Assessing economic sentiment with newspaper text indices: evidence from Switzerland

Marie-Catherine Bieri

Issue
2023-07

Pages
82

JEL classification
C53, C55, E21, E27, E37

Keywords
Economic sentiment, Sentiment analysis, Text-based Indicator

Year
2023

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