Word Power: A New Approach for Content Analysis
Emory University - Department of Finance
Andrew Di Wu
University of Pennsylvania - The Wharton School
October 1, 2012
AFA 2012 Chicago Meetings Paper
We present a new approach for content analysis to quantify document tone. We find a significant relation between our measure of the tone of 10-Ks and market reaction for both negative and positive words. Previous research has not been successful in quantifying tone using positive words. We also find that the appropriate choice of term weighting in content analysis is at least as important as, and perhaps more important than, a complete and accurate compilation of the word list. Furthermore, we show that our approach circumvents the need to subjectively partition words into positive and negative word lists. We also find that the market underreacts to the tone of 10-Ks, and this underreaction is corrected over the next two weeks.
Number of Pages in PDF File: 42
Keywords: Content analysis, 10-Ks, Filing date, term-weighting
JEL Classification: G10, G14working papers series
Date posted: March 18, 2011 ; Last revised: November 1, 2012
© 2013 Social Science Electronic Publishing, Inc. All Rights Reserved.
This page was processed by apollo7 in 0.438 seconds