Bitcoin price prediction using sentiment analysis

Abstract

Aim: To explore the causal relationship between social media sentiment, other related behavioral factors and Bitcoin price performance. Secondary aim is to develop predictive models with higher accuracy in forecasting the Bitcoin price by incorporating sentiment analysis.

Methods: The sentiment analysis of 1.64 million Twitter posts (tweets) collected via web scraping was carried out using the VADER module. The data was collected in November and December 2021. Several forecasting models were created using average daily sentiment polarity, average daily number of tweets and search interest for "Bitcoin" on Google and Wikipedia as input variables. Future Bitcoin prices were predicted using VAR, Prophet and LSTM artificial neural network models. The predictive accuracy of the models was evaluated and compared using the mean absolute percentage error (MAPE) as a performance measure.

Results: The results suggest a Granger causal relationship between social media sentiment and Bitcoin prices. The standard VAR model achieved a MAPE of 8%, while the LSTM model had a lower error rate of 5%. The Prophet model had a MAPE of 11%.

Conclusion: Our results underline the highly speculative nature of Bitcoin, especially in times of high prices. Furthermore, the inclusion of behavioral variables in the development of Bitcoin price prediction models significantly improved the prediction accuracy. In particular, LSTM models for neural networks proved to be an extremely effective tool.