[vivekn]

While 95% accuracy would be a really phenomenal achievement, an accuracy in the range of 85-90% is achievable using methods simpler than deep neural nets. I have done some work on sentiment analysis in the past. I used a Naive Bayes model with some enhancements like n-grams, negation handling and information filtering and was able to get more than 88% accuracy on a similar dataset based on movie reviews.

You can find more details here -http://arxiv.org/ftp/arxiv/papers/1305/1305.6143.pdf and the code over here - https://github.com/vivekn/sentiment/blob/master/info.py