Please use this identifier to cite or link to this item: http://scholarbank.nus.edu.sg/handle/10635/53709
Title: EXTENDING TOPIC MODELS FOR TEXT ANALYSIS OF CORPORATE RISK DISCLOSURES
Authors: BAO YANG
Keywords: topic models, text analysis, corporate risk disclosures, risk sentiment, risk types, econometric analysis
Issue Date: 30-Sep-2013
Source: BAO YANG (2013-09-30). EXTENDING TOPIC MODELS FOR TEXT ANALYSIS OF CORPORATE RISK DISCLOSURES. ScholarBank@NUS Repository.
Abstract: Companies are required to disclose risks that might impact its business in the risk disclosure section of the annual report, where the various risks types facing the company are described in free form text. In this thesis, we propose two extended topic models for identifying risk sentiment and extracting various risk types from textual risk disclosures. The proposed methods could facilitate the analysis of corporate risk disclosures by reducing the amount of human effort substantially. Moreover, the proposed methods enable the empirical study of market reactions to risk disclosures at the individual risk type level. The findings of our empirical study reconcile the conflicting arguments about the effects of risk disclosures on post-disclosure risk perceptions of investors in accounting literature.
URI: http://scholarbank.nus.edu.sg/handle/10635/53709
Appears in Collections:Ph.D Theses (Open)

Show full item record
Files in This Item:
File Description SizeFormatAccess SettingsVersion 
BaoY.pdf1.96 MBAdobe PDF

OPEN

NoneView/Download

Page view(s)

174
checked on Dec 11, 2017

Download(s)

42
checked on Dec 11, 2017

Google ScholarTM

Check


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.