Detection of fake news in social media based on who liked it.

we show that Facebook posts can be classified with high accuracy as hoaxes or non-hoaxes on the basis of the users who "liked" them. We present two classification techniques, one based on logistic regression, the other on a novel adaptation of boolean crowdsourcing algorithms. On a dataset consisting of 15,500 Facebook posts and 909,236 users, we obtain classification accuracies exceeding 99% even when the training set contains less than 1% of the posts.

Obviously, in this situation whoever controls the algorithms has great power. Decisions like what is promoted to the top of a news feed can swing elections. Small changes in UI can drive big changes in user behavior. There are no democratic checks or controls on this power, and the people who exercise it are trying to pretend it doesn’t exist

On Facebook, social dynamics and the algorithms’ taste for drama reinforce each other. Facebook selects from stories that your friends have shared to find the links you’re most likely to click on. This is a potent mix, because what you read and post on Facebook is not just an expression of your interests, but part of a performative group identity.

So without explicitly coding for this behavior, we already have a dynamic where people are pulled to the extremes. Things get worse when third parties are allowed to use these algorithms to target a specific audience.

any system trying to maximize engagement will try to push users towards the fringes. You can prove this to yourself by opening YouTube in an incognito browser (so that you start with a blank slate), and clicking recommended links on any video with political content.

...

This pull to the fringes doesn’t happen if you click on a cute animal story. In that case, you just get more cute animals (an experiment I also recommend trying). But the algorithms have learned that users interested in politics respond more if they’re provoked more, so they provoke. Nobody programmed the behavior into the algorithm; it made a correct observation about human nature and acted on it.

Really cool venue for publishing online, interactive articles for ML

AUC能够在CTR应用中有指导意义的原因

Interesting!

Robert Mercer, Steve Bannon, Breitbart, Cambridge Analytica, Brexit, and Trump.

“The danger of not having regulation around the sort of data you can get from Facebook and elsewhere is clear. With this, a computer can actually do psychology, it can predict and potentially control human behaviour. It’s what the scientologists try to do but much more powerful. It’s how you brainwash someone. It’s incredibly dangerous.

“It’s no exaggeration to say that minds can be changed. Behaviour can be predicted and controlled. I find it incredibly scary. I really do. Because nobody has really followed through on the possible consequences of all this. People don’t know it’s happening to them. Their attitudes are being changed behind their backs.”

-- Jonathan Rust, Cambridge University Psychometric Centre

The team on Google Translate has developed a neural network that can translate language pairs for which it has not been directly trained. "For example, if the neural network has been taught to translate between English and Japanese, and English and Korean, it can also translate between Japanese and Korean without first going through English."

Ground truth in machine learning

2013 article about Douglas Hofstadter, who has continued to pursue an understanding of the human mind through experiments with AI.

In machine learning it's also important to evaluate not just against random, but against how well other methods (e.g. parole boards) do. That kind of analysis would be nice to see.

We should have control of the algorithms and data that guide our experiences online, and increasingly offline. Under our guidance, they can be powerful personal assistants.

Big business has been very militant about protecting their "intellectual property". Yet they regard every detail of our personal lives as theirs to collect and sell at whim. What a bunch of little darlings they are.

What do n and d mean?

UT Austin SDS 348, Computational Biology and Bioinformatics. Course materials and links: R, regression modeling, ggplot2, principal component analysis, k-means clustering, logistic regression, Python, Biopython, regular expressions.

Python interface to the R programming language.<br> Use R functions and packages from Python.<br> https://pypi.python.org/pypi/rpy2

https://twitter.com/open_ai

They're hiring: https://openai.com/about/

The study.

https://github.com/rhiever/tpot TPOT (Tree-based Pipeline Optimization Tool) Built on numpy, scipy, pandas, scikit-learn, and deap.

penn state

I have the feeling we do not need to use models as complicated as some outlined in the text; we can (and finally will have to) abstract from most of the issues we can imagine. I expect that "magic" (an undisclosed heuristic, perhaps in combination with machine learning) will deal with the issues, a black box that will be considered inherently flawed and practical enough at the same time. The results from experimental ethics can help form the heuristic while the necessity for easy implementation and maintainability will limit the applications significantly.

This is a really useful visualization of the Multi Class SVM loss

Someday, maybe projects like Hypothesis will help teach computers to read, too.