Sentiment analysis towards listed companies in the energy sector on the example of the WIG-Energia index on the WSE

Abstract

The study consists of an experiment performed with the use of sentiment analysis, which allows to determine whether the introduction of the sentiment indicator is useful in a model that uses machine learning mechanisms to forecast changes in the price behaviour of companies in the energy sector.The aim of the study has been achieved by comparing the quality of the confusion matrix for the model in which the indicator resulting from the sentiment analysis was used with the model without this indicator. The study has shown that sentiment analysis is not a particularly useful tool in the analysis of stock exchange data of companies in the energy sector, which shows that sentiment analysis cannot be a decisive factor in investment decisions concerning companies in this sector.