Investors’ behaviour is not only influenced by information on fundamentals, such as future cash flows, but also by soft parameters, such as moods, emotions, or feelings. Accordingly, stock returns and trading volume are only partially determined by fundamentals. Recently, the notion of “investor sentiment” has attracted the attention of scholars in finance and financial economics. Although the understanding of the nature of sentiment is still far from being complete, there is considerable empirical evidence that sentiment plays a crucial role for financial markets. In this project, we follow the idea that sentiment is a belief about future developments that is not built upon facts and rational reasoning. Accordingly, sentiment can be regarded as being equivalent to investors’ (non-fundamental) expectations. In this project, we aim to investigate the influence of sentiment for the case of the Berlin stock exchange between 1872 and 1930. We will use different computational sentiment analysis techniques (dictionaries, machine learning) to automatically extract sentiment from a daily column in the Berliner Börsen-Zeitung, which was the most important financial newspaper at the time. We will create a daily sentiment index which can be used to measure investors’ expectations as defined above. In combination with content analysis methods, such as topic modelling and stock market data, we will investigate the impact of expectations and the accompanying narratives on the Berlin stock market, both quantitatively and qualitatively. As we will apply different text mining methods on a large scale, we build this project on an interdisciplinary cooperation between economic history and digital humanities to address the following questions: How did historical experiences, such as wars and political or economic shocks, change investor sentiment, i.e. investors’ expectations, and how did sentiment influence financial markets? Has this influence changed over time? Which role did sentiment play in the development of financial and economic crises, and which were the narratives that accompanied high stock market fluctuations? Hence, our project aims to contribute directly to the priority programme’s three central questions.