美國聯準會會議紀要的文字探勘與台灣經濟變數預測

Text Mining of the FOMC Minutes and Forecasts of Taiwan Economic Variables

黃裕烈(Yu-Lieh Huang) ； 管中閔(Chung-Ming Kuan)

《經濟論文叢刊》 47卷3期 (2019/09) Pp. 363-391

https://doi.org/10.6277/TER.201909_47(3).0002

摘要

本文利用文字探勘的技巧，從美國聯邦公開市場委員會（Federal Open Market Committee,簡稱FOMC）所發表的正式官方文件：minutes of the FOMC中萃取出重要的資訊，再利用情緒分析來判斷FOMC對三大經濟「使命」的正／負面看法，並建立指標，以預測台灣的財經相關變數。相較於之前的文獻，本文統一FOMC常用的專門術語，並且考慮了複合字的情況；這可以避免後續在計算文字字數時，產生重覆計算以及語意錯誤的情況。我們也利用統計模型（MAP-PLSA）將每一份文件中的句子依據FOMC的經濟使命分成三個主題，再利用情緒分析技巧，建立各類主題的指標數列。最後，我們以迴歸模型來分析情緒指標與台灣相關財經變數之間的關聯性。

關鍵字

文字探勘 ； 美國聯邦公開市場委員 ； 主題模型 ； 情緒分析

並列摘要

In this paper we extract useful information from the minutes of the Federal Open Market Committee (FOMC) and examine how such information can help predict economic/financial variables. Based on the minutes during 1993-2016, we conduct sentiment analysis to determine the FOMC's attitude towards different topics, i.e., the mandates of the FED. Our approach is different from related studies in the following respects. First, we identify compound words which carry more specific meaning than do single words. Second, we adopt the topic model, MAP-PLSA, for estimating the conditional probabilities of these words/terms, which in turn can be used to classify sentences in the minutes under different topics. Third, the attitude towards each topic is determined by the ＂tone＂ of its sentences. We then proceed to evaluate whether the FOMC's attitude towards different topics can be used to improve economic forecasts.

並列關鍵字

federal Open Market Committee ； sentiment analysis ； text mining ； topic models

參考文獻

Banchs, Rafael (2012), Text Mining with MATLAB, New York: Springer Sci- ence and Business Media.

Berger, Helge, Jakob de Haan, and Jan-Egbert Sturm (2011), “Does Money Matter in the ECB Strategy? New Evidence Based on ECB Communi- cation," International Journal of Finance and Economics, 16(1), 16–31.

Bernd, Hayoa and Matthias Neuenkirch (2013), “Do Federal Reserve Pres- idents Communicate with a Regional Bias?" Journal of Macroeconomics, 35(4), 62–72.

Blei, David M., Andrew Y. Ng, and Michael I. Jordan (2003), “Latent Dirichlet Allocation," Journal of Machine Learning Research, 3(1), 993– 1022.

Chien, Jen-Tzung and Meng-Sung Wu (2008), “Adaptive Bayesian Latent Semantic Analysis," IEEE Transactions on Audio, Speech, and Language Processing, 16(1), 198–207.