Twitter and Google Trends Interest Precedes Cryptocurrency Price, Study Finds
The volume of tweets and the Google Search Volume Index (SVI) was found to be leading price indicators for Bitcoin and Ethereum, according to a research paper published by Southern Methodist University.
Importance of sentiment
In the paper, researchers gathered data on Twitter mentioning bitcoin and ethereum; The same was done using Google's trends. Based on the ideas of previous research, the hypothesis is that the number of tweets and their emotions (positive and negative) can affect prices. In the study, it was revealed that the number of tweets and Google searches change first before the prices do.
The role of emotion in technical or market analysis is to uncover people's attitudes to an entire market or individual index (in this case Bitcoin and ether). The emotional analysis theory is a boundary of technical analysis that states that the price reduces everything and that ultimately the price development is a reflection of people's psychology.
Therefore, in theory, if you could measure how positive or negative the people's shared views are against a particular stock or crypto competition, you can estimate the price path.
Although in this study, tweet volume and not sentiment were found, it turned out to be a leading factor in the price of cryptographic curves. The lack of emotion as the leading factor was theorized because of the amount of "noise" it is on Twitter about the currencies relative to the actual conversation.
For example, researchers found that 21[ads1] million bots on Twitter wrote the most information about prices, ads, spam, etc. Not people have real discussions about how they feel about either Bitcoin or Ethereum.
The other problem scientists found with Twitter was that emotions were most positive in nature – although the prices of Bitcoin and Ethereum fell.
People who tweet about cryptographic baskets, even when prices fall, have an interest in them beyond investment opportunities, making the tweets biased toward positive.
Despite their findings, the researchers did not completely rule out sentiment analysis using various modeling techniques.
Methodology
In the study, researchers used to open source VADER (Valence Aware Diction ary and Sentiment Reasoner) to analyze tweet data. Tweet data was taken back to 2014 using the bitinfocharts.com website. Google Trends Data (SVI) was taken as far back as 2004 scaled in relation to all search queries for all Bitcoin and Ethereum terms.
Results
For Google trends data, the report found that the price was very correlated with search for the keyword Bitcoin and Ethereum, and that these search peaks occurred before the actual price increase was observed.
Another strong correlation between Twitter and Bitcoin's price was found, except for this time of more convincing results.
Finally, the results of Google trends and tweet data were also used in machine learning. a linear model for verifying the positive correlations. The data was divided between a training model and testing in an 80% and 20% split.
Social Media helps Monitor Investor & # 39; Chatter & # 39;
The VADER data can provide some valuable data for investors in measuring market sentiment.
Formerly Bitcoinist has covered the importance of social media chats on Twitter before with tools like the Twitter Hype Index. But this is the first time Twitter and SVI data have proven to lead and not follow the prices of most popular cryptocurrencies.
Can social media provide valuable trading insights? Share your thoughts below!
Pictures via Shutterstock