I worry that if they're using sentiment analysis that they're not correctly isolating out the multitude of hidden variables involved with analyzing journalistic text. Examples include journalistic bias, extreme quotes from one viewpoint juxtaposed to moderate quotes from an opposing viewpoint, etc. Then again, the more data you throw at a model, the better its predictions become, even using terribly naive algorithms. Since they're in the terabytes range, it's certainly credible.

Could use a year's worth of updating. But definitely establishes their present situation is just part of the trajectory they've had for some time.

Good read! I wonder if there are chemical factors to ego depletion that could be combatted by a supplement. Sounds like a good thesis for a cogsci or medical student.

I think you would have done just as well saying it's an arduino blog. Pretty cool proof of concepts here.

A little disappointed that ctrl+F for "monsanto" yielded no results.

The only thing they miss when closing the gap between twin speak and developmental disability is maybe a comparison with feral or abused children with linguistic abnormalities. The Jeannie case study would have been a good one to parallel with the Kennedy girls. I will definitely rent that movie when it gets rereleased.

Any additional backstory on this? Did someone preprogram the A/V part, or did they really go the extra mile of instantaneously generating text to speech and then parsing speech to text to feed into the chatbot?

All this means is that my phone will be out of date soon. Boo!

Just in case anyone was wondering, I did five minutes worth of research and it doesn't look like a scam. Verified by DealNews and CNET.