Numeral is the crucial part of financial documents. In order to understand the detail of opinions in financial documents, we should not only analyze the text, but also need to assay the numeric information in depth. Because of the informal writing style, analyzing social media data is more challenging than analyzing news and official documents. FinNum is a task for fine-grained numeral understanding in financial social media data - to identify the category of a numeral.
When analyzing a financial instrument, investors always focus on two sides, fundamental and technical. Investors using fundamental analysis attempt to evaluate the intrinsic value of the financial instrument. For the security of company, they may focus on the numerals in financial statements. For the treasury bond, they may evaluate the price depending on US Fed Funds Target Rate. Those who use technical analysis may employ the technical indicator like moving average (MA), relative strength index (RSI), and so on. No matter which analysis method investors use, numeral plays an important role, and provides much pivotal information in financial data.
Numeral contains much important information in financial domain. For example, investors may use price-earnings ratio (P/E ratio) to evaluate the value of security of certain company, where both P/E ratio and the value of security are numeral information. For the purpose of understanding the fine-grained numeral information in social media data, we provide the taxonomy for numerals, and classify numerals into 7 categories and further extend several categories into some subcategories. Especially, the most important category, Monetary, is extended into 8 subcategories. (T1) is an instance that contains several numerals in a tweet, and the category of each numeral are dissimilar. 8 is the numeral about quantity, 17.99 is about stop loss price, 200 is the indicator of technical indicator, and 1 is the price of stock. In such a short sentence, there are 4 kinds of numerals. That shows the importance of numerals in financial narrative.
(T1) 8 breakouts: $CHMT (stop: $17.99), $FLO (200-day MA), $OMX (gap), $SIRO (gap). One sub-$1 stock. Modest selection on attempted swing low.