Deep Learning Benchmarks and Datasets for Social Media Image Classification for Disaster Response

Description of the dataset


The crisis image benchmark dataset consists data from several data sources such as CrisisMMD, data from AIDR and Damage Multimodal Dataset (DMD). The purpose of this work was to develop a consolidated dataset, create non-overlapping train/dev/test set and provide a benchmark results for the community.

The dataset consists labels for four tasks:

  1. Task 1: Disaster types
    • Earthquake
    • Fire
    • Flood
    • Hurricane
    • Landslide
    • Not disaster
    • Other disaster
  2. Task 2: Informativeness
    • Informative
    • Not informative
  3. Task 3: Humanitarian categories
    • Affected, injured, or dead people
    • Infrastructure and utility damage
    • Not humanitarian
    • Rescue volunteering or donation effort
  4. Task 4: Damage severity
    • Little or none
    • Mild
    • Severe


Downloads: Labeled data

  • Crisis Image Benchmarks Dataset version v1.0: download (11G)
    • Individual task sets:

Please cite the following papers, if you use any of these resources in your research.
  1. Firoj Alam, Ferda Ofli, Muhammad Imran, Tanvirul Alam, Umair Qazi, Deep Learning Benchmarks and Datasets for Social Media Image Classification for Disaster Response, In 2020 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining (ASONAM), 2020. [Bibtex]
  2. Firoj AlamFerda Ofli, and Muhammad Imran, CrisisMMD: Multimodal Twitter Datasets from Natural Disasters. In Proceedings of the 12th International AAAI Conference on Web and Social Media (ICWSM), 2018, Stanford, California, USA. [Bibtex]
  3. Hussein Mozannar, Yara Rizk, and Mariette Awad, Damage Identification in Social Media Posts using Multimodal Deep Learning, In Proc. of ISCRAM, May 2018, pp. 529–543.