The objective of this project is to create market sentiment indicators for cryptocurrencies. Market sentiment indicators are built from text analysis of exchanges on Twitter and other sources, that may include embedded or references images (e.g., price curves) and videos. The text dataset for cryptocurrencies may have a very structure from that of traditional currencies. For example, cryptocurrency tweets may reference ‘mining’, which is a concept that does not exist for traditional currencies. Challenges in deriving sentiment indicators arise due to the structure of the tweets, which are very short, but which can reference longer documents, and contain sarcasm and humor that are often present in cryptocurrency discussions. We shall work with the partner to develop methods from machine learning and natural language that that perform well in detecting market sentiment indicators for cryptocurrencies and incorporate these indicators into future modelling frameworks and products.