On: Perspective API – An API that makes it easier to host better conversations

[mr_luc]

I remember (from building a sentiment analysis irc bot[1] back in the day that used the afinn wordlist) that sentiment analysis is effective because robots can do mid-70%-accurate classification, but humans only agree around 80% of the time on 'positive/negative' classification.

So I always wonder, if simple models like the afinn wordlist work at close-to-human levels, how much total value is added by the more robust model. Still very cool!

---

[1] https://github.com/mrluc/cku-irc-bots/blob/master/feelio.cof... - included the following line of code, which is a coffeescript crime but also a cute sentence:

    if i_feel_you then @maybe @occasionally, => say i_feel_you