Assessing economic sentiment with newspaper text indices: evidence from Switzerland
摘要
This study extracts signals from more than 530,000 news articles from 15 large Swiss newspapers to measure economic sentiment in Switzerland. Economic sentiment includes consumer sentiment and business sentiment. The research period for the text sentiment analysis ranges from 2016 to 2022, so this analysis includes the impact of the COVID-19 lockdown period. I contribute two new indices: one measures news sentiment in the German-speaking part of Switzerland, and the other measures news sentiment in the French-speaking part of Switzerland. The two indices show strong comovement, but the sentiment in these two language regions is not identical. The indices are available and updatable in real time. In contrast to macroeconomic variables such as GDP estimates, news articles are not revised, making these text-based indices an interesting source of information for economic forecasters, especially in times of market turmoil.