4.2 Descriptive Statistics
4.2.1 Data Processing
Text data is considered to be unstructured data as it appears in no specified format, has
variable length, variable spelling, contains punctuation, and other non-alphanumeric
characters, and does not adhere to a predefined set of values (Francis and Flynn 2010).
In order to convert the text into structured data for further analysis, the files were
converted into simple text format and the text data was parsed to extract the words.
4.2.2 Converting Files to Simple Text
The comment letters appeared in .pdf or .docx format on the IASB’s and FASB’s
websites. These were downloaded and named according to an id for which
corresponding data for the sender was recorded. The files were then converted into
simple text format using PDF Converter Enterprise, a software that automatically
identifies files which contain graphics and transforms them using Optical Character