Predicting the Occurrence of World News Events Using Recurrent Neural Networks and Auto-Regressive Moving Average Models

  • Emmanuel M. Smith
  • Jim Smith
  • Phil Legg
  • Simon Francis
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 650)

Abstract

The ability to predict future states is fundamental for a wide variety of applications, from weather forecasting to stock market analysis. Understanding the related data attributes that can influence changes in time series is a challenging task that is critical for making accurate predictions. One particular application of key interest is understanding the factors that relate to the occurrence of global activities from online world news reports. Being able to understand why particular types of events may occur, such as violence and peace, could play a vital role in better protecting and understanding our global society. In this work, we explore the concept of predicting the occurrence of world news events, making use of Global Database of Events, Language and Tone online news aggregation source. We compare traditional Auto-Regressive Moving Average models with more recent deep learning strategies using Long Short-Term Memory Recurrent Neural Networks. Our results show that the latter are capable of achieving lower error rates. We also discuss how deep learning methods such as Recurrent Neural Networks have the potential for greater capability to incorporate complex associations of data attributes that may impact the occurrence of future events.

References

  1. 1.
    Brandt, P.T., Freeman, J.R., Schrodt, P.A.: Real time, time series forecasting of inter- and intra-state political conflict. Conflict Manag. Peace Sci. 28(1), 41–64 (2011). doi:10.1177/0738894210388125 CrossRefGoogle Scholar
  2. 2.
    Busseti, E., Osband, I., Wong, S.: Deep learning for time series modeling. Technical report, Stanford (2012)Google Scholar
  3. 3.
    Cadena, J., Korkmaz, G., Kuhlman, C.J., Marathe, A., Ramakrishnan, N., Vullikanti, A.: Forecasting social unrest using activity cascades. PLOS ONE 10(6) (2015). doi:10.1371/journal.pone.0128879
  4. 4.
    Esteban, C., Staeck, O., Yang, Y., Tresp, V.: Predicting clinical events by combining static and dynamic information using recurrent neural networks (2016). http://arxiv.org/abs/1602.02685
  5. 5.
    Gerner, D.J., Abu-jabr, R., Schrodt, P.A., Yilmaz, M.: Conflict and Mediation Event Observations (CAMEO): A New Event Data Framework for the Analysis of Foreign Policy Interactions. International Studies Association, New Orleans (2002). http://www.ku.edu/~keds
  6. 6.
    Goldstein, J.S.: A conflict-cooperation scale for WEIS events data. J. Conflict Resolut. 36(2), 369–385 (1992). doi:10.1177/0022002792036002007
  7. 7.
    Greff, K., Kumar, R., Koutník, J., Steunebrink, B.R., Schmidhuber, U.: LSTM: a search space odyssey (2015). https://arxiv.org/pdf/1503.04069.pdf
  8. 8.
    Hammond, J., Weidmann, N.B.: Using machine-coded event data for the micro-level study of political violence. Res. Polit. 1(2), 1–8 (2014). doi:10.1177/2053168014539924 Google Scholar
  9. 9.
    Hochreiter, S., Bengio, Y., Frasconi, P., Urgen Schmidhuber, J.: Gradient flow in recurrent nets: the difficulty of learning long-term dependencies (2001)Google Scholar
  10. 10.
    Hyndman, R.J., Athanasopoulos, G.: Forecasting: Principles and Practice, online edn. OTexts (2013)Google Scholar
  11. 11.
    Karpathy, A.: The unreasonable effectiveness of recurrent neural networks (2015). http://karpathy.github.io/2015/05/21/rnn-effectiveness/
  12. 12.
    Karpathy, A., Johnson, J., Fei-Fei, L.: Visualizing and understanding recurrent networks (2015). http://arxiv.org/abs/1506.02078
  13. 13.
    Lipton, Z.C., Kale, D.C., Elkan, C., Wetzell, R.: Learning to diagnose with LSTM recurrent neural networks. In: International Conference on Learning Representations, vol. 4 (2015). http://arxiv.org/abs/1511.03677
  14. 14.
    Perry, C.: Machine learning and conflict prediction: a use case. Stability: Int. J. Secur. Dev. 1–18 (2013). http://dx.doi.org/10.5334/sta.cr
  15. 15.
    Phua, C., Feng, Y., Ji, J., Soh, T.: Visual and predictive analytics on Singapore news: experiments on GDELT, Wikipedia, and \(^{\wedge }{\rm STI}\) (2014). http://arxiv.org/abs/1404.1996, http://www.sas.com/singapore
  16. 16.
    Qiao, F., Li, P., Zhang, X., Ding, Z., Cheng, J., Wang, H.: Predicting social unrest events with hidden Markov models using GDELT (2013)Google Scholar
  17. 17.
    Raleigh, C., Hegre, H.: Introducing ACLED: an armed conflict location and event dataset. In: Disaggregating the Study of Civil War and Transnational Violence (2005)Google Scholar
  18. 18.
    Stoll, R.J., Subramanian, D.: Hubs, Authorities, and Networks: Predicting Conflict Using Events Data. International Studies Association (2006)Google Scholar
  19. 19.
    Weidmann, N.B., Ward, M.D.: Predicting conflict in space and time. J. Conflict Resolut. 54(6), 883–901 (2010). doi:10.1177/0022002710371669 CrossRefGoogle Scholar
  20. 20.
    Yonamine, J.E.: A nuanced study of political conflict using the global datasets of events location and tone (GDELT) dataset. Ph.D. thesis, The Pennsylvania State University (2013)Google Scholar
  21. 21.
    Yonamine, J.E.: Predicting future levels of violence in afghanistan districts (2013). http://jayyonamine.com/wp-content/uploads/2013/03/Forecasting_Afghanistan.pdf
  22. 22.
    Yuan, Y.: Modeling inter-country connection from geotagged news reports: a time-series analysis (2016). http://arxiv.org/abs/1604.03647

Copyright information

© Springer International Publishing AG 2018

Authors and Affiliations

  • Emmanuel M. Smith
    • 1
  • Jim Smith
    • 1
  • Phil Legg
    • 1
  • Simon Francis
    • 2
  1. 1.University of the West of EnglandBristolUK
  2. 2.Montvieux LimitedGloucestershireUK

Personalised recommendations