RiTUAL-UH at SemEval-2017 Task 5: Sentiment Analysis on Financial Data Using Neural Networks

Abstract

In this paper, we present our systems for “SemEval-2017 Task-5 on Fine-Grained Sentiment Analysis on Financial Microblogs and News”. In our system, we combined hand-engineered lexical, sentiment, and metadata features with the representations learned from Convolutional Neural Networks (CNN) and Bidirectional Gated Recurrent Unit (Bi-GRU) having Attention model applied on top. With this architecture we obtained weighted cosine similarity scores of 0.72 and 0.74 for subtask-1 and subtask-2, respectively. Using the official scoring system, our system ranked in the second place for subtask-2 and in the eighth place for the subtask-1. However, it ranked first in both subtasks when evaluated with an alternate scoring metric.