Predicting Digital Asset Prices using Natural Language Processing: a survey (2212.00726v1)

Abstract: Blockchain technology has changed how people think about how they used to store and trade their assets, as it introduced us to a whole new way to transact: using digital currencies. One of the major innovations of blockchain technology is decentralization, meaning that traditional financial intermediaries, such as asset-backed security issuers and banks, are eliminated in the process. Even though blockchain technology has been utilized in a wide range of industries, its most prominent application is still cryptocurrencies, with Bitcoin being the first proposed. At its peak in 2021, the market cap for Bitcoin once surpassed 1 trillion US dollars. The open nature of the crypto market poses various challenges and concerns for both potential retail investors and institutional investors, as the price of the investment is highly volatile, and its fluctuations are unpredictable. The rise of Machine Learning, and Natural Language Processing, in particular, has shed some light on monitoring and predicting the price behaviors of cryptocurrencies. This paper aims to review and analyze the recent efforts in applying Machine Learning and Natural Language Processing methods to predict the prices and analyze the behaviors of digital assets such as Bitcoin and Ethereum.