This paper applies algorithmic analysis to financial market text-based data to assess how narratives and sentiment might drive financial system developments. We find changes in emotional content in narratives are highly correlated across data sources and show the formation (and subsequent collapse) of exuberance prior to the global financial crisis. Our metrics also have predictive power for other commonly used indicators of sentiment and appear to influence economic variables. A novel machine learning application also points towards increasing consensus around the strongly positive narrative prior to the crisis. Together, our metrics might help to warn about impending financial system distress.

No abstract

No abstract

This paper applies algorithmic analysis to financial market text-based data to assess how narratives and sentiment might drive financial system developments. We find changes in emotional content in narratives are highly correlated across data sources and show the formation (and subsequent collapse) of exuberance prior to the global financial crisis. Our metrics also have predictive power for other commonly used indicators of sentiment and appear to influence economic variables. A novel machine learning application also points towards increasing consensus around the strongly positive narrative prior to the crisis. Together, our metrics might help to warn about impending financial system distress.

This paper investigates the role of sentiment in the US economy from 1920 to 1934 using digitised articles from The Wall Street Journal. We derive a monthly sentiment index and use a 10-variable vector error correction model to identify sentiment shocks that are orthogonal to fundamentals. We show the timing and strength of these shocks and their resultant effects on the economy using historical decompositions. Intermittent impacts of up to 15 per cent on industrial production, 10 per cent on the S&P 500 and bank loans, and 37 basis points for the credit risk spread suggest a large role for sentiment.