INF-UFG at FiQA 2018 Task 1: Predicting Sentiments and Aspects on Financial Tweets and News Headlines

Abstract

This paper describes our system which participate in Task 1 of FiQA 2018. The task's focuses was to predict sentiment and aspects of financial microblog posts and headlines. The sentiment analysis for a specific company had to be predicted using a scale between -1 and 1, while the aspect prediction had to be predicted using a set of aspects which was given in train data. We had used Support Vector Regression (SVR) to predict the sentiments in both cases (microblog posts and headlines).