General Information

What is Sentiment140?

Sentiment140 (formerly known as "Twitter Sentiment") allows you to discover the sentiment of a brand, product, or topic on Twitter.

How does this work?

You can read about our approach in our technical report: Twitter Sentiment Classification using Distant Supervision. We also added new pieces that aren't described in this paper.

How is this different?

Our approach is different from other sentiment analysis sites because:
  • we use classifiers built from machine learning algorithms. Some other sites use a simpler keyword-based approach, which may have higher precision, but lower recall.
  • we are transparent in how we classify individual tweets. Other sites do not show you the classification of individual tweets and only show aggregated numbers, which makes it difficult to assess how accurate their classifiers are.

Who created this?

Sentiment140 was created by three Computer Science graduate students at Stanford University: Alec GoRicha Bhayani, and Lei Huang.

How did it start?

Sentiment140 started as a class project from Stanford University. We explored various aspects of sentiment analysis classification in the final projects for the following classes:

What are the use cases?

  1. Brand management (e.g. windows 7)
  2. Polling (e.g. obama)
  3. Purchase planning (e.g. kindle)
Can you help me?

We like helping people with machine learning, natural language processing, or social media analysis questions. Feel free to contact us if you need help.

Related work

If you like Sentiment140, you might like Twitter Earth, which allows you to visualize tweets on Google Earth.