e-Xploration
Follow
Find tag "prediction"
21.8K views | +0 today
e-Xploration
antropologo.net, dataviz, collective intelligence, algorithms, social learning, social change, digital humanities
Curated by luiy
Your new post is loading...
Your new post is loading...
Scooped by luiy
Scoop.it!

Want to be Retweeted? Large Scale Analytics on #Factors Impacting Retweet in #Twitter Network | #datascience

more...
No comment yet.
Scooped by luiy
Scoop.it!

#Sentiment Analysis Tool Designed to #Predict Veterans’ Suicide Risk I #datascience

The Veterans Administration is funding the Durkheim Project, an effort to use text and sentiment analysis to predict veterans suicide risk.
luiy's insight:

That’s where computer scientist Chris Poulin and a semantics-based prediction tool enter the picture. Poulin and his company, Patterns & Predictions, had developed a commercial Bayesian analytics tool for predicting events—most notably financial events—based on historical analysis. “You have a stock that went bust on a certain date,” explains Poulin. “What were the forensic features that led up to that stock going bust?”


Ten years ago, as Poulin was launching the company, his best friend committed suicide. “He posted a suicide note—and what turned out to be pre-suicide notes—on social media,” says Poulin.  As time went on, Poulin began to consider whether a similar event prediction model could parse the social media behavior of veterans to uncover those who might be about to harm themselves. Later, as a researcher at Dartmouth, Poulin partnered with Paul Thompson, an instructor at the university’s Geisel School of Medicine who specializes in computational linguistics and also lost a friend to suicide, and they took their pitch to the Pentagon. Three years ago, they were awarded a $1.7 million contract by the Defense Advanced Research Projects Agency (DARPA) to combine Thompson’s linguistics work with Poulin’s event-focused text analytics to create a model to predict those with suicidal or other harmful tendencies.

 

Dubbed the Durkheim Project (after French sociologist Emile Durkheim known for his 19th century study of suicide data) the researchers ultimately hope to use opt-in data from veterans’ social media and mobile content to create a real-time predictive analytics tool for suicide risk. While the team behind the project is optimistic about its abilities to make predictions with 65 percent accuracy, the challenge at this stage is about gaining the cooperation of veterans to join the effort to gain insights into their well-being.


- See more at: http://data-informed.com/sentiment-analysis-tool-designed-to-predict-veterans-suicide-risk/#sthash.CqGn7DHl.nzAN4pbL.dpuf

more...
Intriguing Networks's curator insight, December 9, 2013 6:02 PM

Important work in an obviously serious application surely with lessons for DH hopefully without such severe ramifications. Very interesting thanks for the share from e-Xploration.

Intriguing Networks's curator insight, December 9, 2013 6:05 PM

Re-shared because its such an important application and perhaps shows how the computational aspects are transferrable between apparently unconnected use cases. 

Rescooped by luiy from Global Brain
Scoop.it!

Minority Report-style pre-crime #prediction using Twitter data | #dataviz

Minority Report-style pre-crime #prediction using Twitter data | #dataviz | e-Xploration | Scoop.it
Retweet graph of Project X dataset (snapshot at 2012-09-26 04:32:15). (credit: Marijn ten Thij/University o Twente) It’s the year 2054, where “PreCrime,” a specialized police department, apprehends criminals based on foreknowledge provided by three...

Via Spaceweaver
luiy's insight:

It’s the year 2054, where “PreCrime,” a specialized police department, apprehends criminals based on foreknowledge provided by three psychics called “precogs.”

That’s the premise of the Minority Report film. Now University of Twente (UT) mathematics student Marijn ten Thij* has developeda mathematical model that he says could achieve a similar result (but not limited to crimes) by analyzing tweets — perhaps similar to what the NSA is already doing.

more...
No comment yet.
Rescooped by luiy from Non-Equilibrium Social Science
Scoop.it!

How far should we trust scientific models? I #prediction #modelling

How far should we trust scientific models? I #prediction #modelling | e-Xploration | Scoop.it
In economics, climate science and public health, computer models help us decide how to act. But can we trust them?

Via Bernard Ryefield, NESS
luiy's insight:

Here’s a simple recipe for doing science. Find a plausible theory for how some bits of the world behave, make predictions, test them experimentally. If the results fit the predictions, then the theory might describe what’s really going on. If not, you need to think again. Scientific work is vastly diverse and full of fascinating complexities. Still, the recipe captures crucial features of how most of it has been done for the past few hundred years.

 

Now, however, there is a new ingredient. Computer simulation, only a few decades old, is transforming scientific projects as mind-bending as plotting the evolution of the cosmos, and as mundane as predicting traffic snarl-ups. What should we make of this scientific nouvelle cuisine? While it is related to experiment, all the action is in silico — not in the world, or even the lab. It might involve theory, transformed into equations, then computer code. Or it might just incorporate some rough approximations, which are good enough to get by with. Made digestible, the results affect us all.

more...
No comment yet.
Scooped by luiy
Scoop.it!

'Social dispersion': the Facebook factor that predicts relationships - and when they will end | #datascience

'Social dispersion': the Facebook factor that predicts relationships - and when they will end | #datascience | e-Xploration | Scoop.it
A scientific paper authored by a computer scientist and a senior engineer at Facebook has shown how your online social networks not only reveal who you’re going out with, but also when you’ll break up (and yes, that's without checking your...
luiy's insight:

Backstrom and Kleinberg found that looking at just the number of mutual friends between any two individuals – a factor known as ‘embeddedness’ - was not actually a strong indicator the pair were in a relationship, and that instead a quality known as ‘dispersion’ was far more telling.

 

Dispersion measures not only mutual friends but the network structures that connect these friends together. ‘Low dispersion’ – the quality that was associated with couples – indicates not only that two people have a large number of mutual friends, but also that these mutual friends knew one another.

 

Essentially, romantic partners act as social bridges between individuals’ networks, introducing people to each other and creating friendships. Eg, you might go for drinks with your boyfriend's friends from work and bring some of your friends from home to meet them.

Using this dispersion algorithm Backstrom and Kleinberg  were able to correctly identify who somebody’s spouse was 60 per cent of the time and correctly guess somebody’s partner a third of the time – a far better return than the 2 per cent success rate from pure guesswork.

more...
No comment yet.