tailieunhanh - Twitter mood predicts the stock market

Apart from complete order-book data, the simulator makes a variety of agent- specific and market-wide information available to aid in order placement. In addition to real-time operation (live mode), the simulator supports historical simulations that use archived stock-market data from the requested day. Historical mode operates on a compressed time scale, allowing the simulation of an entire trading day in minutes. As a result, the agent is able to place considerably fewer orders overall than in live mode. Aside from the lower order-placement frequency, historical mode is operationally iden- tical to live mode. In December 2003 and April 2004, live PLAT stock-trading competitions were held including agents from several. | Journal ofComputational Science 2 2011 1-8 Contents lists available at ScienceDirect Journal of Computational Science journal homepage locate jocs Twitter mood predicts the stock market Johan Bollena 1 Huina Maoa 1 Xiaojun Zengb a School of Informatics and Computing Indiana University 919 E. 10th Street Bloomington IN 47408 United States b School of Computer Science University of Manchester Kilburn Building Oxford Road Manchester M13 9PL United Kingdom ARTICLE INFO ABSTRACT Article history Received 15 October 2010 Received in revised form 2 December 2010 Accepted 5 December 2010 Available online 2 February 2011 Keywords Social networks Sentiment tracking Stock market Collective mood Behavioral economics tells us that emotions can profoundly affect individual behavior and decisionmaking. Does this also apply to societies at large . can societies experience mood states that affect their collective decision making By extension is the public mood correlated or even predictive of economic indicators Here we investigate whether measurements of collective mood states derived from large-scale Twitter feeds are correlated to the value of the Dow Jones Industrial Average DJIA over time. We analyze the text content of daily Twitter feeds by two mood tracking tools namely OpinionFinder that measures positive vs. negative mood and Google-Profile of Mood States GPOMS that measures mood in terms of 6 dimensions Calm Alert Sure Vital Kind and Happy . We cross-validate the resulting mood time series by comparing their ability to detect the public s response to the presidential election and Thanksgiving day in 2008. A Granger causality analysis and a Self-Organizing Fuzzy Neural Network are then used to investigate the hypothesis that public mood states as measured by the OpinionFinder and GPOMS mood time series are predictive of changes in DJIA closing values. Our results indicate that the accuracy of DJIA predictions can be significantly improved by the .