Exploring the experience-expectation nexus in macroeconomic forecasting using computational text analysis and machine learning (renewal application to "macroeconomic forecasting in great crisis")

点击翻译按钮获取中文摘要

Based on the findings of the first project period and using the quantitative and qualitative data collected so far in the first work package we will use methods from corpus linguistics (sentiment analysis, topic models) to investigate the experience-expectation nexus and the role of ideology for the production of macroeconomic forecasts. This includes several channels: the selection and assessment of incoming information, the possible strategic usage of forecasts to enforce economic policy reaction, and the impact of the mentioned aspects on the formation of textually expressed expectations.In the second work package we will make use of several results of the corpus-linguistic analysis to investigate aspects of forecast optimality using non-linear methods and machine learning tools, and we will use machine-learning tools to improve the computer-linguistic analysis further.In the third work package we will analyse several other aspects and research gaps in the experience-expectation nexus relevant for macroeconomic forecasts which all explicitly call for the combination of qualitative and quantitative data.The borders between the work packages are not sharp. We expect to realize strong synergy effects between the work packages and through discussions with other related projects of the Priority Program.