This tool works by examining individual words and short sequences of words (n-grams) and comparing them with a probability model. The probability model is built on a prelabeled test set of IMDb movie reviews. It can also detect negations in phrases, i.e, the phrase "not bad" will be classified as positive despite having two individual words with a negative sentiment.

You can read more about the details of the model in this paper . The code for the web application and the training module is open source and available on Github .

I've also provided an API for this tool, details on how to use it are on this page

Author: Vivek Narayanan < >

sentiment analysis
text classification
text categorization
market sentiment
sentiment classification
text mining
tweet classification
twitter analysis
tweet analysis
social media analytics
social media analytics tools
textual analysis
opinion mining
twitter sentiment analysis
sentiment analysis of twitter data
sentiment analysis twitter