UniPI at SemEval-2016 task 4: Convolutional neural networks for sentiment classification

Abstract

The paper describes our submission to the task on Sentiment Analysis on Twitter at SemEval 2016. The approach is based on a Deep Learning architecture using convolutional neural networks. The approach used only word embeddings as features. The submission used embeddings created from a corpus of news articles. We report on further experiments using embeddings built for a corpus of tweets as well as sentiment specific word embeddings obtained by distant supervision..