Abstract
In recent days, humanitarian organizations rely on social media like Twitter for situational awareness during the disaster. Millions of tweets are posted on Twitter in the form of text or images or both. Existing works showed that both image and text give complementary information during the disaster. Multi-modal informative tweet detection is helpful to both government and non-government organizations which remains a challenging task during the disaster. However, most of the existing works focused on either text or image content, but not both. In this paper, we propose a novel method based on the combination of fine-tuned BERT and DenseNet models for identifying the multi-modal informative tweets during the disaster. Fine-tuned BERT model is used to extract the linguistic, syntactic and semantic features which help deep understanding of the informative text present in the multi-modal tweet. On the other hand, the fine-tuned DenseNet model is used to extract the sophisticated features from the image. Different experiments are performed on a vast number of data-sets such as Hurricane Harvey, Hurricane Irma, Hurricane Maria, California Wildfire, Sri Lanka floods and Iraq–Iran Earthquake. Experimental results demonstrate that the proposed method outperforms the state-of-the-art method on different parameters. It is the first attempt, to the best of our knowledge, to detect multi-modal informative tweets using the combination of fine-tuned BERT and DenseNet models, where at least any text or image is informative during the disaster.
Similar content being viewed by others
References
Agarwal M, Leekha M, Sawhney R, Shah RR (2020) Crisis-Dias: towards multimodal damage analysis-deployment, challenges and assessment. Proc AAAI Conf Artif Intell 34:346–353
Alam F, Ofli F, Imran M (2018) Crisismmd: multimodal Twitter datasets from natural disasters. In: Proceedings of the 12th international AAAI conference on web and social media (ICWSM)
Alam F, Ofli F, Imran M (2019) Descriptive and visual summaries of disaster events using artificial intelligence techniques: case studies of hurricanes Harvey, Irma, and Maria. Behaviour & Information Technology pp 1–31
Alberti C, Lee K, Collins M (2019) A BERT baseline for the natural questions. arXiv preprint arXiv:190108634
Basu M, Shandilya A, Khosla P, Ghosh K, Ghosh S (2019) Extracting resource needs and availabilities from microblogs for aiding post-disaster relief operations. IEEE Trans Comput Soc Syst 6(3):604–618
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
Chien T, Kalita J (2019) Adversarial analysis of natural language inference systems. arXiv preprint arXiv:191203441
Cresci S, Tesconi M, Cimino A, Dell’Orletta F (2015) A linguistically-driven approach to cross-event damage assessment of natural disasters from social media messages. In: Proceedings of the 24th international conference on world wide web, ACM, pp 1195–1200
Devlin J, Chang MW, Lee K, Toutanova K (2018) BERT: pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:181004805
Gautam AK, Misra L, Kumar A, Misra K, Aggarwal S, Shah RR (2019) Multimodal analysis of disaster tweets. In: 2019 IEEE Fifth international conference on multimedia big data (BigMM). IEEE, pp 94–103
Goldberg Y (2019) Assessing BERT’s syntactic abilities. arXiv preprint arXiv:190105287
Hao H, Wang Y (2019) Hurricane damage assessment with multi-, crowd-sourced image data: a case study of Hurricane Irma in the city of Miami. In: ISCRAM
Huang G, Liu Z, Van Der Maaten L, Weinberger KQ (2017) Densely connected convolutional networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 4700–4708
Hughes AL, Palen L (2009) Twitter adoption and use in mass convergence and emergency events. Int J Emerg Manag 6(3–4):248–260
Imran M, Castillo C, Lucas J, Meier P, Vieweg S (2014) Aidr: artificial intelligence for disaster response. In: Proceedings of the 23rd international conference on world wide web. ACM, pp 159–162
Imran M, Castillo C, Diaz F, Vieweg S (2015) Processing social media messages in mass emergency: a survey. ACM Comput Surv (CSUR) 47(4):67
Jiang N, de Marneffe MC (2019) Evaluating BERT for natural language inference: a case study on the commitmentbank. In: Proceedings of the 2019 conference on empirical methods in natural language processing and the 9th international joint conference on natural language processing (EMNLP-IJCNLP), pp 6088–6093
Krizhevsky A, Sutskever I, Hinton GE (2012) Imagenet classification with deep convolutional neural networks. In: Advances in neural information processing systems, pp 1097–1105
Li X, Caragea D, Caragea C, Imran M, Ofli F (2019) Identifying disaster damage images using a domain adaptation approach. In: ISCRAM
Lin Y, Tan YC, Frank R (2019) Open sesame: getting inside BERT’s linguistic knowledge. arXiv preprint arXiv:190601698
Madichetty S, Muthukumarasamy S (2020) Detection of situational information from Twitter during disaster using deep learning models. Sādhanā 45(1):1–13
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(1):42
Madichetty S, Sridevi M (2020a) Identification of medical resource tweets using majority voting-based ensemble during disaster. Soc Netw Anal Min 10(1):1–18
Madichetty S, Sridevi M (2020b) A novel method for identifying the damage assessment tweets during disaster. Future Gener Comput Syst 116:440–454
Madichetty S et al (2018) Re-ranking feature selection algorithm for detecting the availability and requirement of resources tweets during disaster. Int J Comput Intell IoT 1(2):207–211
Mouzannar H, Rizk Y, Awad M (2018) Damage identification in social media posts using multimodal deep learning. In: ISCRAM
Nalluru G, Pandey R, Purohit H (2019) Classifying relevant social media posts during disasters using ensemble of domain-agnostic and domain-specific word embeddings. arXiv preprint arXiv:191105165
Nguyen DT, Mannai KAA, Joty S, Sajjad H, Imran M, Mitra P (2016) Rapid classification of crisis-related data on social networks using convolutional neural networks. arXiv preprint arXiv:160803902
Nguyen DT, Ofli F, Imran M, Mitra P (2017) Damage assessment from social media imagery data during disasters. In: Proceedings of the 2017 IEEE/ACM international conference on advances in social networks analysis and mining 2017. ACM, pp 569–576
Rudra K, Ganguly N, Goyal P, Ghosh S (2018a) Extracting and summarizing situational information from the Twitter social media during disasters. ACM Trans Web (TWEB) 12(3):17
Rudra K, Goyal P, Ganguly N, Mitra P, Imran M (2018b) Identifying sub-events and summarizing disaster-related information from microblogs. In: The 41st international ACM SIGIR conference on research & development in information retrieval. ACM, pp 265–274
Sreenivasulu M, Sridevi M (2017) Mining informative words from the tweets for detecting the resources during disaster. In: International conference on mining intelligence and knowledge exploration. Springer, pp 348–358
Sreenivasulu M, Sridevi M (2020) Comparative study of statistical features to detect the target event during disaster. Big Data Min Anal 3(2):121–130
Xie S, Duan J, Liu S, Dai Q, Liu W, Ma Y, Guo R, Ma C (2016) Crowdsourcing rapid assessment of collapsed buildings early after the earthquake based on aerial remote sensing image: a case study of yushu earthquake. Remote Sens 8(9):759
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
Madichetty, S., Muthukumarasamy, S. & Jayadev, P. Multi-modal classification of Twitter data during disasters for humanitarian response. J Ambient Intell Human Comput 12, 10223–10237 (2021). https://doi.org/10.1007/s12652-020-02791-5
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s12652-020-02791-5