The Colour of Finance Words

49 Pages Posted: 21 Aug 2020 Last revised: 17 Jun 2022

See all articles by Diego Garcia

Diego Garcia

University of Colorado at Boulder - Leeds School of Business

Xiaowen Hu

University of Colorado at Boulder - Leeds School of Business

Maximilian Rohrer

NHH - Norwegian School of Economics

Date Written: June 14, 2020

Abstract

Our paper relies on stock price reactions to color words, in order to provide new dictionaries of positive and negative words in a finance context. We extend the machine learning algorithm of Taddy (2013), adding a cross-validation layer to avoid over-fitting. In head-to-head comparisons, our dictionaries outperform the standard bag-of-words approach (Loughran and McDonald, 2011) when predicting stock price movements out-of-sample. By comparing their composition, word-by-word, our method refines and expands the sentiment dictionaries in the literature. The breadth of our dictionaries and their ability to disambiguate words using bigrams both help to color finance discourse better.

Keywords: measuring sentiment, machine learning, earnings calls, 10-Ks, WSJ

JEL Classification: D82, G14

Suggested Citation

Garcia, Diego and Hu, Xiaowen and Rohrer, Maximilian, The Colour of Finance Words (June 14, 2020). Available at SSRN: https://ssrn.com/abstract=3630898 or http://dx.doi.org/10.2139/ssrn.3630898

Diego Garcia (Contact Author)

University of Colorado at Boulder - Leeds School of Business ( email )

Boulder, CO 80309-0419
United States

Xiaowen Hu

University of Colorado at Boulder - Leeds School of Business ( email )

Boulder, CO 80309-0419
United States

Maximilian Rohrer

NHH - Norwegian School of Economics ( email )

Helleveien 30
N-5045 Bergen
Norway

Do you have a job opening that you would like to promote on SSRN?

Paper statistics

Downloads
658
Abstract Views
2,336
rank
56,126
PlumX Metrics