On the predictive ability of narrative disclosures in annual reports

We investigate whether narrative disclosures in 10-K and 10K-405 filings contain value-relevant information for predicting market performance. We apply text classification techniques from computer science to machine code text disclosures in a sample of 4280 filings by 1236 firms over five years. Our methodology develops a model using documents and actual performance for a training sample. This model, when applied to documents from a test set, leads to performance prediction. We find that a portfolio based on model predictions earns significantly positive size-adjusted returns, indicating that narrative disclosures contain value-relevant information. Supplementary analyses show that the text classification model captures information not contained in document-level features of clarity, tone and risk sentiment considered in prior research. However, we find that the narrative score is not providing information incremental to traditional predictors such as size, market-to-book and momentum, but rather affects investors' use of price momentum as a factor that predicts excess returns.

[1]  Mark H. Lang,et al.  Voluntary Disclosure and Equity Offerings: Reducing Information Asymmetry or Hyping the Stock?* , 1997 .

[2]  Fabrizio Sebastiani,et al.  Machine learning in automated text categorization , 2001, CSUR.

[3]  Yiming Yang,et al.  A re-examination of text categorization methods , 1999, SIGIR '99.

[4]  Heikki Mannila,et al.  Principles of Data Mining , 2001, Undergraduate Topics in Computer Science.

[5]  Marlene Plumlee,et al.  Disclosure Level and Expected Cost of Equity Capital: An Examination of Analysts' Rankings of Corporate Disclosure and Alternative Methods of Estimating Expected Cost of Equity Capital , 2000 .

[6]  Peter M. Clarkson,et al.  Evidence That Management Discussion and Analysis (MD&A) is a Part of a Firm's Overall Disclosure Package* , 1999 .

[7]  Ian Witten,et al.  Data Mining , 2000 .

[8]  John E. Core,et al.  A Review of the Empirical Disclosure Literature: Discussion , 2001 .

[9]  Gerard Salton,et al.  Term-Weighting Approaches in Automatic Text Retrieval , 1988, Inf. Process. Manag..

[10]  Susan T. Dumais,et al.  Inductive learning algorithms and representations for text categorization , 1998, CIKM '98.

[11]  Marc R. Reinganum Misspecification of capital asset pricing : Empirical anomalies based on earnings' yields and market values , 1981 .

[12]  Thomas Z. Lys,et al.  Empirical Research on Accounting Choice , 2001 .

[13]  Paul Thompson Automatic categorization of case law , 2001, ICAIL '01.

[14]  David M. Pennock,et al.  Mining the peanut gallery: opinion extraction and semantic classification of product reviews , 2003, WWW '03.

[15]  Jorge Calera-Rubio,et al.  A Text Categorization Approach for Music Style Recognition , 2005, IbPRIA.

[16]  Leah S. Larkey,et al.  Automatic essay grading using text categorization techniques , 1998, SIGIR '98.

[17]  Robert G. Insley,et al.  Performance and Readability: A Comparison of Annual Reports of Profitable and Unprofitable Corporations , 1993 .

[18]  E. Henry Market Reaction to Verbal Components of Earnings Press Releases: Event Study Using a Predictive Algorithm , 2006 .

[19]  Christine Botosan Disclosure level and the cost of equity capital , 1997 .

[20]  Shyam Sunder,et al.  Are Unmanaged Earnings Always Better for Shareholders , 2003 .

[21]  R. Ball,et al.  An empirical evaluation of accounting income numbers , 1968 .

[22]  Orie E. Barron,et al.  MD&A Quality as Measured by the SEC and Analysts' Earnings Forecasts* , 1999 .

[23]  Sholom M. Weiss,et al.  Automated learning of decision rules for text categorization , 1994, TOIS.

[24]  S. Kothari Capital Markets Research in Accounting , 2001 .

[25]  David M. Boje,et al.  The financial crisis and mark‐to‐market accounting: An analysis of cascading media rhetoric and storytelling , 2010 .

[26]  Krishna G. Palepu,et al.  Information Asymmetry, Corporate Disclosure and the Capital Markets: A Review of the Empirical Disclosure Literature , 2000 .

[27]  Martin Walker,et al.  Undertaking large-scale disclosure studies when AIMR-FAF ratings are not available: the case of prices leading earnings , 2003 .

[28]  Brad Barber,et al.  Reassessing the Returns to Analysts' Stock Recommendations , 2003 .

[29]  R. Taffler,et al.  The chairman’s statement ‐ A content analysis of discretionary narrative disclosures , 2000 .

[30]  A. Rashad Abdel-Khalik,et al.  Empirical research in accounting , 1979 .

[31]  Karine Zeitouni,et al.  Text Categorization for Multi-label Documents and Many Categories , 2007, Twentieth IEEE International Symposium on Computer-Based Medical Systems (CBMS'07).

[32]  Shyam Sunder,et al.  Earnings Management and the Revelation Principle , 1998 .

[33]  FletcherJonathan,et al.  “An Examination of Resampled Portfolio Efficiency”: Authors' Response , 2003 .

[34]  Narasimhan Jegadeesh,et al.  Analyzing the Analysts: When Do Recommendations Add Value? , 2002 .

[35]  Amit Singhal,et al.  Pivoted document length normalization , 1996, SIGIR 1996.

[36]  S. Brooks Marshall,et al.  Content Analysis of Information Cited in Reports of Sell-Side Financial Analysts , 1998 .

[37]  Padmini Srinivasan,et al.  Learning to crawl: Comparing classification schemes , 2005, TOIS.

[38]  Narasimhan Jegadeesh,et al.  Returns to Buying Winners and Selling Losers: Implications for Stock Market Efficiency , 1993 .

[39]  Rajkumar Roy,et al.  TEXT CLASSIFICATION METHOD REVIEW , 2007 .

[40]  Sofus A. Macskassy,et al.  More than Words: Quantifying Language to Measure Firms' Fundamentals the Authors Are Grateful for Assiduous Research Assistance from Jie Cao and Shuming Liu. We Appreciate Helpful Comments From , 2007 .

[41]  Jeremy Piger,et al.  Louis Working Paper Series Beyond the Numbers : An Analysis of Optimistic and Pessimistic Language in Earnings Press Releases , 2006 .

[42]  E. Fama,et al.  The Cross‐Section of Expected Stock Returns , 1992 .

[43]  Feng Li Annual Report Readability, Current Earnings, and Earnings Persistence , 2008 .

[44]  Albert H. Segars,et al.  The President's Letter to Stockholders: An Examination of Corporate Communication Strategy , 1992 .