Financial Correlation Modelling Using News and Social Media Data

This thesis compares the performance of various models that measure the relationship between news and stock price correlations. These models are analysed when they are applied on the different datasets. One dataset contains social media news while the other dataset contains news flows provided by Thomson Reuters. These datasets have consequently different characteristics. Social media news are much more dynamic, since it allows a wide range of audience an easy and fast access to gain and share information. On the other hand the news flow doesn’t spread as widely and quickly as the social media news flow. As a result of the different characteristics of these datasets, there is not one overall best performing model but one best performing model for each dataset.