Forecasting the IBEX-35 stock index using deep learning and news emotions

Measuring the informational content of text in economic and financial news is useful for market participants to adjust their perception and expectations on the dynamics of financial markets. In this work, we adopt a neural machine translation and deep learning approach to extract the emotional content of economic and financial news from Spanish journals. To this end, we exploit a dataset of over 14 million articles published in Spanish newspapers over the period from 1st of July 1996 until 31st of December 2019. We then examine the role of these news-based emotions indicators in forecasting the Spanish IBEX-35 stock market index by using DeepAR, an advanced neural forecasting method based on auto-regressive Recurrent Neural Networks operating in a probabilistic setting. The aim is to evaluate if the combination of a richer information set including the emotional content of economic and financial news with state-of-the-art machine learning can help in such a challenging prediction task. The DeepAR model is trained by adopting a rolling-window approach and employed to produce point and density forecasts. Results look promising, showing an improvement in the IBEX-35 index fitting when the emotional variables are included in the model.