Deciphering Federal Reserve Communication via Text Analysis of Alternative FOMC Statements
American Economic Journal: Macroeconomics · 2020 · Taeyoung Doh、Dongho Song、Shu-Kuei X. Yang
中文摘要
本文提出一种基于文本的货币政策立场度量方法，将FOMC声明建模为鸽派与鹰派替代文本的凸组合，从而为委员会在政策光谱上的位置提供一个可处理的表示形式。利用工作人员起草的替代性声明，我们对预训练语言模型进行微调，以同时捕捉量化精度与语义语气。立场被定义为语气与新奇性的乘积，并借助高频金融数据分解为预期成分与意外成分。意外源于语气相对预期的变化或声明的新奇性。我们的框架能够进行反事实分析，展示替代性沟通本可以如何影响市场。(JEL D83, D84, E31, E32, E43, E52, E58)
Abstract
We propose a text-based measure of monetary policy stance that models FOMC statements as convex combinations of dovish and hawkish alternatives, providing a tractable representation of the Committee's position along the policy spectrum. Leveraging staff-drafted alternative statements, we fine-tune a pretrained language model to capture both quantitative precision and semantic tone. Stance is defined as the product of tone and novelty, and decomposed into expected and surprise components using high-frequency financial data. Surprises arise from shifts in tone relative to expectations or from statement novelty. Our framework enables counterfactuals showing how alternative communication could have moved markets. (JEL D83, D84, E31, E32, E43, E52, E58)