Template-type: ReDIF-Article 1.0
Author-Name: Ksenia Yakovleva
Author-Email: yakovlevakv@cbr.ru
Author-Workplace-Name: Bank of Russia
Title: Text Mining-based Economic Activity Estimation
Abstract: This paper outlines a methodology for constructing a high-frequency indicator of economic activity in Russia. News stories from internet resources are used as data sources. News data is analyzed using text mining and machine learning methods, which, although developed relatively recently, have quickly found wide application in scientific research, including economic studies. This is because news is not only a key source of information but a way to gauge the sentiment of journalists and survey respondents about the current situation and convert it into quantitative data.
Classification-JEL: C51, C81, E37
Keywords: economic activity estimates, nowcasting, text mining, machine learning, Big Data, data mining, topic modelling, sentiment analysis
Journal: Russian Journal of Money and Finance
Pages: 26-41
Volume: 77
Issue: 4
Year: 2018
Month: December
DOI: 10.31477/rjmf.201804.26
File-URL: https://rjmf.econs.online/upload/iblock/00a/RJMF_77-04_ENG_Yakovleva.pdf
Handle: RePEc:bkr:journl:v:77:y:2018:i:4:p:26-41