Brainwaves can predict audience reaction for television programming

news.gatech.edu

20 points·Libertatea··5 comments

At first glance this seemed really creepy and invasive, but it seems like they're just measuring 'engagement' and predicting user preference for ads. If that leads to more interesting ads, I'm not entirely opposed. On the other hand, it's treading awfully close to Huxley/Bradbury territory.

One step closer to converting all mass media into a homogenous slurry designed to appeal to a "broad audience" I guess.

Misleading title. Looks like they were able to predict 40-60% of the variance. And we're talking about tweets.

That doesn't seem too surprising to me. After working on some EEG projects in the past (coincidentally within gatech) coming up with meaningful correlations that generalize across multiple subjects is very nontrivial and for a number of features you're not going to find anything of much use.

Tweets also do seem to be a poor feature to try to track, but generating labels for anything regarding EEG related problems tends to be quite fickle and very subjective.

I look forward to the day we can track larger populations of this this data in real time. I say this because yesterday me and a good friend got back from a long road trip and one of the more interesting ideas I thought we discussed was the notion of an ever-increasing level of synchronicity between each of our creative/entertainment brainwaves, whether that increase in overlap could be mathematically predictable, and finally whether a gigantic clap of overlapping unified consciousness could be considered a type of singularity. We also joked about which of our favorite youtube videos could do it.

Reply on news.ycombinator.com