A large fraction of financial markets data takes the form of unstructured, qualitative information (i.e., text). Analysis of text is therefore emerging as a research priority in accounting and finance. However, current approaches in the literature are often simplistic (e.g., keyword lists) and inconsistent with practice procedures in computational linguistics (e.g., training and validation).
This workshop aims to provide a rigorous and applied introduction to core methods used in natural language processing (NLP) and corpus linguistics. The workshop is supported by the Economic and Social Research Council, Lancaster University Management School, and UCREL.