News for hackers. Stuff that matters.
Re:Wells Fargo uncovers up to 1.4M more fake accounts by Steeeve on Sunday September 03, 2017 @04:43PM (#15163792)
That is very interesting. Can I ask how you discern whether an article is related to ethics?
Re:Wells Fargo uncovers up to 1.4M more fake accounts by cknight on Sunday September 03, 2017 @04:52PM (#15163839)
Simply by erasing stop words from a headline and then scanning the remaining terms for likely hits. The media has quite a few terms it likes to repetitively use in headlines for certain topics. I currently have about 100 terms to check a headline against. Think words like "environment", "bribe", "scandal", "accuse", "working conditions", etc...

It's... not a sophisticated system. It misses some major stories, gives me a few false positives, and of course lots of duplicates from differing sources.

But compared to what I had before (basically, nothing) it's a million times better.

Re:Wells Fargo uncovers up to 1.4M more fake accounts by Santzes on Monday September 04, 2017 @03:58AM (#15166500)
If you have enough training data I think a Bayesian filter might work well and be easy to set up