Our paper has been accepted for publication in the Transactions of the Japanese Society for Artificial Intelligence.
[Bibliographic information
Koichiro Tamura and Yutaka Matsuo: Modeling and Analysis of Actions on Financial Markets from Influence Relations in Social Media, Transactions of the Japanese Society for Artificial Intelligence, Vol. 35, No. 6 (2020)
Summary
We proposed a method for formulating the effects of social media on financial markets based on their influence relationships and modeling them using neural networks.
We extracted and analyzed the interactions that cannot be directly observed and that contribute to price fluctuations of actual financial assets, as well as users’ cognition and psychological states that change in a complex manner over time.