Abstract
In recent years, many citizens use social media platforms like Twitter to share and get the most up-to-date information regarding crisis events such as natural and man-made crisis. Automatically identifying this crisis-related information from social media data is a challenging task because of the sheer amount of data is being communicated between users during such crisis situations. The general public, response groups, and relief agencies can increase situational awareness by identifying and assessing crisis-related information from these massive amounts of social media data in real-time. Many studies have been published, that employ traditional machine learning approaches to detect crisis events, as well as others that use a deep neural network. In recent years, the models based on the deep neural network have outperformed traditional machine learning models for a variety of tasks. Two popularly used deep neural network models are Convolutional Neural Network (CNN) and the Gated Recurrent Unit (GRU). The local features can be detected by CNN in a multidimensional field, while the GRU network can learn sequential data because it can remember previously read data. In this paper, we propose two novel hybrid deep neural network models. The first model combines CNN and GRU and the second one combines CNN with SkipCNN. We evaluate our proposed models on 4 different datasets provided by CrisisNLP to show their effectiveness in detecting crisis-related information as well as identifying different types of information required for humanitarian aid. We find that from our proposed models CNN-SkipCNN is the best performing model and achieving better results than the state-of-the-art methods with an improvement of up to 16.55 absolute points for detecting crisis-related events and with an improvement of up to 21.71 absolute points in detecting different types of crisis information.
Similar content being viewed by others
References
Aivazoglou M, Roussos AO, Margaris D, Vassilakis C, Ioannidis S, Polakis J, Spiliotopoulos D (2020) A fine-grained social network recommender system. Soc Netw Anal Min 10(1):8
Alam F, Joty S, Imran M (2018) Graph based semi-supervised learning with convolution neural networks to classify crisis related tweets. arXiv:1805.06289
Andrews S, Gibson H, Domdouzis K, et al. (2016) Creating corroborated crisis reports from social media data through formal concept analysis. J Intell Inf Syst 47:287–312. https://doi.org/10.1007/s10844-016-0404-9
Bengio Y, Ducharme R, Vincent P, Jauvin C (2003) A neural probabilistic language model. J Mach Learn Res 3:1137–1155
Bhoi A, Pujari SP, Balabantaray RC (2020) A deep learning-based social media text analysis framework for disaster resource management. Soc Netw Anal Min 10(1):1–14
Burel G, Alani H (2018) Crisis event extraction service (crees)-automatic detection and classification of crisis-related content on social media
Burel G, Saif H, Alani H (2017) Semantic wide and deep learning for detecting crisis-information categories on social media. In: International semantic web conference. Springer, Cham, pp 138–155
Burel G, Saif H, Fernandez M, Alani H (2017) On semantics and deep learning for event detection in crisis situations
Caragea C, Silvescu A, Tapia AH (2016) Identifying informative messages in disaster events using convolutional neural networks. In: International conference on information systems for crisis response and management, pp 137–147
Cheng W, Sun Y, Li G, Jiang G, Liu H (2019) Jointly network: a network based on CNN and RBM for gesture recognition. Neural Comput and Applic 31(1):309–323
Chung J, Gulcehre C, Cho K, Bengio Y (2014) Empirical evaluation of gated recurrent neural networks on sequence modeling. In: Deep learning and representation learning workshop at the 28th conference on neural information processing systems. Curran Associates, New York
Demšar J (2006) Statistical comparisons of classifiers over multiple data sets. J Mach Learn Res 7(12/1/2006):1–30
Derrac J, García S, Molina D, Herrera F (2011) A practical tutorial on the use of nonparametric statistical tests as a methodology for comparing evolutionary and swarm intelligence algorithms. Swarm Evol Comput 1(1):3–18. ISSN 2210-6502, https://doi.org/10.1016/j.swevo.2011.02.002
Dhiman A, Toshniwal D (2020) An approximate model for event detection from Twitter data. In: IEEE Access, vol 8, pp 122168–122184. https://doi.org/10.1109/ACCESS.2020.3007004
Friedman M (1937) The use of ranks to avoid the assumption of normality implicit in the analysis of variance. J Am Stat Assoc 32:675–701
Friedman M (1940) A comparison of alternative tests of significance for the problem of m rankings. Ann Math Stat 11:86–92
Gao H, Barbier G, Goolsby R (2011) Harnessing the crowdsourcing power of social media for disaster relief. IEEE Intell Syst 26(3):10–14
Imran M, Elbassuoni S, Castillo C, Diaz F, Meier P (2013) Extracting information nuggets from disaster-related messages in social media. In: Iscram
Imran M, Elbassuoni S, Castillo C, Diaz F, Meier P (2013) Practical extraction of disaster-relevant information from social media. In: Proceedings of the 22nd international conference on World Wide Web, pp 1021–1024
Imran M, Mitra P, Castillo C (2016) Twitter as a lifeline: Human-annotated twitter corpora for NLP of crisis-related messages. In: Proceedings of the Tenth international conference on language resources and evaluation (LREC)
Imran M, Mitra P, Castillo C (2016) Twitter as a lifeline: human-annotated twitter corpora for NLP of crisis-related messages. arXiv:1605.05894
Interdonato R, Guillaume JL, Doucet A (2019) Lightweight and multilingual framework for crisis information extraction from Twitter data. Soc Netw Anal Min 9:65. https://doi.org/10.1007/s13278-019-0608-4
Karimi S, Yin J, Paris C (2013) Classifying microblogs for disasters. In: Proceedings of the 18th Australasian document computing symposium, pp 26–33
Kaufhold M-A, Bayer M, Reuter C (2020) Rapid relevance classification of social media posts in disasters and emergencies: a system and evaluation featuring active, incremental and online learning. Information Processing and Management, 57, http://www.sciencedirect.com/science/article/pii/S0306457319303152
Kejriwal M, Zhou P (2020) On detecting urgency in short crisis messages using minimal supervision and transfer learning. Soc Netw Anal Min 10:58. https://doi.org/10.1007/s13278-020-00670-7
Kersten J, Kruspe A, Wiegmann M, Klan F (2019) Robust filtering of crisis-related tweets. In: ISCRAM 2019 Conference proceedings-16th international conference on information systems for crisis response and management
Khare P, Fernandez M, Alani H (2017) Statistical semantic classification of crisis information
Kim Y (2014) Convolutional neural networks for sentence classification. arXiv:1408.5882
Kingma DP, Ba J (2015) Adam: a method for stochastic optimization. In: Proceedings of the 3rd international conference for learning representations
Kumar A, Garg G (2019) Sentiment analysis of multimodal twitter data. Multimed Tools Appl 78:24103–24119. https://doi.org/10.1007/s11042-019-7390-1
Kumar A, Sangwan SR, Nayyar A (2019) Rumour veracity detection on twitter using particle swarm optimized shallow classifiers. Multimed Tools Appl 78:24083–24101. https://doi.org/10.1007/s11042-019-7398-6
Lee H, Ahn Y, Lee H, Ha S, Lee S-g (2016) Quote recommendation in dialogue using deep neural network. In: Proceedings of the SIGIR, pp 957–960. https://doi.org/10.1145/2911451.2914734
Li H, Caragea D, Caragea C, Herndon N (2018) Disaster response aided by tweet classification with a domain adaptation approach. J Contingencies Crisis Manag 26(1):16–27
Madichetty S, Sridevi M (2019) Disaster damage assessment from the tweets using the combination of statistical features and informative words. Soc Netw Anal Min 9:42. https://doi.org/10.1007/s13278-019-0579-5
Mendon S, Dutta P, Behl A et al (2021) A hybrid approach of machine learning and lexicons to sentiment analysis. Enhanced Insights from Twitter Data of Natural Disasters, Inf Syst Front. https://doi.org/10.1007/s10796-021-10107-x
Nguyen DT, Al Mannai KA, Joty S, Sajjad H, Imran M, Mitra P (2016) Rapid classification of crisis-related data on social networks using convolutional neural networks. arXiv:1608.03902
Olteanu A, Vieweg S, Castillo C (2015) What to expect when the unexpected happens: social media communications across crises. In: Proceedings of the 18th ACM conference on computer supported cooperative work & social computing, pp 994–1009. ACM
Pennington J, Socher R, Manning CD (2014) Glove: Global vectors for word representation. In: Empirical methods in natural language processing (EMNLP), pp 1532–1543
Power R, Robinson B, Colton J, Cameron M (2014) Emergency situation awareness Twitter case studies. Int. Conf. on Info. Systems for Crisis Response and Management in Mediterranean Countries (ISCRAM). Toulouse
Qu Y, Huang C, Zhang P, Zhang J (2011) Microblogging after a major disaster in China: a case study of the 2010 Yushu earthquake. In: Proceedings of the ACM 2011 conference on computer supported cooperative work, pp 25–34. ACM
Resch B, Usländer F, Havas C (2018) Combining machine-learning topic models and spatiotemporal analysis of social media data for disaster footprint and damage assessment. Cartogr Geogr Inf Sci 45(4):362–376
Şahin C, Rokne J, Alhajj R (2019) Emergency detection and evacuation planning using social media. In: Social networks and surveillance for society. Springer, Cham, pp 149–164
Sailunaz K, Alhajj R (2019) Emotion and sentiment analysis from Twitter text. Journal of Computational Science, 36
Sakaki T, Okazaki M, Matsuo Y (2010) Earthquake shakes Twitter users: real-time event detection by social sensors. In: Proceedings of the 19th international conference on World wide web, pp 851–860
Schempp T, Zhang H, Schmidt A, Hong M, Akerkar R (2019) A framework to integrate social media and authoritative data for disaster relief detection and distribution optimization. Int J Disaster Risk Reduct 39:101143
Sinnappan S, Farrell C, Stewart E (2010) Priceless tweets! a study on Twitter messages posted during crisis: Black Saturday. ACIS 2010 Proceedings, p 39
Stowe K, Paul M, Palmer M, Palen L, Anderson KM (2016) Identifying and categorizing disaster-related tweets. In: Proceedings of The fourth international workshop on natural language processing for social media, pp 1–6
Sultana T, Badugu S (2020) A review on different question answering system approaches. In: Advances in decision sciences, image processing, security and computer vision, pp 579–586. Springer, Cham
Thomson R, Ito N, Suda H, Lin F, Liu Y, Hayasaka R, Isochi R, Wang Z (2012) Trusting tweets: the Fukushima disaster and information source credibility on twitter. In: Proceedings of the 9th international ISCRAM conference, pp 1–10
Verma S, Vieweg S, Corvey WJ, Palen L, Martin JH, Palmer M, Schram A, Anderson KM (2011) Natural language processing to the rescue? Extracting” situational awareness” tweets during mass emergency. In: ICWSM, pp 385–392
Vieweg S, Hughes AL, Starbird K, Palen L (2010) Microblogging during two natural hazards events: what twitter may contribute to situational awareness. In: Proceedings of the SIGCHI conference on human factors in computing systems, pp 1079–1088. ACM
Wang Y, Taylor JE (2018) Urban crisis detection technique: a spatial and data driven approach based on latent Dirichlet allocation (LDA) topic modeling. In: Proceedings of the 2018 construction research congress
Wang J, Xu W, Fu X, Xu G, Wu Y (2020) ASTRAL: adversarial trained LSTM-CNN for named entity recognition. Knowl-Based Syst, 105842
Xia K, Huang J, Wang H (2020) LSTM-CNN architecture for human activity recognition. IEEE Access 8:56855–56866
Zhang Z, Luo L (2019) Hate speech detection: a solved problem? The challenging case of long tail on twitter. Semantic Web 10.5:925–945
Zhang S, Vucetic S (2016) Semi-supervised discovery of informative tweets during the emerging disasters. arXiv:1610.03750
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Paul, N.R., Sahoo, D. & Balabantaray, R.C. Classification of crisis-related data on Twitter using a deep learning-based framework. Multimed Tools Appl 82, 8921–8941 (2023). https://doi.org/10.1007/s11042-022-12183-w
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11042-022-12183-w