Abstract
With the rapid development of internet, text data is becoming richer, but most part of them is unstructured. So compared to statistics data, the text data is more difficult to be utilized. How to apply the informetrics on financial network text mining is a supplement to the traditional research methods of finance. The paper tries to forecast exchange rate volatility through informetrics on financial network text mining by means of affective computing. We find that if the amount of informetrics on network is used during predicting, only the peak and valley values of its volatility and are synchronous with the volatility of exchange rate. While the volatility of emotional intensity of words of informetrics on network in text data can accurately predict not only the drastic volatility of exchange rate, but also the moderate volatility. Introduction Recently, many currencies have seen a significant devaluation against the U.S. dollar, which has caused many investors and policymakers to worry. Therefore, how to accurately predict the future trend of the exchange rate has become the main task of current researchers. There are many traditional methods to predict the future trend of financial variables, such as probability method, signal method, Markov switching approach, network method, etc. But these methods are helpless facing online text data. So this paper tries to explore whether the exchange rate can be accurately predicting through informetrics on financial network text mining.
Conclusion
Through informetrics on financial network mining by means of affective computing, which is realized through the SparkR platform, in which the distributed computing technology is introduced, the paper tests whether text data can be used to forecast the volatility of exchange rate between RMB and U.S. dollar. It finds that:
(1) In most cases the volatility of the amount of informetrics on network are not always consistent and sometime opposite. While the peak values of the volatility of the amount of information of the exchange rate volatility is synchronous, so are the valley values.
(2) The volatility of the amount of emotional informetrics on network is more closer to the volatility of exchange rate, but there are also some daily volatility of exchange rate that are not so close to the amount of emotional information of the text data.
