SENSEI-LIF at SemEval-2016 Task 4: Polarity embedding fusion for robust sentiment analysis

Abstract

This paper describes the system developed at LIF for the SemEval-2016 evaluation campaign. The goal of Task 4.A was to identify sentiment polarity in tweets. The system extends the Convolutional Neural Networks (CNN) state of the art approach. We initialize the input representations with embeddings trained on different units: lexical, partof-speech, and sentiment embeddings. Neural networks for each input space are trained separately, and then the representations extracted from their hidden layers are concatenated as input of a fusion neural network. The system ranked 2nd at SemEval-2016 and obtained an average F1 of 63.0%.