Title :
Text Mining of Business News for Forecasting
Author :
Kroha, Petr ; Baeza-Yates, Ricardo ; Krellner, Björn
Author_Institution :
Fac. of Comput. Sci., Technol. Univ., Chemnitz
Abstract :
In this paper, we analyze the relation between the content of business news and long-term market trends. We describe cleansing and classification of business news, we investigate how much similarity good news and bad news have, and how their ratio behaves in context of long-terms market trends. We have processed more than 400 thousand business news coming from the years 1999 to 2005. We present results of our experiments and their possible impact on forecasting of long-term market trends
Keywords :
business data processing; classification; data mining; demand forecasting; market research; text analysis; business news classification; business news content; business news forecasting; market trend forecasting; text mining; Business; Chemical technology; Computer science; Consumer electronics; Data mining; Databases; Economic forecasting; Engines; Humans; Text mining;
Conference_Titel :
Database and Expert Systems Applications, 2006. DEXA '06. 17th International Workshop on
Conference_Location :
Krakow
Print_ISBN :
0-7695-2641-1
DOI :
10.1109/DEXA.2006.135
