It seems obvious that cryptocurrency prices are influenced by social media; criticism levelled at famous people for even talking about cryptocurrencies is testament to that. But until now, no-one had used scientific methods to prove that a link actually exists.
New research now tells us that we were partly right – social media does affect cryptocurrency prices, but it isn’t necessarily the most well-known people that are responsible.
Two years’ worth of data
Feng Mai, a professor at the business school of Stevens Institute of Technology, a private research university in New Jersey, analysed two years of data to test his hypothesis that Bitcoin value can be manipulated by public sentiment as expressed through social media.
He worked in conjunction with the business school of the University of Cincinnati, and the results were published in Taylor and Francis Online.
For their study, the team focused on an online forum called Bitcointalk.org.
Bitcointalk has 2.2 million members and 454 new registrations every day, according to its own statistics page. It was created by Satoshi Nakamoto in December 2009 and saw its millionth post in July 2012. As of now it has seen almost 41 million posts and averages 8,340 posts a day.
The team also collected 3.3 million Twitter posts over a period of two months.
Reclassifying Your Traders as "Pros" - How Can You Do It Right?Go to article >>
Using a Python programme, they organised the comments into groupings of good, bad and neutral, and divided the people making the comments into two groups – frequent posters and infrequent posters. It should be noted here that frequent posters as a group were relatively small in number but produced 60 percent of the collected samples.
They then used vector error correction to compared these results with the corresponding price of Bitcoin. Vector error correction is useful to study phenomena with variables that are many and difficult/impossible to predict, such as the economy; for example, when studying Bitcoin price movements, variables such as stock market movements and gold prices also had to be taken into account. In addition to that, Bitcoin price/public sentiment is a two-way street: “Any changes in Bitcoin’s price are obviously going to affect the sentiment around it, so we needed to factor in those influences as well,” said Mai.
The first conclusion, which Mai called “robust”, confirms that prices are indeed affected by sentiment.
Said Mai: “Many of us probably intuitively believe this, but this was the first robust statistical finding to verify that social media and Bitcoin prices are actually linked.”
The second conclusion, which is slightly less obvious, is that the frequent posters had very little effect on the price of Bitcoin. In contrast, what the research refers to as the “silent majority”, that is, people who took the time to comment when they usually don’t, moved the price as much as ten times more when they posted something positive.
“Vocal users of social media may sometimes have a certain agenda, in this case hyping or boosting the price of Bitcoin because they themselves have invested in it. So if most of the social messages around Bitcoin are generated by people who are biased, the sentiments on social media may not actually accurately reflect the currency’s actual value,” said Mai.
“This was a big finding, and it does seem to prove that people are trusting the silent majority much more, perhaps because they do not seem to have an agenda,” he added.