R. Heiberger. Computational Social Networks, volume 9197 of Lecture Notes in Computer Science, Springer International Publishing, New York, (August 2015)
DOI: 10.1007/978-3-319-21786-4_26
Abstract
In this paper, we combine network analytical methods to understand the structure of financial markets with recent research about collective attention shifts by utilizing massive social media data. Our main goal, hence, is to investigate whether changes in stock networks are connected with collective attention shifts. To examine the relationship between structural market properties and mass online behavior empirically, we merge company-level Google Trends data with stock network dynamics for all S&P 100 corporations between 2004 and 2014. The interplay of massive online behavior and market activities reveals that collective attention shifts precede structural changes in stock market networks and that this connection is mostly carried by companies that already dominate the development of the S&P 100.
Full Text PDF:C\:\\Users\\ac135138\\Zotero\\storage\\F3HXBF4H\\Heiberger - 2015 - Shifts in Collective Attention and Stock Networks.pdf:application/pdf;Snapshot:C\:\\Users\\ac135138\\Zotero\\storage\\T54FADGN\\10.html:text/html
%0 Book Section
%1 heiberger_shifts_2015
%A Heiberger, Raphael H.
%B Computational Social Networks
%C New York
%D 2015
%E Thai, My T.
%E Nguyen, Nam P.
%E Shen, Huawei
%I Springer International Publishing
%K (incl. Applications Artificial Collective Communication Computational Computer Data Database Discovery, Econophysics, Information Intelligence Internet), Knowledge Management, Mining Networks, Retrieval, Robotics), Stock Storage Systems Theory, and attention, crisis, financial networks science,
%P 296--306
%R 10.1007/978-3-319-21786-4_26
%T Shifts in Collective Attention and Stock Networks
%U http://link.springer.com/chapter/10.1007/978-3-319-21786-4_26
%V 9197
%X In this paper, we combine network analytical methods to understand the structure of financial markets with recent research about collective attention shifts by utilizing massive social media data. Our main goal, hence, is to investigate whether changes in stock networks are connected with collective attention shifts. To examine the relationship between structural market properties and mass online behavior empirically, we merge company-level Google Trends data with stock network dynamics for all S&P 100 corporations between 2004 and 2014. The interplay of massive online behavior and market activities reveals that collective attention shifts precede structural changes in stock market networks and that this connection is mostly carried by companies that already dominate the development of the S&P 100.
%@ 978-3-319-21785-7 978-3-319-21786-4