Paper: AUEB: Two Stage Sentiment Analysis of Social Network Messages

ACL ID S14-2015
Title AUEB: Two Stage Sentiment Analysis of Social Network Messages
Venue Joint Conference on Lexical and Computational Semantics
Session
Year 2014
Authors

This paper describes the system submit- ted for the Sentiment Analysis in Twitter Task of SEMEVAL 2014 and specifically the Message Polarity Classification sub- task. We used a 2?stage pipeline approach employing a linear SVM classifier at each stage and several features including mor- phological features, POS tags based fea- tures and lexicon based features.