The modern world of finances changes rapidly. In most cases the amount of information related to financial situations of different companies is too large for human brain to process it all in a reasonable frame of time. This is especially relevant when dealing with non-numerical information, such as quarter reports or press releases, involving some certain nuances in the reports language style. “Is it so important”, you may ask. But it seems that it is.
This is the main motive fueling a new trend of research in the field of computer algorithms: automated processing and analysis of textual information. And, obviously, the results of this research are being adapted where they yield the most valuable and short-term outcome, i.e. world of finances:
“Financial statements carry important information about the health of reporting companies,” says Chao-Lin Liu at National Chengchi University in Taipei, Taiwan. But companies habitually downplay negative aspects by using ambiguous language and burying nuggets of information in pages of droning prose.
Text-mining techniques generally concentrate on single words: counting the number of negative or positive words in a body of text can give an indication of the overall tone, for example. But it is impossible to say whether certain words taken in isolation – such as “increased” – are positive or negative, says team member Yuan-Chen Chang. So the team designed an algorithm to recognise meaningful phrases instead (arxiv.org/abs/1210.3865).
To do this, Liu and his colleagues use statistical models to automatically identify what they call opinion patterns – subjective phrases paired with an opinion holder. For example, the sentence “The Company believes the profits could be adversely affected” contains the opinion holder “The Company” and the subjective phrases “believes” and “could be adversely affected”.
“Computer linguistics and automated textual-information processing are one of the new frontiers in the world of finance,” says Werner Antweiler of the Sauder School of Business at the University of British Columbia in Vancouver, Canada.
Read more at: Newscientist.com