Measuring information flux between social media and stock prices with Transfer Entropy.

ABSTRACT: Transfer Entropy was applied to analyze the correlations and flow of information between 200,500 tweets and 23 of the largest capitalized companies during 6 years along the period 2013-2018. The set of tweets were obtained applying a text mining algorithm and classified according to daily date and company mentioned. We proposed the construction of a Sentiment Index applying a Natural Processing Language algorithm and structuring the sentiment polarity for each data set. Bootstrapped Simulations of Transfer Entropy were performed between stock prices and Sentiment Indexes. The results of the Transfer Entropy simulations show a clear information flux between general public opinion and companies' stock prices. There is a considerable amount of information flowing from general opinion to stock

SUBMITTER: Mendoza Urdiales RA 

PROVIDER: S-EPMC8459996 | biostudies-literature | 2021

REPOSITORIES: biostudies-literature