Abstract
The network of developers in distributed ledgers and blockchains open source projects is essential to maintaining the platform: understanding the structure of their exchanges, analysing their activity and its quality (e.g. issues resolution times, politeness in comments) is important to determine how “healthy” and efficient a project is. The quality of a project affects the trust in the platform, and therefore the value of the digital tokens exchanged over it.In this paper, we investigate whether developers’ emotions can effectively provide insights that can improve the prediction of the price of tokens. We consider developers’ comments and activity for two major blockchain projects, namely Ethereum and Bitcoin, extracted from Github. We measure sentiment and emotions (joy, love, anger, etc.) of the developers’ comments over time, and test the corresponding time series (i.e. the affect time series) for correlations and causality with the Bitcoin/Ethereum time series of prices. Our analysis shows the existence of a Granger-causality between the time series of developers’ emotions and Bitcoin/Ethereum price. Moreover, using an artificial recurrent neural network (LSTM), we can show that the Root Mean Square Error (RMSE)—associated with the prediction of the prices of cryptocurrencies—significantly decreases when including the affect time series.
Highlights
The ecosystem of cryptocurrencies traded and exchanged every day has been exponentially growing over the past ten years
2 Dataset and methods we describe how affect time series are constructed using the comments of Ethereum and Bitcoin developers on Github for the period of December 2010 to August 2017
3 Results we summarise the results of our analysis concerning testing for (i) causality between affect time series and cryptocurrency returns and (ii) improvement in Root Mean Square Error (RMSE) for the prediction of returns when including affect time series
Summary
The ecosystem of cryptocurrencies traded and exchanged every day has been exponentially growing over the past ten years. We focus our investigation precisely on the impact of developers’ activities and emotions, sentiment and politeness on the cryptocurrencies issued and transferred over the platform they contribute to develop. The main idea of this study is to understand whether emotions mining, sentiment analysis, politeness, and VAD analysis can be used to improve the prediction power of machine learning algorithms for the returns of the Bitcoin/Ethereum cryptocurrency. These metrics could be useful to monitor the health and quality of projects and platforms from a software engineering point of view.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
