The vast amounts of user-generated content on the Web produces information overload more frequently than enlightenment. How do we get the big picture on what people are thinking?
Twitter Weather reduces large quantities of text into meaningful data, visualizing the prevailing mood by rendering a weather-report-style display. Positive and negative feelings about a topic are mapped to a "temperature" from 0 to 100. Supporting Twitter Weather is a user-trained Bayesian classifier that aggregates and ranks emotional content on a topic.
Experimental Comment Weather bookmarklet for news sites. When you're reading an article, click on it to get the emotional weather of the comments at a glance. Note that Internet comments tend to be negative, so think of it as the climate in London in March — 50 degrees is a great day.
Done with the help of Stephanie Bian, who wrote the initial classifier. I built on that and wrote the backend in Python, multithreaded for performance. This service fed visualizations in HTML and Quartz Composer.