The Impact of News Media on Cryptocurrency Prices: Modelling Data Driven Discourses in the Crypto-Economy

Natural Language Processing was adopted in this study to model data driven discourses in the crypto economy. Utilising topic modelling, specifically Latent Dirichlet Allocation (LDA), a text analysis of cryptocurrency articles (N=4218) published from over 60 countries in international news media, identified key topics associated with cryptocurrency in the international news media from 2018 to 2020. This study provides empirical evidence that 18 key topics were framed around the following key macro discourses: crypto related crime, financial speculation and investment, financial governance and regulation, political economy (with reference to specific geographical areas), cryptocurrency actors and communities and specific crypto projects and their respective markets. Analysis showed that the identified cryptocurrency macro discourses may have had a ‘social signal’ effect on movements in the crypto financial markets, including potential effects of crypto price volatility. Further in some cases, that the source of the news may have amplified the effect, particularly in terms of geographical region, relative to broader market conditions.