Events such as COVID-19 and the U.S. presidential elections have made 2020 a year unlike any other. Below is a summary of 10 of the most interesting data insights we drew from news analytics and sentiment data in 2020.
1. News about “Anger” was found to erode Trump’s election winning chances.
Analyzing the relationship between levels of news about “Anger” and different candidates’ winning chances revealed that the more “Anger” was covered in the news the more Trump’s projected chances of winning the U.S. election slipped.
The opposite was true of Biden where mentions of “Anger” forewarned of improving winning chances.
2. Analyzing news sentiment around companies’ scheduled earning dates can bring 8% more annual returns.
When companies change the dates of their official earnings releases it is often thought to be because they want to delay the release of bad news or bring forward the release of good news.
A portfolio investment strategy that put this theory to the test and added news sentiment into the mix produced solid annual excess returns of 8.4%, for mid to large-cap stocks and 18.6% for small-caps.
3. In the run-up to the U.S. election, it became clear this was not going to be a referendum on the administration’s handling of the Covid pandemic.
There was no evidence the U.S. presidential election was a ‘referendum’ on the administration’s response to the Covid-19 pandemic.
Although a link between the two was noted in the Spring, Trump’s projections were largely unaffected by Covid news during the months of June and between mid-August and early October. Polls also seem to have been unmoved by mentions of the virus.
4. It was possible to predict the winner of the presidential election using news analytics alone, without having to canvas a single voter.
According to our media monitor, Biden’s sentiment consistently remained above Trump’s from March 2020 till election day.
On the day before the election, our model was forecasting Biden to win by 313 electoral college votes (ECV) to 225. In the end, Biden won by 306 to Trump’s 232. The sentiment-based model was only 7 ECVs off the actual result.
5. Carry traders in the FX market can use news sentiment to enhance their trading strategies.
When we tested to see if our news sentiment data could enhance more traditional factors in the global FX market, such as the carry, value and momentum we found the resulting model was 3 times more effective than that which was based on traditional factors alone.
6. A news analytics-based model warned of both the June and November UK lockdowns.
A media exposure gauge using our data correctly forecast both major UK lockdown periods, starting with the Leicester lockdown in June and then the tougher lockdown in November.
7. Levels of media hype around the Coronavirus successfully predicted the beginnings and ends of the various waves of the Coronavirus pandemic.
A measure of the volume of news about Covid, the Media Hype Index, and another index - the Panic Index - that measured the level of concern in the media, provided interpretable warning signals of the various peaks of the coronavirus pandemic as well as the March stock market trough.
8. Companies in the BioPharma sector with the highest levels of Covid news were also those that went on to make the greatest stock market gains.
Research from earlier in the year uncovered a close connection between the number of times a BioPharma company was co-mentioned with COVID-19 in the news and changes to its share price.
The conclusion was that BioPharma stocks with “a higher co-mention volume with the virus were also the top performers in their sector,” wrote Peter Hafez, Chief Data Scientist, at RavenPack.
9. Signals based on the buying and selling of company shares by ‘insiders’ timed the market peaks and troughs of the Covid pandemic.
News about how company executives trade their shares, also known as insider transactions data, can provide investors an information edge and could have forewarned of the major market turns caused by Covid.
A trading strategy based on insider insights delivered, “a robust global portfolio performance with little exposure to systematic risk factors,” says Peter Hafez, Chief Data Scientist at RavenPack
10. News sentiment has been found to accurately forecast central bank policy decisions.
A growing corpus of research shows that news analytics can help forecast central bank policy moves by analyzing relevant news in the run-up to scheduled meetings.
A study undertaken by researchers at the Bank of International Settlements (BIS) found news analytics outperformed a leading economist’s survey at predicting interest rate changes by the Bank of Indonesia (BOI).