News for hackers. Stuff that matters.
Re:Ask HN: Sentiment Analysis – how to handle biased word li... by dhammack on Friday February 20, 2015 @09:28AM (#9080520)
If you think the true sentiment is symmetric, you can just change the decision threshold so that your algorithm answers positively about half the time. Just say positive when the sentiment is greater than the mean sentiment over your training set.
Re:Ask HN: Sentiment Analysis – how to handle biased word li... by markovbling on Friday February 20, 2015 @09:54AM (#9080629)
This is an interesting approach to normalisation - will give it a go :)