Skip to main content
SpringerLink
Log in

Utilizing social media for emergency response: a tweet classification system using attention-based BiLSTM and CNN for resource management

  • Published:
Multimedia Tools and Applications Aims and scope Submit manuscript

Abstract

During disasters and emergencies, microblogging platforms like Twitter are crucial sources of real-time information. With so much verbal content present during such situations, it is challenging to extract pertinent situational information. There have been various attempts to identify tweets that are relevant to disasters, but relatively few have concentrated on finding tweets with precise information. Techniques employing the underlying linguistic qualities had been applied in earlier studies which are not suitable for microblogs. We concentrate on one specific application that is crucial for the efficient administration of disaster-related recovery operations: recognizing tweets that provide information about the requirements and availability of vital resources. We focus on a supervised approach using deep learning techniques to differentiate resource tweets from others. The proposed system is a hybrid model employing CNN and BiLSTM to effectively learn fine-grained features from the tweet text. The attention mechanism is also incorporated into the model to get an importance-weighted feature vector. Once the resource tweets have been found, emergency responders can use them to schedule resource allocation so that recovery actions can be carried out efficiently. A supervised model is trained on tweets collected during earthquakes that struck Nepal and Italy in 2015 and 2016, respectively. To verify the appropriateness of the system for practical deployment, we performed in-domain and cross-domain experiments. Our system surpassed several state-of-the-art approaches. According to experimental findings, text categorization in a chaotic environment, such as a disaster event, will gain by considering local key information and global term dependency.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Algorithm 1
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12
Fig. 13

Similar content being viewed by others

Data Availability

The datasets used and analyzed during the current study are available online at the following URLs:

\(\bullet \) http://doi.org/10.5281/zenodo.2649794

\(\bullet \) http://www.isical.ac.in/fire/data/2016/FIRE2016-microblogs-track-data.tar.gz

\(\bullet \) http://doi.org/10.5281/zenodo.3336563

\(\bullet \) https://crisisnlp.qcri.org/

Notes

  1. https://media.ifrc.org/ifrc/world-disaster-report-2018/.

  2. http://www.bloggerchica.com/how-social-media-broke-the-story-of-the-sfo-plane-crash

  3. https://pypi.org/project/tweet-preprocessor/

References

  1. Adwaith D, Abishake AK, Raghul SV et al (2022) Enhancing multimodal disaster tweet classification using state-of-the-art deep learning networks. Multimedia Tools and Applications 81(13):18,483-18,501

    Article  Google Scholar 

  2. Altman NS (1992) An introduction to kernel and nearest-neighbor nonparametric regression. Am Stat 46(3):175–185

    Article  MathSciNet  Google Scholar 

  3. Bahdanau D, Cho K, Bengio Y (2014) Neural machine translation by jointly learning to align and translate. arXiv:1409.0473

  4. Basu M, Ghosh K, Das S et al (2017) Identifying post-disaster resource needs and availabilities from microblogs. In: 2017 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining (ASONAM), IEEE, pp 427–430

  5. Basu M, Shandilya A, Khosla P et al (2019) Extracting resource needs and availabilities from microblogs for aiding post-disaster relief operations. IEEE Trans Comput Soc Syst 6(3):604–618

    Article  Google Scholar 

  6. Briskilal J, Subalalitha C (2022) An ensemble model for classifying idioms and literal texts using bert and roberta. Inf Process Manag 59(1):102,756

    Article  Google Scholar 

  7. 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

  8. Chen T (2016) Story and lessons behind the evolution of xgboost

  9. Chundi R, Hulipalled VR, Simha J (2020) Saekcs: Sentiment analysis for english-kannada code switchtext using deep learning techniques. In: 2020 International conference on smart technologies in computing. Electrical and Electronics (ICSTCEE), IEEE, pp 327–331

  10. Cortes C, Vapnik V (1995) Support-vector networks. Mach Learn 20(3):273–297

    Article  Google Scholar 

  11. Daniluk M, Rocktäschel T, Welbl J et al (2017) Frustratingly short attention spans in neural language modeling. arXiv:1702.04521

  12. Devlin J, Chang MW, Lee K et al (2018) Bert: pre-training of deep bidirectional transformers for language understanding. arXiv:1810.04805

  13. Dong L, Satpute MN, Wu W et al (2021) Two-phase multidocument summarization through content-attention-based subtopic detection. IEEE Trans Comput Soc Syst 8(6):1379–1392

    Article  Google Scholar 

  14. Du J, Vong CM, Chen CP (2020) Novel efficient rnn and lstm-like architectures: Recurrent and gated broad learning systems and their applications for text classification. IEEE Trans Cybern 51(3):1586–1597

    Article  Google Scholar 

  15. Elnagar A, Al-Debsi R, Einea O (2020) Arabic text classification using deep learning models. Inf Process Manag 57(1):102,121

    Article  Google Scholar 

  16. Fellbaum C, Brown K (2005) Encyclopedia of language and linguistics

  17. Fix E, Hodges JL Jr (1952) Discriminatory analysis-nonparametric discrimination: Small sample performance. Tech. rep., University of California, Berkeley

    Google Scholar 

  18. Ghasemi R, Ashrafi Asli SA, Momtazi S (2022) Deep persian sentiment analysis: Cross-lingual training for low-resource languages. J Inf Sci 48(4):449–462

    Article  Google Scholar 

  19. Ghosh S, Ghosh K (2016) Overview of the fire 2016 microblog track: information extraction from microblogs posted during disasters. In: FIRE (Working Notes), Citeseer, pp 56–61

  20. Ghosh S, Ghosh K, Ganguly D et al (2017) Ecir 2017 workshop on exploitation of social media for emergency relief and preparedness (smerp 2017). ACM SIGIR Forum. ACM, New York, pp 36–41

    Google Scholar 

  21. Guo Z, Han D (2022) Sparse co-attention visual question answering networks based on thresholds. Appl Intell:1–15

  22. Guo Z, Zhu L, Han L (2021) Research on short text classification based on roberta-textrcnn. In: 2021 International Conference on Computer Information Science and Artificial Intelligence (CISAI), IEEE, pp 845–849

  23. Han J, Pei J, Kamber M (2011) Data mining: concepts and techniques. Elsevier

  24. Hiware K, Dutt R, Sinha S et al (2020) Narmada: need and available resource managing assistant for disasters and adversities. arXiv:2005.13524

  25. Hochreiter S, Schmidhuber J (1997) Long short-term memory. Neural Comput 9(8):1735–1780

    Article  Google Scholar 

  26. Jang B, Kim M, Harerimana G et al (2020) Bi-lstm model to increase accuracy in text classification: combining word2vec cnn and attention mechanism. Appl Sci 10(17):5841

    Article  Google Scholar 

  27. Jelodar H, Wang Y, Orji R et al (2020) Deep sentiment classification and topic discovery on novel coronavirus or covid-19 online discussions: Nlp using lstm recurrent neural network approach. IEEE J Biomed Health Inform 24(10):2733–2742

    Article  Google Scholar 

  28. Kalchbrenner N, Grefenstette E, Blunsom P (2014) A convolutional neural network for modelling sentences. arXiv:1404.2188

  29. Khattar A, Quadri S (2022) Generalization of convolutional network to domain adaptation network for classification of disaster images on twitter. Multimedia Tools and Applications 81(21):30,437-30,464

    Article  Google Scholar 

  30. Khosla P, Basu M, Ghosh K et al (2017) Microblog retrieval for post-disaster relief: applying and comparing neural ir models. arXiv:1707.06112

  31. Kim Y (2015) Convolutional neural networks for sentence classification. arXiv:1408.5882

  32. Kingma DP, Ba J (2014) Adam: A method for stochastic optimization. arXiv:1412.6980

  33. Kowsari K, Brown DE, Heidarysafa M et al (2017) Hdltex: hierarchical deep learning for text classification. In: 2017 16th IEEE international conference on machine learning and applications (ICMLA), IEEE, pp 364–371

  34. Kumar A, Singh JP, Dwivedi YK et al (2020) A deep multi-modal neural network for informative twitter content classification during emergencies. Ann Oper Res:1–32

  35. Larochelle H, Hinton GE (2010) Learning to combine foveal glimpses with a third-order boltzmann machine. Adv Neural Inf Process Syst 23

  36. Liu G, Guo J (2019) Bidirectional lstm with attention mechanism and convolutional layer for text classification. Neurocomputing 337:325–338

    Article  Google Scholar 

  37. Liu Y, Ott M, Goyal N et al (2019) Roberta: A robustly optimized bert pretraining approach. arXiv:1907.11692

  38. Lu Y, Zeng J, Zhang J et al (2021) Attention calibration for transformer in neural machine translation. In: Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pp 1288–1298

  39. Madichetty S, Sridevi M (2018) Re-ranking feature selection algorithm for detecting the availability and requirement of resources tweets during disaster. Int J Comput Intell IoT 1(2)

  40. Madichetty S, Sridevi M (2021) A novel method for identifying the damage assessment tweets during disaster. Futur Gener Comput Syst 116:440–454

    Article  Google Scholar 

  41. Madichetty S et al (2020) Classifying informative and non-informative tweets from the twitter by adapting image features during disaster. Multimed Tool Appl 79(39):28,901-28,923

    Article  Google Scholar 

  42. Madichetty S et al (2020) Identification of medical resource tweets using majority voting-based ensemble during disaster. Soc Netw Anal Min 10(1):1–18

    Article  Google Scholar 

  43. Madichetty S et al (2021) A stacked convolutional neural network for detecting the resource tweets during a disaster. Multimedia tools and applications 80(3):3927–3949

    Article  Google Scholar 

  44. Minaee S, Kalchbrenner N, Cambria E et al (2021) Deep learning-based text classification: a comprehensive review. ACM Comput Surv (CSUR) 54(3):1–40

    Article  Google Scholar 

  45. Nguyen DT, Al Mannai KA, Joty S et al (2017a) Robust classification of crisis-related data on social networks using convolutional neural networks. In: Eleventh international AAAI conference on web and social media

  46. Nguyen DT, Ofli F, Imran M et al (2017b) 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, pp 569–576

  47. Oral B, Eryiğit G (2022) Fusion of visual representations for multimodal information extraction from unstructured transactional documents. Int J Doc Anal Recognit (IJDAR):1–19

  48. Pathak AR, Pandey M, Rautaray S (2021) Topic-level sentiment analysis of social media data using deep learning. Appl Soft Comput 108:107,440

    Article  Google Scholar 

  49. Paul NR, Sahoo D, Balabantaray RC (2023) Classification of crisis-related data on twitter using a deep learning-based framework. Multimedia Tool Appl 82(6):8921–8941

    Article  Google Scholar 

  50. Pennington J, Socher R, Manning CD (2014) Glove: global vectors for word representation. In: Proceedings of the 2014 conference on empirical methods in natural language processing (EMNLP), pp 1532–1543

  51. Pourebrahim N, Sultana S, Edwards J et al (2019) Understanding communication dynamics on twitter during natural disasters: a case study of hurricane sandy. Int J Disaster Risk Reduction 37:101,176

    Article  Google Scholar 

  52. Purohit H, Castillo C, Diaz F et al (2014) Emergency-relief coordination on social media: automatically matching resource requests and offers. First Monday

  53. Qu S, Yang Y, Que Q (2021) Emotion classification for spanish with xlm-roberta and textcnn. In: IberLEF@ SEPLN, pp 94–100

  54. Rudra K, Ganguly N, Goyal P et al (2018) Extracting and summarizing situational information from the twitter social media during disasters. ACM Trans Web (TWEB) 12(3):1–35

    Article  Google Scholar 

  55. Shu X, Zhang L, Qi GJ et al (2021) Spatiotemporal co-attention recurrent neural networks for human-skeleton motion prediction. IEEE Trans Pattern Anal Mach Intell 44(6):3300–3315

    Article  Google Scholar 

  56. Shu X, Yang J, Yan R et al (2022) Expansion-squeeze-excitation fusion network for elderly activity recognition. IEEE Trans Circuits Syst Video Technol 32(8):5281–5292

    Article  Google Scholar 

  57. Strohman T, Metzler D, Turtle H et al (2005) Indri: A language model-based search engine for complex queries. In: Proceedings of the international conference on intelligent analysis, Citeseer, pp 2–6

  58. Subba R, Bui T (2017) Online convergence behavior, social media communications and crisis response: an empirical study of the 2015 nepal earthquake police twitter project. In: Proceedings of the 50th hawaii international conference on system sciences

  59. Tang J, Shu X, Yan R et al (2019) Coherence constrained graph lstm for group activity recognition. IEEE Trans Pattern Anal Mach Intell 44(2):636–647

    Article  Google Scholar 

  60. Temnikova IP, Castillo C, Vieweg S (2015) Emterms 1.0: a terminological resource for crisis tweets. In: ISCRAM

  61. Varga I, Sano M, Torisawa K et al (2013) Aid is out there: looking for help from tweets during a large scale disaster. In: Proceedings of the 51st annual meeting of the association for computational linguistics (Volume 1: Long Papers), pp 1619–1629

  62. Varghese RR, Yadukrishnan T (2019) Role of social media during kerala floods 2018. Libr Philos Pract 2754:1–15

    Google Scholar 

  63. Vaswani A, Shazeer N, Parmar N et al (2017) Attention is all you need. Adv Neural Inf Process Syst 30

  64. Wadud MAH, Kabir MM, Mridha M et al (2022) How can we manage offensive text in social media-a text classification approach using lstm-boost. Int J Inf Manag Data Insights 2(2):100,095

    Google Scholar 

  65. Wiciaputra YK, Young JC, Rusli A (2021) Bilingual text classification in english and indonesian via transfer learning using xlm-roberta. Int J Adv Soft Comput Appl 13(3)

  66. Wouts J, de Boer J, Voppel A et al (2021) belabbert: a dutch roberta-based language model applied to psychiatric classification. arXiv:2106.01091

  67. Zhang Y, Wallace BC (2015) A sensitivity analysis of (and practitioners guide to) convolutional neural networks for sentence classification. arXiv:1510.03820

  68. Zheng X, Wang B, Du X et al (2021) Mutual attention inception network for remote sensing visual question answering. IEEE Trans Geosci Remote Sens 60:1–14

    Google Scholar 

  69. Shu X, Zhang L, Sun Y, et al (2020) Host–parasite: Graph lstm-in-lstm for group activity recognition. IEEE transactions on neural networks and learning systems 32(2):663–674

  70. Shu X, Tang J, Qi GJ, et al (2019) Hierarchical long short-term concurrent memory for human interaction recognition. IEEE transactions on pattern analysis and machine intelligence 43(3):1110–1118

Download references

Author information

Authors and Affiliations

  1. Department of Computer Science & Engineering, National Institute of Technology, Trichy, 620015, Tamilnadu, India

    Rani Koshy & Sivasankar Elango

  2. Department of Computer Science & Engineering, College of Engineering, Trivandrum, 695016, Kerala, India

    Rani Koshy

Authors
  1. Rani Koshy
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Sivasankar Elango
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Rani Koshy.

Ethics declarations

Competing interests

The authors declare that they have no conflict of interest.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Koshy, R., Elango, S. Utilizing social media for emergency response: a tweet classification system using attention-based BiLSTM and CNN for resource management. Multimed Tools Appl 83, 41405–41439 (2024). https://doi.org/10.1007/s11042-023-16766-z

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11042-023-16766-z

Keywords

Search

Navigation