Umigon is developed since December 2012 as a web application providing a service of sentiment detection in tweets. It has been designed to be fast and scalable. Umigon also provides indications for additional semantic features present in the tweets, such as time indications or markers of subjectivity.
Umigon is in continuous development, it can be tried freely at www.umigon.com.
Its code is open sourced at: https://github.com/seinecle/Umigon.

hdl.handle.net/1765/104171
2nd Joint Conference on Lexical and Computational Semantics, *SEM 2013
Department of Marketing Management

Levallois, C. (2013). Umigon: Sentiment analysis for tweets based on lexicons and heuristics. In *SEM 2013 - 2nd Joint Conference on Lexical and Computational Semantics (pp. 414–417). Retrieved from http://hdl.handle.net/1765/104171