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

• Authors: J. Chołoniewski , J. Sienkiewicz , J. Hołyst , M. Thelwall
• Languages of publication: EN

Abstracts

EN

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.

Keywords

EN

02.50.-r; 07.05.Hd; 89.20.Hh

Discipline

• 07.05.Hd: Data acquisition: hardware and software
• 02.50.-r: Probability theory, stochastic processes, and statistics(see also section 05 Statistical physics, thermodynamics, and nonlinear dynamical systems)
• 89.20.Hh: World Wide Web, Internet

• Publisher: Institute of Physics, Polish Academy of Sciences
• Journal: Acta Physica Polonica A
• Year: 2015
• Volume: 127
• Issue: 3A
• Pages: A-21-A-28

Dates

published

2015-03

Contributors

author

J. Chołoniewski

• Physics in Economy and Social Sciences Research Group, Faculty of Physics, Warsaw University of Technology, Koszykowa 75, PL-00662 Warszawa, Poland

author

J. Sienkiewicz

• Physics in Economy and Social Sciences Research Group, Faculty of Physics, Warsaw University of Technology, Koszykowa 75, PL-00662 Warszawa, Poland

author

J. Hołyst

• Physics in Economy and Social Sciences Research Group, Faculty of Physics, Warsaw University of Technology, Koszykowa 75, PL-00662 Warszawa, Poland
• ITMO University, 19, Kronverkskiy av., 197101 Saint Petersburg, Russia

author

M. Thelwall

• Statistical Cybermetrics Research Group, School of Mathematics and Computer Science, University of Wolverhampton, Wulfruna Street, Wolverhampton WV1 1LY, United Kingdom

References

• [1] J. Kwapien, S. Drozdz, Phys. Rep. 515, 115 (2012), doi: 10.1016/j.physrep.2012.01.007
• [2] K. Malarz, K. Kulakowski, Acta Phys. Pol. A 117, 695 (2010)
• [3] P. Gawronski, K. Malarz, M.J. Krawczyk, J. Malinowski, A. Kupczak, W. Sikora, K. Kulakowski, J. Was, J.W. Kantelhardt, Acta Phys. Pol. A 123, 522 (2013), doi: 10.12693/APhysPolA.123.522
• [4] M. Wilinski, A. Sienkiewicz, T. Gubiec, R. Kutner, Z.R. Struzik, Physica A 392, 5963 (2013), doi: 10.1016/j.physa.2013.07.064
• [5] K. Urbanowicz, J.A. Hołyst, Physica A 344, 284 (2004), doi: 10.1016/j.physa.2004.06.133
• [6] A. Sienkiewicz, T. Gubiec, R. Kutner, Z.R. Struzik, Acta Phys. Pol. A 123, 615 (2013), doi: 10.12693/APhysPolA.123.615
• [7] P. Oswiecimka, S. Drozdz, J. Kwapien, A.Z. Gorski, Acta Phys. Pol. A 123, 597 (2013), doi: 10.12693/APhysPolA.123.597
• [8] C. Cattuto, A. Barrat, A. Baldassarri, G. Schehr, V. Loreto, PNAS 106, 10511 (2009), doi: 10.1073/pnas.0901136106
• [9] G. Bello, H. Menendez, S. Okazaki, D. Camacho, Computational Collective Intelligence: Technologies and Applications, Eds: C. Badica, N.T. Nguyen, M. Brezovan, Springer-Verlag, Berlin, Germany 2013, vol. 8083, p. 622
• [10] A. Chmiel, J. Sienkiewicz, M. Thelwall, G. Paltoglou, K. Buckley, A. Kappas, J.A. Hołyst, PLoS ONE 6, e22207 (2011), doi: 10.1371/journal.pone.0022207
• [11] P. Sobkowicz, M. Kaschesky, G. Bouchard, Government Information Quarterly 29, 470 (2012), doi: 10.1016/j.giq.2012.06.005
• [12] P. Sobkowicz, A. Sobkowicz, SSCR 30, 448 (2012), doi: 10.1177/0894439312436512
• [13] P. Pohorecki, J. Sienkiewicz, M. Mitrovic, G. Paltoglou, J.A. Hołyst, Acta Phys. Pol. A 123, 604 (2013), doi: 10.12693/APhysPolA.123.604
• [14] A. Chmiel, P. Sobkowicz, J. Sienkiewicz, G. Paltoglou, K. Buckley, M. Thelwall, J. A. Hołyst, Physica A 390, 2936 (2011), doi: 10.1016/j.physa.2011.03.040
• [15] U.M. Fayyad, N. Weir, S. Djorgovski, Proceedings of the Second International Conference on Information and Knowledge Management, ACM, New York, USA 1993, p. 527
• [16] D. Rousseau, IEEE Software 29, 11 (2012), doi: 10.1109/MS.2012.123
• [17] C.C. Fischer, K.J. Tibbetts, D. Morgan, G. Ceder, Nat. Mater. 5, 641 (2006), doi: 10.1038/nmat1691
• [18] S. Lebègue, T. Björkman, M. Klintenberg, R.M. Nieminen, O. Eriksson, Phys. Rev. X 3, 031002 (2013), doi: 10.1103/PhysRevX.3.031002
• [19] Y.L. Chen, K. Tang, R.J. Shen, Y.H. Hu, Decision Support Systems 40, 339 (2005), doi: 10.1016/j.dss.2004.04.009
• [20] E.W.T. Ngai, L. Xiu, D.C.K. Chau, Expert Systems with Applications 36, 2592 (2009), doi: 10.1016/j.eswa.2008.02.021
• [21] N. Lavrac, E.T. Keravnou, B. Zupan, Intelligent data analysis in medicine and pharmacology, Kluwer Academic Publishers, Norwell, MA, USA 1997, vol. 414, p. 1
• [22] C.L. Huang, M.C. Chen, C.J. Wang, Expert Systems with Applications 33, 847 (2007), doi: 10.1016/j.eswa.2006.07.007
• [23] F. Murtagh, M.J. Kurtz, arXiv: 1209.0125, 2012
• [24] J.J. Grefenstette, IEEE Transactions on Systems, Man and Cybernetics 16, 122 (1986), doi: 10.1109/TSMC.1986.289288
• [25] D.L. Verbyla, Canad. J. For. Res. 17, 1150 (1987), doi: 10.1139/x87-177
• [26] C. Cortes, V. Vapnik, Mach. Learn. 20, 273 (1995), doi: 10.1023/A:1022627411411
• [27] D. Horn, A. Gottlieb, Phys. Rev. Lett. 88, 018702 (2001), doi: 10.1103/PhysRevLett.88.018702
• [28] M. Opper, R. Urbanczik, Phys. Rev. Lett. 86, 4410 (2001), doi: 10.1103/PhysRevLett.86.4410
• [29] A. Decelle, Ph.D. Thesis, Université Paris-Sud, Paris, 2011
• [30] J. Bollen, H. Mao, X. Zeng, J. Comput. Sci. 2, 1 (2011), doi: 10.1016/j.jocs.2010.12.007
• [31] J.M. Miotto, E.G. Altmann, PLoS ONE 9, e111506 (2014), doi: 10.1371/journal.pone.0111506
• [32] M. Thelwall, K. Buckley, G. Paltoglou, J. Assoc. Inf. Sci. Technol. 63, 163 (2012), doi: 10.1002/asi.21662
• [33] Billauer's homepage,http://www.billauer.co.il/peakdet.html

Identifiers

DOI

10.12693/APhysPolA.127.A-21