Corporate Financial Information Environment (CFIE) Project
Mahmoud El-Haj
SCC, Lancaster University
In this talk I present the evaluation of our automatic methods for detecting and extracting document structure in annual financial reports. The work presented is part of the Corporate Financial Information Environment (CFIE) project in which we are using Natural Language Processing (NLP) techniques to study the causes and consequences of corporate disclosure and financial reporting outcomes. We aim to uncover the determinants of financial reporting quality and the factors that influence the quality of information disclosed to investors beyond the financial statements. The CFIE consists of the supply of information by firms to investors, and the mediating influences of information intermediaries on the timing, relevance and reliability of information available to investors.
We aim to scale up the application of current readability metrics and improve their granularity. In the research beyond that presented here, we have employed a suite of statistical and rule-based NLP tools for analysing firms' narrative communication practices. To improve on previous work, we need to apply the metrics to individual sections of firms' annual reports. Therefore, a necessary prerequisite for our work is to automatically determine the structure of these reports.
The data used in our experiments consisted of 1,500 financial annual reports of around 200 of the largest UK firms listed on the London Stock Exchange, with an average of seven annual reports for each firm between the years 2003 and 2012.
http://ucrel.lancs.ac.uk/cfie/