The Role of Emotional Variables in the Classification and Prediction of Collective Social Dynamics

J. Chołoniewskia, J. Sienkiewicza, J. Hołysta,b and M. Thelwallc aPhysics in Economy and Social Sciences Research Group, Faculty of Physics, Warsaw University of Technology, Koszykowa 75, PL-00662 Warszawa, Poland bITMO University, 19, Kronverkskiy av., 197101 Saint Petersburg, Russia cStatistical Cybermetrics Research Group, School of Mathematics and Computer Science, University of Wolverhampton, Wulfruna Street, Wolverhampton WV1 1LY, United Kingdom

Full Text PDF

We demonstrate the power of data mining techniques for the analysis of collective social dynamics within British Tweets during the Olympic Games 2012. The classification accuracy of online activities related to the successes of British athletes significantly improved when emotional components of tweets were taken into account, but employing emotional variables for activity prediction decreased the classifiers' quality. The approach could be easily adopted for any prediction or classification study with a set of problem-specific variables.

DOI: 10.12693/APhysPolA.127.A-21 PACS numbers: 02.50.-r, 07.05.Hd, 89.20.Hh