Paper: SAP-RI: Twitter Sentiment Analysis in Two Days

ACL ID S14-2091
Title SAP-RI: Twitter Sentiment Analysis in Two Days
Venue Joint Conference on Lexical and Computational Semantics
Year 2014

We describe the submission of the SAP Research & Innovation team to the Se- mEval 2014 Task 9: Sentiment Analy- sis in Twitter. We challenged ourselves to develop a competitive sentiment anal- ysis system within a very limited time frame. Our submission was developed in less than two days and achieved an F 1 score of 77.26% for contextual polar- ity disambiguation and 55.47% for mes- sage polarity classification, which shows that rapid prototyping of sentiment anal- ysis systems with reasonable accuracy is possible.