Textual and Quantitative Analysis: Towards a New, e-Mediated Social Science
- Topics:
- Reporting and Control
- Tags:
- Finance,
- Financial,
- Financial Accounting,
- Manual Analysis,
- Metaphor,
- Quantitative Analysis,
- University Of Surrey
- Source:
- University of Surrey
FREE Registration is required
Overview: This paper describes a method for automatically extracting sentiment from texts: the frequency of use of positive and negative sentiment words that may reflect a community's sentiment. The method is applied to a corpus of financial news text to automatically extract frequent key terms and symbols; and automatically disambiguate key terms and symbols. Manual analysis suggests that spatial metaphors (fall/rise, up/down), speed metaphors (accelerate or decelerate) and biological metaphors (growth/decay) are prevalent in financial texts. The use of key words and metaphors in financial text appears to be governed by a set of rules that some authors refer to as a local grammar.
(Is this item miscategorized? Does it need more tags? Let us know.)
Format: PDF | Size: 77KB | Pages: 12





