Understanding Sentiment Through Context

80 Pages Posted: 2 Jan 2023

See all articles by Richard M. Crowley

Richard M. Crowley

Singapore Management University - School of Accountancy

M.H. Franco Wong

University of Toronto - Rotman School of Management

Date Written: December 30, 2022

Abstract

We examine whether empirical results using text-based sentiment of U.S. annual reports depend on the underlying context, within documents, from which sentiment is measured. We construct a clause-level measure of context, showing that sentiment is driven by many different contexts and that positive and negative sentiment are driven by different contexts. We then construct context-level sentiment measures and examine whether sentiment works as expected at the context-level across four prediction problems. Our results demonstrate that document-level sentiment exhibits significant noise in prediction and suggest that document-level aggregation of sentiment leads to missed empirical nuances. The contexts driving sentiment results vary substantially by outcome, suggesting lower empirical internal validity for document-level sentiment. Using three additional sentiment measures, we document the same inferences, concluding that document-level aggregation likely leads to lower internal validity. Sentiment is thus best applied at the level of specific contexts rather than across whole documents.

Keywords: Sentiment analysis, context, machine learning, aggregation, lasso regression, text analysis

JEL Classification: C18, C45, D83, G3, M40, M41

Suggested Citation

Crowley, Richard M. and Wong, M.H. Franco, Understanding Sentiment Through Context (December 30, 2022). Rotman School of Management Working Paper No. 4316229, Singapore Management University School of Accountancy Research Paper No. 2023-160, Available at SSRN: https://ssrn.com/abstract=4316229 or http://dx.doi.org/10.2139/ssrn.4316229

Richard M. Crowley (Contact Author)

Singapore Management University - School of Accountancy ( email )

60 Stamford Road
Singapore 178900
Singapore

HOME PAGE: http://rmc.link

M.H. Franco Wong

University of Toronto - Rotman School of Management ( email )

105 St. George Street
Toronto, Ontario M5S 3E6
Canada
416-946-0729 (Phone)

HOME PAGE: http://www.rotman.utoronto.ca/FacultyAndResearch/Faculty/FacultyBios/Wong.aspx

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

Paper statistics

Downloads
265
Abstract Views
1,103
Rank
229,468
PlumX Metrics