Is Positive Sentiment in Corporate Annual Reports Informative? Evidence from Deep Learning

54 Pages Posted: 15 Aug 2019

See all articles by Mehran Azimi

Mehran Azimi

University of Alabama, Culverhouse College of Commerce & Business Administration, Students

Anup Agrawal

University of Alabama - Culverhouse College of Commerce & Business Administration

Date Written: July 2019

Abstract

We use a novel text classification approach from deep learning to more accurately measure sentiment in a large sample of 10-Ks. In contrast to most prior literature, we find that positive, and negative, sentiment predicts abnormal return and abnormal trading volume around 10-K filing date and future firm fundamentals and policies. Our results suggest that the qualitative information contained in corporate annual reports is richer than previously found. Both positive and negative sentiments are informative when measured accurately, but they do not have symmetric implications, suggesting that a net sentiment measure advocated by prior studies would be less informative.

Keywords: Corporate annual reports, 10-K filings, Textual analysis, Textual sentiment classification, Deep learning

JEL Classification: C81, D83, G10, G14, G30, M41

Suggested Citation

Azimi, Mehran and Agrawal, Anup, Is Positive Sentiment in Corporate Annual Reports Informative? Evidence from Deep Learning (July 2019). Available at SSRN: https://ssrn.com/abstract=3258821 or http://dx.doi.org/10.2139/ssrn.3258821

Mehran Azimi

University of Alabama, Culverhouse College of Commerce & Business Administration, Students ( email )

AL
United States

Anup Agrawal (Contact Author)

University of Alabama - Culverhouse College of Commerce & Business Administration ( email )

Culverhouse College of Business
EFLS, Box 870224
Tuscaloosa, AL 35487-0224
United States
205-348-8970 (Phone)
205-348-0590 (Fax)

HOME PAGE: http://aagrawal.people.ua.edu/

Register to save articles to
your library

Register

Paper statistics

Downloads
450
Abstract Views
2,330
rank
63,813
PlumX Metrics