Predicting BIST 100 Index Movement by using Sentiment Scores and Technical Indicators during the COVID-19 Pandemic

Abstract

Sentiment analysis includes the stages of identifying the positive, negative or neutral emotions contained in the text data. Positive and/or negative emotions reflected by the text data can affect the decision-making processes of people, small or large-scale companies. Emotions reflected by documents can be vectorized with sentiment scores and these scores could be useful to forecast time series models. As it is known, the coronavirus, which emerged in Wuhan, China on December 1, 2019 caused a global pandemic all around the world. The Covid-19 pandemic has brought sharp and sudden declines in global and domestic stock markets. Within the scope of our study, it was analyzed whether the sentiment scores obtained from the Covid-19 related news documents were effective in forcasting the trend of the Bist100 index. Technical indicators that have great importance in estimating stock market indices, were also used in the analysis. Hence, the effect of sentiment scores and technical indicators in determining the trend of the stock market index during the pandemic could be observed. As a result of the study, it was observed that the sentiment scores were effective to predict the price trend of stock market index for some periods.