WarwickDCS: From Phrase-Based to Target-Specific Sentiment Recognition

Abstract

We present and evaluate several hybrid systems for sentiment identification for Twitter, both at the phrase and document (tweet) level. Our approach has been to use a novel combination of lexica, traditional NLP and deep learning features. We also analyse techniques based on syntactic parsing and token-based association to handle topic specific sentiment in subtask C. Our strategy has been to identify subphrases relevant to the designated topic/target and assign sentiment according to our subtask A classifier. Our submitted subtask A classifier ranked fourth in the SemEval official results while our BASELINE and µPARSE classifiers for subtask C would have ranked second.