Skip to main content
This is a pre-production deployment of Warehouse. Changes made here affect the production instance of PyPI (
Help us improve Python packaging - Donate today!

SAIL/AIL Sentiment Analyzer

Project Description

This is a tool for doing sentiment analysis. The short-term goal of this project is to share the sentiment analysis research. The long-term goal of this project is to allow researchers the ability to demonstrate and test sentiment analysis tools, so that performance can be evaluated and compared.

Currently, the models are trained on Twitter data from the 2012 US Presidential election. In the future we hope to have general models as well as models for other domains.

This code was first released by the collaboration of two labs at the University of Southern California (USC), the Signal Analysis and Interpretation Laboratory (SAIL) and Annenberg Innovation Laboratory (AIL). The sentiment research at SAIL is supported by grants including NSF, NIH, and DARPA. The sentiment research at AIL is sponsored by the lab sponsors, especially IBM, an AIL founding sponsor, and Orange, the flagship brand of France Telecom.

This work was made possible by using existing open source projects and code. NLTK ( provides some of the basic classes of the SASA tool, e.g. frequency distributions and classifiers. Christopher Potts’ twitter-specific tokenizer for sentiment analysis is used for tokenization.

Release History

This version
History Node


History Node


History Node


Download Files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Filename, Size & Hash SHA256 Hash Help File Type Python Version Upload Date
(2.9 MB) Copy SHA256 Hash SHA256
Source None Apr 30, 2013

Supported By

Elastic Elastic Search Pingdom Pingdom Monitoring Dyn Dyn DNS Sentry Sentry Error Logging CloudAMQP CloudAMQP RabbitMQ Heroku Heroku PaaS Kabu Creative Kabu Creative UX & Design Fastly Fastly CDN DigiCert DigiCert EV Certificate Google Google Cloud Servers