Multimodal Damage Identification for Humanitarian Computing

Donated on 6/1/2018

5879 captioned images (image and text) from social media related to damage during natural disasters/wars, and belong to 6 classes: Fires, Floods, Natural landscape, Infrastructural, Human, Non-damage.

Dataset Characteristics

Multivariate, Text

Subject Area

Social

Associated Tasks

Classification

Attribute Type

Integer

# Instances

5879

# Attributes

-

Information

Additional Information

Samples were retrieved from social media posts including Instagram and Twitter.

Attribute Information

Additional Information

640x640 RGB images and raw text

Download
0 citations
717 views

Creators

Hussein Mouzannar

Yara Rizk

Mariette Awad

License

By using the UCI Machine Learning Repository, you acknowledge and accept the cookies and privacy practices used by the UCI Machine Learning Repository.

Read Policy