sábado, 29 de junio de 2013

Como en las investigaciones de redes sexuales, distribución de colas gordas (fat tail distribution)

Simplemente como un detalle anecdótico, esta encuesta publicada por el sitio Entre Mujeres sobre la cantidad de compañeros sexuales que han tenido una muestra de mujeres, responde a los patrones observados por otras investigaciones sobre redes sexuales en la cuales predominan un número muy pequeño de gente con muchos compañeros sexuales y una gran mayoría que solo tuvo pocos o ninguna pareja sexual. A esa distribución de eventos se le denomina distribución de ley de potencia o distribución de cola gorda.

3 de cada 10 mujeres perdieron la cuenta de con cuántas personas se acostaron

Desde Entremujeres quisimos saber la cantidad de amantes que tuvieron nuestras lectoras. Lanzamos una encuesta que demostró que, en tiempos de amores fugaces, el "touch and go" se lleva la delantera. ¿A vos tampoco te alcanzan los dedos de las manos para sacar el cálculo? 

¿Con cuántas personas tuviste intimidad? Simple y directa fue la consigna de la encuesta de Entremujeres, que contó con 22.560 participantes. Las respuestas fueron muy variadas y pasaron de un extremo al otro con total libertad. Pero una, la ganadora, llamó especialmente nuestra atención. 

“Perdí la cuenta”
Así nomás. El primer puesto se lo llevó el reino de los “touch and go”. Unas 6.435  (el 28,5% de las que votaron), ya ni recuerdan de la cantidad de personas con las que se fueron a la cama… O a lugares similares.

“De 2 a 5”
Ni nada ni demasiado. “De 2 a 5” fue la segunda respuesta con mayor cantidad de votos. La eligieron 5.725 mujeres, el 25,4% de las participantes. Ellas tienen experiencia en la cama, apuestan al erotismo, pero le huyen al amor descartable.  

“De 6 a 10”
Como era de esperar, la opción intermedia ocupó una posición intermedia. Fue elegida por 3.554 mujeres, el 15,8% de las participantes.

“De 11 a 20”
El mayor de los rangos propuestos quedó casi al final. Tuvo 3.455 votos, el 15,3% de los realizados. Quizás la fiaca pueda explicar el flojo resultado: ¿para qué ponerse a calcular si existe la opción “perdí la cuenta”?

“Solo con el amor de mi vida”
Si bien quedó última, la respuesta más romántica (y recatada) tuvo unos cuantos votos. Hasta podríamos decir que nos sorprendió. En tiempos de relaciones fugaces, unas 3.391 mujeres (el 15% de las encuestadas) siguen apostando a su primer y único amor.  

Y vos, ¿con cuántas personas te acostaste? ¿Fueron pocas y especiales? ¿O tenés que usar los dedos de varias manos para recordarlas?

viernes, 28 de junio de 2013

Una clase de Análisis de redes sociales avanzado usando R y Statnet

Goudreau-Hunter tutorial on Advanced Social Network Analysis Using R and statnet

Below are the videos for the Goudreau-Hunter tutorial on social network analysis using R. Note that this tutorial was recorded on five tapes of about one hour each, hence the five videos below.

"Advanced Social Network Analysis Using R and statnet"
Presenters
Steve Goodreau and David Hunter
Description
This workshop will introduce the use of the R statistical computing platform (via the statnet software suite) for statistical modeling of social network data. Topics covered include the use of exponential random graph (ERG or p*) models for representing structural hypotheses, model parameterization, simulation and inference, degeneracy checking, and goodness-of-fit assessment. Although a short "refresher" will be provided, some prior exposure to R and standard network analytic methods is strongly recommended.
For more information, please see the workshop web page, or our project home page .
|  

miércoles, 26 de junio de 2013

Visualización: Nube de palabras de la conversación política estadounidense


Campaign visualizations: the a moving picture of the national conversation

I've been working with postdoctoral fellow of mine at Northeastern and IQSS, Yu-ru Lin, on visualizations that capture campaign 2010. Over the next couple of days we will be posting some of the visualizations on the blog. The first visualization is a dynamic word cloud based on daily snapshots of all Democratic and Republican campaign websites in October. So, for example, the words for the home pages of all Democratic candidates for the House were pooled together, and for each day, a word cloud was created, where words were sized based on their frequency (certain functional words were omitted, and word counts were normalized so no one website could dominate the count). This process was repeated for Republicans in the House, and for both parties in Senate and gubernatorial races. Below we show the dynamics for the Republican and Democratic websites. For the full set of 6 graphics, with interactivity, we have set up a dedicated website.
A brief perusal suggests some interesting contrasts. You can see jobs in both websites, but more prominently for Democrats, and tax and spending are a lot more visible for Republicans. America is big for Republicans, and education for Democrats. Democrats talk more about veterans and security, and Republicans about business. Republicans use "Republican" a lot, and Democrats "Democrat" very little. Notably missing are: Iraq, Afghanistan, health, and Obama. (For health, there is an interesting contrast with Senate campaign websites, where both parties feature health very prominently.)ç





lunes, 24 de junio de 2013

Una presentación sobre ciencia social computacional, por Lazer

PRESENTATION ON COMPUTATIONAL SOCIAL SCIENCE
This 10 minute presentation of mine on computational social science (using "big data" to understand social systems) at Harvard's CID might be of interest to some readers of this blog. It covers issues ranging from detecting emergencies in sociotechnical systems, to detecting "invisible" political networks from unstructured text:
A reminder-- if you are from the Northeast and have an Android phone, please participate in our study on communication behavior during Hurricane Sandy. We will be giving $3 to food banks in affected areas for every completed survey we receive.
By David Lazer | 2:59 PM
STUDYING HURRICANE SANDY VIA DATA ON _YOUR_MOBILE PHONE
My lab, with the support of the NSF, is launching a crowd-sourced study of Hurricane Sandy, so as to better understand how people react in emergencies. If you were affected by Hurricane Sandy and use an Android phone, I hope you will be willing to help out. This will take 10-15 minutes of your time. And if you weren't, then I hope you can pass this post on to someone that was affected by Sandy.
How do people respond in large-scale emergency situations, like earthquakes and hurricanes? Understanding this should inform more effective responses to save lives and reduce hardships. Getting hard behavioral data in the moment and aftermath is difficult--because people have better things to do than to participate in a study. There is quite a bit of valuable research based on interviews after the fact, but such research necessarily relies on reconstructed memories of behavior.
There is another path--which is to study the data passively collected about people by the sociotechnical systems relied upon during emergencies. An outstanding example of this is the paper by Bagrow et al that examined behavior as captured by mobile phones during a set of emergencies. The power of this approach is that it offers hard behavioral data at massive scale. The shortcoming, however, is that it cannot contextualize (beyond geography) the data. Who, exactly, are people calling? Their spouses? Friends? What are they communicating--the need for help, reassurances that they are ok?
Here we are launching a study that sits between these two approaches. Essentially, we are asking people to load an app on their Android phones (iPhone users: sorry, but for now we could only afford to develop for one platform), and the app will ask about their situations during Hurricane Sandy, and look at their calling and texting behaviors, asking them about their relationships with those individuals. We will therefore get a precise record of behaviors before/during/after Hurricane Sandy, and contextualize within personalize circumstances and particular relationships.
My motivation here is scientific and personal. I think there is the possibility to do great science here that is potentially consequential for people's lives, that can inform interventions that will help people. And, having grown up on Long Island, and spent the early part of my career Red Bank, New Jersey --near the shore ("shaw")-- I could see a lot of suffering occur among my friends and family in the aftermath, where there was very little I could do. But this study is at least something good that I can make out of a terrible thing.
We have posted more information about the study on our newly launched crowd-sourced science website, Volunteer Science, or you could go directly to the Google Play store.

By David Lazer | 

jueves, 20 de junio de 2013

¿Papá, en que aplicación conociste a mamá?

After Tinder, kids of the future may be asking “Mommy, which app did you meet Daddy in?”


By Simone Foxman




Short on time and savvy with social media, young professionals have been some of the first to adopt Tinder, a dating app launched in October. The app, available on iPhones and iPads, lets you decide—based on a few details and a couple of pictures—whether a person within a certain radius of you is “dateable.”
It works that out by comparing your lists of friends and interests on Facebook to match you with likely prospects. Then it shows you their pictures. The beauty of the app is its game-like speed: swipe left (no thanks) or right (mmm, cute)—or click the X or heart button—and move on to the next one. If both you and another person separately approve one another, the app lets you chat together.
It may sound like the ultimate in objectification, but young people see it as a practical way to get rid of the drama and possibility of rejection. “There’s really no rejection,” says Justin Mateen, the app’s co-founder. “You don’t have to do anything. It’s really instant gratification. And you don’t have to sell yourself, which removes some of the stigma of dating sites.” The average user is a 27-year-old iPhone owner in a big city, according to Tinder. The company plans an Android launch within the next 30 days.
Anecdotal evidence suggests that it’s particularly popular with people who spend long hours at work and have the least time for meeting people the old-fashioned way. ”With crazy schedules it was a fast way to meet someone,” says one private equity analyst. “The two people I’ve been on Tinder dates with are pretty impressive people career-wise.” A junior associate at a major Wall Street firm admitted that his friends are obsessed with it. Another said that using Tinder and OkCupid had developed into a “hobby.” This author even watched four of her male and female friends—twenty-somethings in finance and advertising—spend over an hour swiping away on the app at a bar last month. (Riveting.)
group playing tinder
Rating would-be dates is also a group activity. And then the inevitable “OH! I know him/her” moment.Instagram
The adoption has been massive and global, according to the company. Tinder says it has made 60 million matches since October, its users have rated each other 5.7 billion times, and it has prompted 20 engagements. In some countries, Tinder users already number more than 1% of the country’s entire population. The more seasoned OkCupid—a property owned by social media conglomerate IAC, which was also an early investor in Tinder—asked Tinder for help on its own swiping “Hot or not” function, OkCupid Local. Since that app launched two weeks ago, its users have voted on each other 20 million times.
But Tinder plans to use its platform to expand beyond dating. “We don’t consider ourselves a dating app per se,” says Mateen. “We want to include everyone. The need to meet new people is universal…We don’t believe it’s right to restrict a relationship and categorize it. We feel like keeping it broad and people can figure out the intentions of others by chatting.” He said future versions of the app will be focused on including people who aren’t looking for a romantic relationship, and could include mobile purchases in some form.
Of course, Tinder’s future plans and monetary ambitions probably matter little to Tinder’s current users. The really burning question is: How many of them are devotees of Game of Thrones?

http://qz.com/95009

miércoles, 19 de junio de 2013

Mi precioso grafo social de Facebook

Facebook Is Done Giving Its Precious Social Graph To Competitors


By Josh Constine -  TechCrunch

Of all Facebook’s data sets, it’s the social graph that’s truly unique. It’s spent nine years getting you to confirm who you know, and apparently it’s sick of handing over your friend list to competitors. This week it cut off both Twitter’s new photo app Vine and messaging app Voxer from Find Friends, Facebook’s API that lets you connect with Facebook friends on other apps. But this could backfire.
Facebook knows who you are, what you’re interested in, where you go on the web, what apps you use, and more. However, other companies have bits and pieces of these data sets. LinkedIn knows your resume, Google knows your web searches, Twitter knows who you follow, Apple and Amazon have your credit card number, and your phone’s OS maker knows what apps you’ve downloaded. Who your real-life friends are, though, is Facebook’s domain.
Find Friends ScreenshotReconfirming your social graph manually on other apps is awkward at worst and annoying at best. Think about it. If your Facebook account were reset and you had to send friend requests to all your old friends, how many do you think would confirm? Even your best friends might be too lazy to, and people who were glad to friend you when you met years ago probably wouldn’t bother if they remember you.
There’s plenty of noise in Facebook’s social graph. Some people blindly accept most requests they get, others send them to anyone they meet once, and all the connections grow stale over the years. Still, if you want to jumpstart a social app, Facebook’s Find Friends feature is very valuable. It can be the difference between an empty feed and low retention, and a vibrant, addictive feed teeming with content from people you care about.
Facebook has offered Find Friends for years. But those were years when it was a web-based social network. It’s more now, or at least it wants to be. Facebook hopes to host all the ways you communicate. That has pitted it against Apple, Google, and other companies in war for messaging that’s only just heating up.
Data portability first became a big issue in 2010 when Facebook blocked Twitter from using its Find Friends feature. Later that year it got into a spat with Google about exporting contact lists. Google was pissed Facebook was sucking in Gmail contacts but not exporting friend lists. Facebook eventually began offering Download Your Data, which included your Friend List, but only in plain text.
More recently though, Twitter may have awoken the dragon when it cut off Instagram’s access to Twitter’s own version of “Find Friends.” It was an understandable retaliation since Facebook had cut it off, and Twitter had wanted to buy Instagram, too.
Now Facebook is coming out swinging, citing its Platform Policy that states “Competing social networks: (a) You may not use Facebook Platform to export user data into a competing social network without our permission.”
Last week it blocked voice-messaging app Voxer’s access to the social graph. At the time, Facebook told me this was because Voxer qualified as a competing messaging platform, but also because Voxer wasn’t contributing much back to Facebook. Voxer only had a buried, and largely unnecessary, “share to Facebook” option. It got an email stating its Find Friends access would be revoked 48 hours later.
Then today Facebook shut off Find Friends for Twitter’s Vine, as spotted by Jeff Martines and reported by The Verge. That makes both more and less sense. More because Twitter is a real competitor. It has decent scale and mindshare and competes for the same advertisers as Facebook. Twitter would love to know your Facebook social graph, which could help it refine its version, the “interest graph,” which powers its ad targeting.Vine Blocked
It makes less sense because Vine had a prominent “share to Facebook” option. What happened to Facebook only going after apps that don’t contribute much back? Apparently that got overruled because Twitter is a more legitimate threat. So much so that Facebook employed its policy that “we reserve the right to take action against your app even before the end of this 48 hour period.” It didn’t want Twitter getting any social graph data.
Enforcement of these policies could create a moat around Facebook. It creates a barrier to engagement, retention, and growth for competing companies. It will force social apps to rely on other data sets, such as your phone’s contacts which may not have as complete of a social graph, though likely does include your closest friends whose numbers you have.
That advantage may not be worth it, though. The enforcement means Facebook is not an “open platform.” If companies are worried that Find Friends or other Facebook data access could be ripped away from them with little notice, it could cause a chilling effect on development on the Facebook platform. No one wants to build an app that relies on Facebook data if it could disappear.
Facebook reaffirmed this fear this morning when it enforced its ban on exporting data for use in social networks. Russian search engine Yandex’s new social search mobile app Wonder got all of its API calls blocked just three hours after launch. That’s a lot of programming and product work down the drain.
Facebook is playing with fire. It could use policy enforcement to cook competitors and shine a light on its dominance of social networking. But if this enforcement scares off developers whose apps might otherwise provide content that could be shown next to ads in the news feed and piped into Graph Search, Facebook could get burned badly.
[Image Credits: Newscom]

martes, 18 de junio de 2013

Como visualizar tu red de amigos de Facebook

How to: visualize the network of your friends on Facebook





Here I will teach you how to visualize the network of mutual friendship among your Facebook friends using a simple online tool called FriendsGraph.

First of all you will need to access the FriendsGraph website: https://app.friendsgraph.me and login using your Facebook account. You will be asked to allow the application to access the list of your friends but don't worry, it's just needed to build the network.


Now you are almost ready to visualize your network. FriendsGraph will take up to a couple of minutes to compute the connections among your friends, in the meantime you will be presented some interesting facts related to your friends.



After approximately one minute you will be able to explore your network of friends. You can zoom in and out using your mouse wheel or the bar on the bottom left of the screen. Clicking on a friends will highlight the sub-network of common friendship and display a picture of him/her. The search bar at the top of the screen can be used to search for a particular friend within your network.

The application has another very interesting feature: as you have noticed, FriendsGraph assign to each node (friend) a color based on a community-detection algorithm and a position based on the connections with the other nodes (friends). This means that your friends which belong to the same "social group" are more likely to be near and to be of the same color.

Are you able to distinguish the different groups among your friends and give a name to them?
- See more at: http://cavajohn.blogspot.com.ar/2013/06/how-to-visualize-network-of-your.html#sthash.l2Idq0hx.dpuf

Data Analysis and Visualization