Deep Learning for Social Media Analysis in Crises Situations (Position paper)

Mehdi Ben Lazreg
University of Agder, Grimstad, Norway

Morten Goodwin
University of Agder, Grimstad, Norway

Ole-Christoffer Granmo
University of Agder, Grimstad, Norway

Ladda ner artikel

Ingår i: The 29th Annual Workshop of the Swedish Artificial Intelligence Society (SAIS), 2–3 June 2016, Malmö, Sweden

Linköping Electronic Conference Proceedings 129:4, s. 6

Visa mer +

Publicerad: 2016-06-20

ISBN: 978-91-7685-720-5

ISSN: 1650-3686 (tryckt), 1650-3740 (online)


Social media has become an important open communication medium during crises. This has motivated much work on social media data analysis for crises situations using machine learning techniques but has mostly been carried out by traditional techniques. Those methods have shown mixed results and are criticised for being unable to generalize beyond the scope of the designed study. Since every crisis is special, such retrospect models have little value. In contrast, deep learning shows very promising results by learning in noisy environments such as image classification and game playing. It has, therefore great potential to play a significant role in the future social media analysis in noisy crises situations. This position paper proposes an approach to improve the social media analysis in crises situations to achieve better understanding and decision support during a crisis. In this approach, we aim to use Deep Learning to extract features and patterns related to the text and concepts available in crisis related social media posts and use them to provide an overview of the crisis.


artificial intelligence


[1] Maresh-Fuehrer, M.M. and R. Smith, Social media mapping innovations for crisis prevention, response, and evaluation. Computers in Human Behavior, 2016. 54: p. 620-629.

[2] Zielinski, A., et al. Social media text mining and network analysis for decision support in natural crisis management. in ISCRAM 2013 Conference Proceedings - 10th International Conference on Information Systems for Crisis Response and Management. 2013.

[3] Valkanas, G., et al. Mining Twitter Data with Resource Constraints. in Web Intelligence (WI) and Intelligent Agent Technologies (IAT), 2014 IEEE/WIC/ACM International Joint Conferences on. 2014.

[4] Imran, M., et al., Processing Social Media Messages in Mass Emergency: A Survey. CoRR, 2014. abs/1407.7071.

[5] Yin, J., et al., Using social media to enhance emergency situation awareness. IEEE Intelligent Systems, 2012. 27(6): p. 52-59.

[6] Power, R., et al., Emergency situation awareness: Twitter case studies, in Information Systems for Crisis Response and Management in Mediterranean Countries. 2014, Springer. p. 218-231.

[7] Imran, M., et al. Aidr: Arti cial intelligence for disaster response. in Proceedings of the companion publication of the 23rd international conference on World wide web companion. 2014. International World Wide Web Conferences Steering Committee.

[8] Ashktorab, Z., et al., Tweedr: Mining twitter to inform disaster response. Proc. of ISCRAM, 2014.

[9] Phuvipadawat, S. and T. Murata. Breaking news detection and tracking in Twitter in Web Intelligence and Intelligent Agent Technology (WI-IAT). IEEE/WIC/ACM International Conference on. 2010.

[10] Musaev, A., D. Wang, and C. Pu. LITMUS: Landslide detection by integrating multiple sources. in 11th International Conference Information Systems for Crisis Response and Management (ISCRAM). 2014.

[11] Rogstadius, J., et al., CrisisTracker: Crowdsourced social media curation for disaster awareness. IBM Journal of Research and Development, 2013. 57(5): p. 4: 1-4: 13.

[12] Berlingerio, M., et al. SaferCity: a system for detecting and analyzing incidents from social media. in Data Mining Workshops (ICDMW), 2013.

[13] Kireyev, K., L. Palen, and K. Anderson. Applications of topics models to analysis of disaster-related twitter data. in NIPSWorkshop on Applications for Topic Models: Text and Beyond. 2009. Canada: Whistler.

[14] LeCun, Y., Y. Bengio, and G. Hinton, Deep learning. Nature, 2015. 521(7553): p. 436-444.

[15] Deng, L., et al. Recent advances in deep learning for speech research at Microsoft. in Acoustics, Speech and Signal Processing (ICASSP), 2013.

[16] Anavi, Y., et al. A comparative study for chest radiograph image retrieval using binary texture and deep learning classification. 37th Annual International Conference of the IEEE in Engineering in Medicine and Biology Society (EMBC), 2015.

[17] Arel, I., D.C. Rose, and T.P. Karnowski, Deep Machine Learning - A New Frontier in Artificial Intelligence Research. IEEE Computational Intelligence Magazine, 2010. 5(4): p. 13-18.

[18] Silver, D., et al., Mastering the game of Go with deep neural networks and tree search. Nature, 2016. 529(7587): p. 484-489.

[19] Kalaimani, E., E. Kirubakaran, and P. Anbalagan, Classi cation and topic discovery of web documents using semantic deep learner based on semantic smoothing model. International Journal of Applied Engineering Research, 2015. 10(2): p. 2575-2598.

[20] Lu, Y., et al., CHEMDNER system with mixed conditional random elds and multi-scale word clustering. Journal of Cheminformatics, 2015. 7.

[21] Wang, Y., et al., Word vector modeling for sentiment analysis of product reviews, in Communications in Computer and Information Science. 2014. p. 168-180.

[22] Hailong, Z., G. Wenyan, and J. Bo. Machine learning and lexicon based methods for sentiment classi cation: A survey. in Proceedings - 11th Web Information System and Application Conference, WISA. 2014.

[23] Acharyya, S., et al., Language independent unsupervised learning of short message service dialect. International Journal on Document Analysis and Recognition (IJDAR), 2009. 12(3): p. 175-184.

[24] Aggarwal, C.C. and H. Wang, Text Mining in Social Networks, in Social Network Data Analytics, C.C. Aggarwal, Editor. 2011, Springer US: Boston, MA. p. 353-378.

[25] Najafabadi, M.M., et al., Deep learning applications and challenges in big data analytics. Journal of Big Data, 2015. 2(1): p. 1-21.

[26] Dumais, S.T., Latent semantic analysis. Annual review of information science and technology, 2004. 38(1): p. 188-230.

[27] Blei, D.M., A.Y. Ng, and M.I. Jordan, Latent dirichlet allocation. the Journal of machine Learning research, 2003. 3: p. 993-1022.

[28] Zhou, G., K. Sohn, and H. Lee, Online incremental feature learning with denoising autoencoders. in International Conference on Artificial Intelligence and Statistics, 2012

Citeringar i Crossref