Recently a study conducted in South Korea found out that forum comments can be used to predict the variations in the price of Bitcoins to an accuracy of over 80%. The research paper is entitled “When Bitcoin encounters information in an online forum: Using text mining to analyze user opinions and predict value fluctuation”
The research paper was produced by five researchers from two universities in South Korea; Korea University and Kangnam University. The study which was supported by the Basic Science Research Program through the National Research Foundation of Korea (NRF) funded by the Ministry of Education, Science, ICT and Future Planning was also funded by the Korean government through the Institute for Information and Communication Technology promotion (IITP).
On a brief of the research and its significance in predicting Bitcoin prices, the authors mentioned in the research that;
“In order to predict the price fluctuation of Bitcoin, we analyze the comments posted in the Bitcoin online forum. Our approach involved extracting keywords from Bitcoin-related user comments posted on the online forum with the aim of analytically predicting the price and extent of transaction fluctuation of the currency.”
What method of data collection and analysis was used in this Research?
The accuracy of the findings of a research depends to a big extent on the methods used for data collection and analysis. According to the authors, the method used involved data extraction, data gathering, data analysis and development of models. Models would be tested to simulate how the prediction process works. The research main data involved keywords of user comments in major bitcoin forums and number of bitcoin transaction against their corresponding prices. The study covered data collected for a period of three years from 2013 to 2016. The study whose data was analyzed by an artificial intelligent model established the relationship between Bitcoin transaction count and price based on the extracted keywords and quantification.
High level of accuracy:
The study produced models with very high levels of accuracy in relating bitcoin price trends with the trends of the activities happening in Bitcoin Forums. The authors found out that online user postings influenced Bitcoin transaction which affects Bitcoin prices in return. The authors said in a statement that,
“We analyzed the user comments posted on a Bitcoin online forum to predict the fluctuation in the bitcoin price and transaction count. Based on the easily accessible online data, the proposed method predicted the bitcoin price fluctuation with an accuracy rate of over 80%.”
Do the models apply for all digital currencies?
The researchers were so confident that their models can be applied to predict the price of any digital currency. However, they suggested ways for improving the accuracy of the results. The researchers mainly emphasized the use of quantitative analysis on the search results or relevant content. This kind of research can also be adapted in other fields apart from digital currencies.