Emotions on the stock exchange. Can investor sentiment be measured? Yes, currently it is done on the basis of surveys (e.g. AAII Bull and Bear), a set of complex measures (Fear and Greed index) or an analysis of buying trends (Investor Sentiment Index). The latter means predicting the actions of stock buyers on the basis of … these actions, not an external indicator. And is it possible to measure emotions on the stock market and what does that mean? You will find out from the following article.
Research to date on the use of sentiment in forecasting stock market indices
In December 2018, the publication “Media Sentiment and International Asset Prices” appeared, published by the National Bureau of Economic Research, in which the authors analyze Reuters’ and Bloomberg’s articles in terms of their impact on major stock exchange indices. Researchers discovered interesting relationships between sentiment in the articles and index values, such as for example:
- The first mood of the news correlates 4x more strongly with the bear market (dominated by declines) than during the bull market boom,
- The second mood index is a much better reflection of the behaviour of world indices than the commonly used VIX (CBOE Volatility Index),
- and the positive mood in the media has a more positive impact on the developed markets.(but negative on the emerging markets).
Unfortunately, none of the approaches allowed for forecasts to be more than 55-60% accurate. This is probably not possible based on sentiment or emotional tags offered by social networking platforms like Twitter or Facebook.
Emotional monitoring for stock price forecasting
What if, using deep neural networks, we could combine media and emotion monitoring? In Sentimenti we have much more possibilities – 11 emotional variables. Our tools allow for automatic analysis of sentiment and emotion in texts. We check what is the sentiment and share of each of Plutchik’s 8 basic emotions in what Internet users write in a given period about a particular listed company and its products. We measure the arousal of each statement.
Thanks to that, we see if they like it, show anger or loathing, talk about trust in the brand. We measure how emotions change from day to day, week to week, one settlement period to another.
Then we compare the results of the analysis of emotions with hard indicators: WIG-Banks index, company share prices.
Emotions on the stock exchange. Forecasting on the Warsaw Stock Exchange
At the turn of November and December 2018 we tested our assumptions in practice. Therefore, we downloaded all the opinion-forming text data available on the Polish Internet about 50 randomly selected companies. We downloaded for the same period and the same entities the exchange rate data. Our team of financial analysts and artificial intelligence specialists prepared teaching scenarios for test models. When we checked their effectiveness. It turned out that in 87.1% of cases, changes in the intensity of emotions in texts about the company allow us to predict course changes!
We offer you a complete report. It showing how often we were able to predict changes in the share price only on the basis of an analysis of sentiment and emotion. Read it and check how many cases have been successful. We will only mention CD Projekt, KGHM Polska Miedź, Gino Rossi, Enea and Wawel.
Monitoring emotions as an indicator supporting trend analysis is a valuable tool for investors. It is the mood of the stock market reduced to a numerical form. Al without the need to ask anyone complicated questions. It is enough to monitor social media and the press.
We have carried out similar research for the cryptocurrencies market, and it is worth getting to know them.