News for hackers. Stuff that matters.
Re:Hack day report: Using Amazon Machine Learning to predict... by justonepost on Friday July 17, 2015 @06:34PM (#9905741)
Is AML using a deep learning architecture? I'm sure there are enough phrases that when used alongside or near other phrases can cause trolling to occur. Given a big enough training set and deep enough architecture, I can imagine it would work well. Perhaps you'd want to use a thesaurus to canonicalize words in case your training set isn't big enough. Removing fill words might help as well.

For example, the phrase "Trump was bombastic in his political speech" might become something like "Trump grandiose political speech" or even just "political speech".

I wonder if this sort of feature extraction has been done elsewhere and could be re-used for this problem.

edit: looks good: http://blog.mafr.de/2012/04/15/scikit-learn-feature-extracti...

Re:Hack day report: Using Amazon Machine Learning to predict... by zorrb on Friday July 17, 2015 @10:18PM (#9906347)
No.. From their documentation it says they use "Industry Standard Logistic Regression", which just means logistic regression. Which can be very useful, but is also the most basic model you could use.
Re:Hack day report: Using Amazon Machine Learning to predict... by binarysolo on Friday July 17, 2015 @06:33PM (#9905738)
I need to look at the git repo to make better sense of what AML is doing and why their numbers are poor, but off-handedly: the way you structure the ML problem is basically the battle and how it'll do. (Feature extraction etc.) Blackboxing all that makes it really non-trivial to come up with a generalized solution for everything because it counts on the human to frame the problem still.

(Will comment more intelligently once I read the codebase itself.)