Study Funded by Korean Government
A research paper entitled “When Bitcoin encounters information in an online forum: Using text mining to analyse user opinions and predict value fluctuation” was published last week. It is co-authored by five researchers from two universities in South Korea; Korea University and Kangnam University.
This study was supported by Basic Science Research Program through the National Research Foundation of Korea (NRF) funded by the Ministry of Education, Science, ICT and Future Planning. It is also funded by the Korean government through Institute for Information & communications Technology Promotion (IITP).
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.
The method used in this study involves data extraction, data gathering, data analysis and model development. Keywords of interest from user comments were extracted as well as daily bitcoin transaction counts and prices.
Data were crawled from the “Bitcoin Discussion” section of the Bitcointalk forum from December 1, 2013, to September 21, 2016. The daily bitcoin price and the number of transactions for the above period were crawled from Coindesk. In addition, Google Trends data and Wikipedia usage data were gathered using the keyword “Bitcoin”.
The relationship between the Bitcoin transaction count and price based on the extracted keywords and quantification was analyzed. “Then, we developed a model based on deep learning to predict the Bitcoin transaction count and price,” the paper details.
Over 80% Accuracy
After extensive analysis, the researchers concluded:
We analysed 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%.
“Online user postings influenced Bitcoin transactions,” the authors found, claiming that their method shed light on some aspects of how comments affect users’ decisions to buy and sell the cryptocurrency.
They then suggested various ways of improving the accuracy of prediction such as using quantitative analysis on search results or relevant content. Forum posts could also be filtered more meticulously for added accuracy.
In conclusion, they asserted that their method “is conducive to understanding a range of cryptocurrencies other than bitcoin and increasing their usability,” adding that it can also be useful in many other fields.
Do you agree with their finding that forum user comments can predict bitcoin’s price fluctuation with more than 80% accuracy? Let us know in the comments section below.
Images courtesy of Shutterstock