a CD or music gift certificate, or a John Wayne DVD box set...?

הצג עוד

This piece is based on posts made in the United States during the evening of February 26, 2015. All data has been anonymized and aggregated.

Last night saw one of those beautiful moments made possible by the interconnected age we live in: someone posted a picture of a dress, and the Internet lost its collective min...d. Was the dress black and blue, or was it white and gold? The furor even drowned out what would ordinarily be a strong viral winner of the day, a video about two llamas on the lam. Everyone had theories about why people might see the dress differently; we thought we'd take a look at four hypotheses.

We anonymized and aggregated posts from people in the United States last night which mentioned either "black" and "blue", or "white" and "gold", but not both. Then, we looked at how the black/blue percentage changed with different attributes, using a multiple regression to filter out correlations and find the true effect of each difference. Margins of error are under 1 percent throughout.

In all, 42 percent of Facebook users choosing a side were on team Black and Blue, while 58 percent were on team White and Gold.

Gender

One natural starting place to look was gender, where vision differences are well-known: for instance, 8% of men are colorblind, while only 1 in 200 women is. We found a significant gender split -- controlling for other variables, men were more likely to vote black and blue by 6%.



Age

The younger a person was, the more likely they were to believe the dress was black and blue. All other things being equal, a whopping 10% more of 13-17 year old users were on team Black and Blue, compared to 55-64 year old users. The below chart shows the difference in the percentage of people voting Black/Blue relative to the 25-34 year old crowd.



Interface

We wondered if the interface used by the person might have something to do with the percentage: after all, the same image might visually look very different depending on the light signature of the device used to view it. Making the assumption that people posted to Facebook on the same device they used to view the image, this was indeed the case: relative to people posting from a computer, 6% more iPhone users said that the dress was white and gold, while this number was 7% for Android users! These numbers, which are controlled for the other factors mentioned in this note, may be related not only to the devices in question but to the locations in which one uses them (for instance, presumably mobile users are far more likely to be outside).



Time of day

One of the major breaks in the Case of the Colorful Dress came when the Internet managed to track down the actual dress, which was duly revealed to be blue and black. As this information spread through the network, people gradually started shifting their opinion to black and blue (or perhaps the black-and-blue side felt more emboldened). By midnight Eastern time, the fraction of people voting black and blue had risen by 4%.



Conclusion

The dress that broke the internet also produced a fascinating natural experiment about vision. We see that men are significantly more likely to perceive the dress as black and blue; so are younger people, and people on a desktop instead of a phone. Finally, as the night went on and more people knew the truth, people gravitated -- at least publicly -- towards the winning team. We're data scientists, not oculists or neurologists; we'll leave speculation about exactly how this perceptual difference occurs up to the experts. But this one dress provides a fascinating window into how human vision and the brain it feeds can perceive things so differently.

Adrien says it's White and Gold. Mike says it's Black and Blue. Their friendship may or may not survive this incident.
הצג עוד

by Winter Mason, Funda Kivran-SwaineMoira Burke, and Lada Adamic.


Over the past few months, many people have been challenging one another to share on Facebook the things for which they are most grateful. So, for example, one friend might challenge another to “write 3 things you are thankful for over the next 5 days.”...

המשך/המשיכי לקרוא

by Ta Virot Chiraphadhanakul, Solomon Messing, Alex Peysakhovich, and Sean J. Taylor

(Facebook Core Data Science Team)


When Burkina Faso beauty salon owner Korotimi Sere needed a loan, she had few options. For Korotimi and millions like her in Sub-Saharan Africa, getting a conventional loan is nearly impossible--80% of...

המשך/המשיכי לקרוא

With the 2014 midterm elections approaching, we decided to take a look at the cultural similarities and differences between people who support Democrats and people who support Republicans. To do this, we looked at everyone who liked the campaign page of any Democrat or Republican running for governor, U.S. Senate or U.S. House of Representatives. W...e then looked at what other pages those people liked on Facebook and identified the pages that were most differentiating—that is, the pages which were disproportionately liked by the supporters of one party versus the other—and those that were most balanced.

Note: in all of the figures below, the more a page is disproportionately liked by fans of Republican candidates, the farther right the page name appears (precisely indicated by the darker line in the middle). Conversely, the more a page is disproportionately liked by fans of Democratic candidates, the farther left the page name appears. The font size of the name is proportional to the total number of people from the US who liked that page.


Musicians / Bands

Let's start by looking at the musicians and bands liked by Democratic and Republican supporters.




This figure shows the top 20 bands disproportionately liked by Democrats and Republicans and the top 20 bands that bridge the divide. 

Landmarks / Destinations




This figure demonstrates that the most balanced landmark page nationwide is the Jersey Shore. 

Authors




The author most disproportionately liked by Democrats is poet Maya Angelou, while Republicans disproportionately like Dr. Ben Carson. But it seems everyone can agree on James Patterson. 

Books



Here we see “Atlas Shrugged” lean right and “The Great Gatsby” lean left, while the Farmer's Almanac's down home wisdom receives a balanced number of likes from the left and the right.


TV shows




The most balanced shows are the ones that fill TV networks' prime-time lineups while news commentary shows have more partisan popularity. 

הצג עוד

by Lada Adamic and Pinkesh Patel


A month ago we posted the top books mentioned in the “10 books that have stayed with you” meme (see https://www.facebook.com/notes/facebook-data-science/books-that-have-stayed-with-us/10152511240328859). At the time we only looked at the English-language version, which was dominated by s...

המשך/המשיכי לקרוא

By Solomon Messing, Annie Franco, Arjun Wilkins, Dustin Cable, and Matthew Warshauer


During each U.S. election cycle, the Data Science Team looks at civic engagement surrounding the election. This year, we’ll look at the issues candidates are talking about on their Facebook pages and how people respond.

...

המשך/המשיכי לקרוא

by Mike Develin and Adrien Friggeri, Facebook Data Science


For years, parents have been naming their children in clever, or, if you feel less charitable, "clever" ways. This dates at least all the way back to Roman times, where the twins Romulus and Remus share more than just genes and a wolf-mother: their names themselves bear obvious typographical... and phonetic resemblance.


This trend is alive and well today. Roger Clemens loved strikeouts so much that he named his children all starting with the letter K. It's sad to imagine the Kardashian family helplessly struggling to name its children in a world missing that same letter. The winner in this department, however, has to be boxer George Foreman, who famously named all five of his sons George.

How common is this alliteration? It turns out to be quite significant. We looked at pairs of siblings on Facebook who both live in the United States, and found that at all ages, they had a much higher likelihood of having the same first initial: 



As you can see, a pair of siblings has about an 11% chance of having the same first initial, compared to about 7% as we'd expect from random chance (if their first names were independently drawn from the pool of all users of their respective ages). This trend does not appear to be fluctuating much over time; the late-teens drop is due to a cultural phenomenon where best friends of that age will often list each other as siblings.

When we examine the most common pairs of sibling names, we see even more similarity, and other themes emerge. These are the pairs of sibling names that occur most often compared to random chance (that is, # of pairs / # of expected pairs if names are random within their age):
  1. Yvette-Yvonne: 37.4 times as often as expected
  2. Faith-Hope: 31.4
  3. Charity-Faith: 24.3
  4. Jami-Jodi: 23.8
  5. Gretchen-Heidi: 22.0
  6. Charity-Hope: 21.2
  7. Kelli-Kerri: 18.9
  8. Latasha-Latoya: 18.5
  9. Eileen-Maureen: 18.4
  10. Colleen-Maureen: 17.0 
11-20: Cesar-Oscar, Landon-Logan, Edgar-Oscar, Blair-Blake, Tammi-Terri, Adriana-Alejandra, Dalton-Dillon, Autumn-Summer, Edgar-Omar, Juana-Maria

21-30: Trent-Trevor, Kory-Kyle, Trent-Troy, Brendan-Colin, Eduardo-Jorge, Javier-Jorge, Garrett-Grant, Kathleen-Maureen, Jesus-Jose, Chance-Chase

The patterns are striking. There are two categories of non-typographical associations: names associated with the same ethnicity, and the Faith-Hope-Charity trinity of virtuous names. Aside from these (and even within the coethnic names) it's extreme typographical and phonetic similarity, even above and beyond having the same first initial. It looks like the entire country, at least on this front, is keeping up with the Kardashians.

You may have noticed an unusual sawtooth pattern in the graph above, along with a spike for young ages. These both come from a set of siblings that's even more sibling than ordinary siblings: twins! Romulus and Remus are just one in a series of twin pairs with similar names. Compared to the 11% rate for siblings and the 7% expected random-chance rate, twins have a much higher chance of having the same first initial (surprisingly, looking at the gender rates, this is only slightly higher for same-gender and thus for identical twins):




Interestingly, this rate has gone down quite a bit over the last 40 years, but many twins are still saddled with the same first initial, resulting in what is no doubt a lifetime of frustration around login names.

We close by looking at another surprising influence on name: where you live. In the state of Virginia, 46% more people are named Virginia than in the country at large; in West Virginia, it's 28% more. We see no bump in surrounding states, suggesting that it's not just cultural: either people named Virginia are drawn to these states or, perhaps more likely, parents are trying to be clever again. Oh, those parents.

All data was anonymized and aggregated. We removed cases where the siblings have the same name (sorry, Mr. Foreman, these are more likely to be multiple profiles of the same person than genuine siblings), and for the state case we adjusted for non-person user profiles (e.g. "Virginia Highway Patrol").
הצג עוד