Using Social Media Topics and Hawkes Models to Study Cryptocurrency Returns

Summary

This study investigates whether the timing and subject matter of cryptocurrency social media discussions are related to later price behavior. It applies dynamic topic modelling to communication in social media communities, then uses a Hawkes model to examine interactions between topic occurrences and cryptocurrency prices. The approach is intended to identify topics that may precede particular return patterns.

Reported associations include risk and investment versus trading discussions preceding price falls, talk of substantial price movements preceding volatility, and technical communities’ discussion of fundamental cryptocurrency value preceding price rises. These findings suggest possible inputs for trading or alerting systems, but the document does not report the sample construction, assets, predictive accuracy, or out-of-sample tests. The stated relationships are associations and should not by themselves be read as causal effects or as evidence of a profitable signal after execution costs.

Key ideas

• Dynamic topic modelling is used to track the timing of themes in cryptocurrency social media.
• A Hawkes model estimates interactions between topic activity and cryptocurrency price events.
• Some topics are reported to precede price falls, volatility, or price rises.
• The observed relationships could inform monitoring or signal systems, but predictive performance is not quantified.
• The document does not establish causality or trading profitability.

Tags

# Mutual-Excitation of Cryptocurrency Market Returns and Social Media Topics


# Mutual-Excitation of Cryptocurrency Market Returns and Social Media Topics









Cryptocurrencies have recently experienced a new wave of price volatility and interest; activity within social media communities relating to cryptocurrencies has increased significantly. There is currently limited documented knowledge of factors which could indicate future price movements. This paper aims to decipher relationships between cryptocurrency price changes and topic discussion on social media to provide, among other things, an understanding of which topics are indicative of future price movements. To achieve this a well-known dynamic topic modelling approach is applied to social media communication to retrieve information about the temporal occurrence of various topics. A Hawkes model is then applied to find interactions between topics and cryptocurrency prices. The results show particular topics tend to precede certain types of price movements, for example the discussion of 'risk and investment vs trading' being indicative of price falls, the discussion of 'substantial price movements' being indicative of volatility, and the discussion of 'fundamental cryptocurrency value' by technical communities being indicative of price rises. The knowledge of topic relationships gained here could be built into a real-time system, providing trading or alerting signals.

Shown in full with attribution under the source's licence. Licence: abstract CC0

This summary was written by Stratmill's research agent from the original; it is not a copy of the source.