research-article

Open access

Single or ensemble model ? A study on social media images classification in disaster response

Authors:

Hafiz Budi Firmansyah,

Jose Luis Fernandez-Marquez,

Jesus Cerquides,

Giovanna Di Marzo SerugendoAuthors Info & Claims

MISNC '23: Proceedings of the 10th Multidisciplinary International Social Networks Conference

Pages 48 - 54

https://doi.org/10.1145/3624875.3624884

Published: 16 October 2023 Publication History

All formats PDF

Abstract

Social media generate large amounts of almost real-time data which can turn out extremely valuable in an emergency situation, especially for providing information within the first 72 hours after a disaster event. Despite abundant state-of-the-art machine learning techniques to automatically classify social media images, the operational problem in the event of a new disaster remains unsolved. In this study, we evaluate the adaptability of a machine learning model when tested with a completely new disaster. The experimental result showed that a single model trained on the data from different disasters obtained better performance than an ensemble of models, with one model for each individual disaster.

References

[1]

Firoj Alam, Ferda Ofli, and Muhammad Imran. 2018. CrisisMMD: Multimodal Twitter Datasets from Natural Disasters. Proceedings of the 12th International AAAI Conference on Web and Social Media (ICWSM) (2018).

[2]

Firoj Alam, Ferda Ofli, Muhammad Imran, Tanvirul Alam, and Umair Qazi. 2020. Deep learning benchmarks and datasets for social media image classification for disaster response. 2020 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining (ASONAM) (2020). https://doi.org/10.1109/asonam49781.2020.9381294

Digital Library

[3]

Sara Barozzi, Amudha Ravi Shankar, Jose Luis Fernandez-Marquez, and Barbara Pernici. 2019. Filtering Images Extracted from Social Media in the Response Phase of Emergency Events. ISCRAM 2019 Conference Proceedings – 16th International Conference on Information Systems for Crisis Response and Management (2019).

[4]

Moumita Basu, Anurag Shandilya, Prannay Khosla, Kripabandhu Ghosh, and Saptarshi Ghosh. 2019. Extracting resource needs and availabilities from microblogs for aiding post-disaster relief operations. IEEE Transactions on Computational Social Systems 6, 3 (2019), 604–618. https://doi.org/10.1109/tcss.2019.2914179

[5]

Carlos Castillo. 2019. Big Crisis Data: Social Media in disasters and time-critical situations. Cambridge University Press.

[6]

Zhiyuan Cheng, James Caverlee, and Kyumin Lee. 2010. You are where you tweet. Proceedings of the 19th ACM international conference on Information and knowledge management - CIKM ’10 (2010). https://doi.org/10.1145/1871437.1871535

Digital Library

[7]

Jia Deng, Wei Dong, Richard Socher, Li-Jia Li, Kai Li, and Li Fei-Fei. 2009. ImageNet: A large-scale hierarchical image database. 2009 IEEE Conference on Computer Vision and Pattern Recognition (2009), 248–255. https://doi.org/10.1109/CVPR.2009.5206848

[8]

Xuefan Dong and Ying Lian. 2021. A review of social media-based public opinion analyses: Challenges and recommendations. Technology in Society 67 (2021), 101724. https://doi.org/10.1016/j.techsoc.2021.101724

[9]

Hafiz Budi Firmansyah, Jesus Cerquides, and Jose Luis Fernandez-Marquez. 2022. Ensemble learning for the classification of social media data in disaster response. ISCRAM 2022 Conference Proceedings – 19th International Conference on Information Systems for Crisis Response and Management (2022).

[10]

M.A. Ganaie, Minghui Hu, A.K. Malik, M. Tanveer, and P.N. Suganthan. 2022. Ensemble deep learning: A Review. Engineering Applications of Artificial Intelligence 115 (2022), 105151. https://doi.org/10.1016/j.engappai.2022.105151

Digital Library

[11]

Muhammad Hanif, Muhammad Atif Tahir, and Muhammad Rafi. 2021. Vrbagged-net: Ensemble based Deep Learning Model for Disaster Event Classification. Electronics 10, 12 (2021), 1411. https://doi.org/10.3390/electronics10121411

[12]

Kaiming He, Georgia Gkioxari, Piotr Dollár, and Ross Girshick. 2017. Mask R-CNN. 2017 IEEE International Conference on Computer Vision (ICCV) (2017). https://doi.org/10.1109/ICCV.2017.322

[13]

Muhammad Imran, Carlos Castillo, Fernando Diaz, and Sarah Vieweg. 2015. Processing social media messages in mass emergency. Comput. Surveys 47, 4 (2015), 1–38. https://doi.org/10.1145/2771588

Digital Library

[14]

Ilan Kelman. 2015. Climate change and the Sendai Framework for Disaster Risk Reduction. International Journal of Disaster Risk Science 6, 2 (2015), 117–127. https://doi.org/10.1007/s13753-015-0046-5

[15]

Prashant Khare, Grégoire Burel, and Harith Alani. 2018. Classifying crises-information relevancy with semantics. The Semantic Web (2018), 367–383. https://doi.org/10.1007/978-3-319-93417-4_24

Digital Library

[16]

Lingyao Li, Michelle Bensi, Qingbin Cui, Gregory B. Baecher, and You Huang. 2021. Social media crowdsourcing for rapid damage assessment following a sudden-onset natural hazard event. International Journal of Information Management 60 (2021), 102378. https://doi.org/10.1016/j.ijinfomgt.2021.102378

Digital Library

[17]

Fang Liu, Yeting Guo, Zhiping Cai, Nong Xiao, and Ziming Zhao. 2019. Edge-Enabled Disaster Rescue: A Case Study of Searching for Missing People. ACM Trans. Intell. Syst. Technol. 10, 6, Article 63 (dec 2019), 21 pages. https://doi.org/10.1145/3331146

Digital Library

[18]

Sreenivasulu Madichetty and M. Sridevi. 2021. A novel method for identifying the damage assessment tweets during disaster. Future Generation Computer Systems 116 (2021), 440–454. Publisher: Elsevier.

[19]

SreeJagadeesh Malla and Alphonse P.J.A.2021. Covid-19 outbreak: An Ensemble pre-trained deep learning model for detecting informative tweets. Applied Soft Computing 107 (2021), 107495. https://doi.org/10.1016/j.asoc.2021.107495

[20]

Kaveh Moradkhani and Abdolhossein Fathi. 2022. Segmentation of waterbodies in remote sensing images using deep stacked ensemble model. Applied Soft Computing 124 (2022), 109038. https://doi.org/10.1016/j.asoc.2022.109038

Digital Library

[21]

Omer Sagi and Lior Rokach. 2018. Ensemble learning: A survey. WIREs Data Mining and Knowledge Discovery 8, 4 (2018). https://doi.org/10.1002/widm.1249

[22]

Mark Sandler, Andrew Howard, Menglong Zhu, Andrey Zhmoginov, and Liang-Chieh Chen. 2018. Mobilenetv2: Inverted residuals and linear bottlenecks. In Proceedings of the IEEE conference on computer vision and pattern recognition. 4510–4520.

[23]

Tomer Simon, Avishay Goldberg, and Bruria Adini. 2015. Socializing in emergencies—A review of the use of social media in emergency situations. International Journal of Information Management 35, 5 (2015), 609–619. https://doi.org/10.1016/j.ijinfomgt.2015.07.001

Digital Library

[24]

Karen Simonyan and Andrew Zisserman. 2015. Very Deep Convolutional Networks for Large-Scale Image Recognition. arXiv:1409.1556 [cs] (April 2015). http://arxiv.org/abs/1409.1556 arXiv:1409.1556.

[25]

Christian Szegedy, Vincent Vanhoucke, Sergey Ioffe, Jonathon Shlens, and Zbigniew Wojna. 2015. Rethinking the Inception Architecture for Computer Vision. arXiv:1512.00567 [cs] (Dec. 2015). arXiv:1512.00567 version: 3.

[26]

Swapan Talukdar, Bonosri Ghose, Shahfahad, Roquia Salam, Susanta Mahato, Quoc Bao Pham, Nguyen Thi Thuy Linh, Romulus Costache, and Mohammadtaghi Avand. 2020. Flood susceptibility modeling in Teesta River basin, Bangladesh using novel ensembles of bagging algorithms. Stochastic Environmental Research and Risk Assessment 34, 12 (Dec. 2020), 2277–2300. https://doi.org/10.1007/s00477-020-01862-5

[27]

Jiting Tang, Saini Yang, and Weiping Wang. 2021. Social Media-based disaster research: Development, trends, and obstacles. International Journal of Disaster Risk Reduction 55 (2021), 102095. https://doi.org/10.1016/j.ijdrr.2021.102095

[28]

Ethan Weber, Dim P. Papadopoulos, Agata Lapedriza, Ferda Ofli, Muhammad Imran, and Antonio Torralba. 2022. INCIDENTS1M: A large-scale dataset of images with natural disasters, damage, and incidents. IEEE Transactions on Pattern Analysis and Machine Intelligence (2022), 1–14. https://doi.org/10.1109/tpami.2022.3191996

Digital Library

Cited By

Firmansyah HLorini VMulayim MGomes JFernandez-Marquez J(2024)Improving Social Media Geolocation for Disaster Response by Using Text From Images and ChatGPTProceedings of the 2024 11th Multidisciplinary International Social Networks Conference10.1145/3675669.3675696(67-72)Online publication date: 21-Aug-2024
https://dl.acm.org/doi/10.1145/3675669.3675696
Qin HLi Y(2024)FedInc: One-Shot Federated Tuning for Collaborative Incident RecognitionArtificial Neural Networks and Machine Learning – ICANN 202410.1007/978-3-031-72347-6_12(174-185)Online publication date: 17-Sep-2024
https://doi.org/10.1007/978-3-031-72347-6_12

Index Terms

Single or ensemble model ? A study on social media images classification in disaster response
1. Computing methodologies
  1. Machine learning
    1. Learning paradigms
2. Information systems
  1. Information systems applications

Index terms have been assigned to the content through auto-classification.

Recommendations

Improving Social Media Geolocation for Disaster Response by Using Text From Images and ChatGPT
MISNC '24: Proceedings of the 2024 11th Multidisciplinary International Social Networks Conference

Social media can serve as a valuable source of timely and valuable information about the impacts on people and infrastructure during a disaster. However, due to the lack of geographical data in most social media posts, this information is often ...
Accelerating Crisis Response: Automated Image Classification for Geolocating Social Media Content
ASONAM '23: Proceedings of the 2023 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining

In the immediate aftermath of natural or man-made disasters, social media plays an essential role in assessing the impact of the event. The images from social media demonstrated the potential to accelerate the response to a crisis. However, finding the ...
Digitally enabled disaster response: the emergence of social media as boundary objects in a flooding disaster

In recent times, social media has been increasingly playing a critical role in response actions following natural catastrophes. From facilitating the recruitment of volunteers during an earthquake to supporting emotional recovery after a hurricane, ...

Comments

Please enable JavaScript to view thecomments powered by Disqus.

Information & Contributors

Information

Published In

cover image ACM Other conferences

MISNC '23: Proceedings of the 10th Multidisciplinary International Social Networks Conference

September 2023

241 pages

ISBN:9798400708176

DOI:10.1145/3624875

Copyright © 2023 Owner/Author.

This work is licensed under a Creative Commons Attribution International 4.0 License.

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 16 October 2023

Check for updates

Author Tags

Qualifiers

Research-article
Research
Refereed limited

Conference

MISNC 2023

MISNC 2023: The 10th Multidisciplinary International Social Networks Conference

September 4 - 6, 2023

Phuket, Thailand

Acceptance Rates

Overall Acceptance Rate 57 of 97 submissions, 59%

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

1
Total Citations
View Citations
200
Total Downloads

Downloads (Last 12 months)180
Downloads (Last 6 weeks)22

Reflects downloads up to 17 Nov 2024

Other Metrics

View Author Metrics

Citations

Cited By

Firmansyah HLorini VMulayim MGomes JFernandez-Marquez J(2024)Improving Social Media Geolocation for Disaster Response by Using Text From Images and ChatGPTProceedings of the 2024 11th Multidisciplinary International Social Networks Conference10.1145/3675669.3675696(67-72)Online publication date: 21-Aug-2024
https://dl.acm.org/doi/10.1145/3675669.3675696
Qin HLi Y(2024)FedInc: One-Shot Federated Tuning for Collaborative Incident RecognitionArtificial Neural Networks and Machine Learning – ICANN 202410.1007/978-3-031-72347-6_12(174-185)Online publication date: 17-Sep-2024
https://doi.org/10.1007/978-3-031-72347-6_12

View Options

View options

PDF

View or Download as a PDF file.

eReader

View online with eReader.

HTML Format

View this article in HTML Format.

Login options

Check if you have access through your login credentials or your institution to get full access on this article.

Full Access

Get this Publication

Media

Figures

Other

Tables

View Table of Contents