Sentiment Classification using Word Sense Disambiguation
Switch branches/tags
Nothing to show
Clone or download
Latest commit da13fdb Jan 20, 2018



This library is sited here.

iPhone App for Twitter Sentiments is Out

App no longer available. Sorry Due to lack of funds to run a seperate server App has been taken out of the app store. Use it free to build your own app tho

Sentiment Classification using WSD, Maximum Entropy & Naive Bayes Classifiers


Sentiment Classifier using Word Sense Disambiguation using wordnet and word occurance statistics from movie review corpus nltk. For twitter sentiment analysis bigrams are used as features on Naive Bayes and Maximum Entropy Classifier from the twitter data. Classifies into positive and negative labels. Next is use senses instead of tokens from the respective data.


Download Stats Provided by pypi-github-stats

Sentiment Classifiers and Data

The above online demo uses movie review corpus from nltk, twitter and Amazon,on which Naive Bayes classifier is trained. Classifier using WSD SentiWordNet is based on heuristics and uses WordNet and SentiWordNet. Test results on sentiment analysis on twitter and amazon customer reviews data & features used for NaiveBayes will be Github.


In Version 0.5 all the following requirements are installed automatically. In case of troubles install those manually.

How to Install

Shell command

python install


Script Usage

Shell Commands:

senti_classifier -c file/with/review.txt

Python Usage

Shell Commands

cd sentiment_classifier/src/senti_classifier/
python -c reviews.txt

Library Usage

from senti_classifier import senti_classifier
sentences = ['The movie was the worst movie', 'It was the worst acting by the actors']
pos_score, neg_score = senti_classifier.polarity_scores(sentences)
print pos_score, neg_score

... 0.0 1.75
from senti_classifier.senti_classifier import synsets_scores
print synsets_scores['peaceful.a.01']['pos']

... 0.25


  • 0.7 Python 3.0 suport Thanks to @MrLokans
  • 0.6 Bug Fixed upon nltk upgrade
  • 0.5 No additional data required trained data is loaded automatically. Much faster/Optimized than previous versions.
  • 0.4 Added Bag of Words as a Feature as occurance statistics
  • 0.3 Sentiment Classifier First app, Using WSD module