ABSTRACT
This study aims to accurately predict stock indexes by combining sentiment analysis with machine learning. We apply web crawlers to collect text information from a representative Chinese stock forum, build a high-frequency investor sentiment index, and select a suitable mixed-data sampling model to make nowcasting predictions on the Shanghai Composite Index (SHA). We show that the investors’ sentiments significantly drive the SHA, and that the exchange rate is the most powerful indicator for short term SHA prediction. Additionally, no autoregressive effect exists on the SHA. These results will benefit investors and policymakers.
Acknowledgments
This work is supported by the Project of Youth in the National Social Science Foundation of China under Grant number 18CGL009; Natural Science Fund of Shandong under Grant number ZR2019QG005.
Disclosure statement
No potential conflict of interest was reported by the authors.
Notes
1. HOWNET is a knowledge resource and reveals the relationship between concepts and the attributes of concepts as its basic content. DLUTSD and NTUSD were developed separately by the Dalian University of Technology and Taiwan University. They are based on the rule-based algorithm, which primarily provides prior knowledge of sentiment polarity and degree.