2017/07/18 by Andrés García-Medina, Leonidas Sandoval, Leonidas Sandoval Junior +3 · 1 voice
Economics, Econometrics and Finance · Physics and Astronomy · #Complex Network Analysis Techniques #Complex Systems and Time Series Analysis #Opinion Dynamics and Social Influence #physics.soc-ph #q-fin.ST
paper · pdf · doi:10.1016/j.physa.2018.02.154
18 pages, 14 figures
arxiv created 2017/07/18 · arxiv published 2017/07/18 · openalex created_date 2017/07/31 · openalex publication_date 2018/03/01 · arxiv updated 2018/04/04 · openalex updated_date 2026/07/28
We use Random Matrix Theory (RMT) and information theory to analyze the correlations and flow of information between 64,939 news from The New York Times and 40 world financial indices during 10 months along the period 2015-2016. The set of news was quantified and transformed into daily polarity time series using tools from sentiment analysis. Results from RMT shows that a common factor lead the world indices and news, and even share the same dynamics. Furthermore, the global correlation structure has found preserved when adding white noise, which indicate that correlations are not due to sample size effects. Likewise, we found a lot of information flowing from news to world indices for specific delay, being of practical interest for trading purpose. Our results suggest a deep relationship between news and world indices, and show a situation where news drive world market movements, giving a new evidence to support behavioral finance as the current economic paradigm.