姜富伟，中央财经大学

In this paper we apply economic narratives to inflation forecasting using a large news corpus and machine learning algorithms. We measure economic narratives quantitatively from the full text content of over 880,000 Wall Street Journal articles and represent them as interpretable news topics. The results indicate that narrative-based forecasts are more accurate than the benchmarks both in-sample and out-of-sample, which perform especially well during recession periods. Narrative-based forecasts perform better in the long-run forecasting, suggesting that narratives help to capture the slowly-varying trend inflation objectives. Information about inflation expectations and prices of specific goods embedded in narratives contributes to its predictive power. Overall, we provide a novel representation of economic narratives and highlight the important role of economic narratives in inflation forecasting.