1.1
1
xml
info:srw/schema/1/mods-v3.2
Towards Practical Usage of a Domain Adaptation Algorithm in the Early Hours of a Disaster
Hongmin Li
author
Doina Caragea
author
Cornelia Caragea
author
2017
Iscram
Albi, France
English
Many machine learning techniques have been proposed to reduce the information overload in social media data during an emergency situation. Among such techniques, domain adaptation approaches present greater potential as compared to supervised algorithms because they don't require labeled data from the current disaster for training. However, the use of domain adaptation approaches in practice is sporadic at best. One reason is that domain adaptation algorithms have parameters that need to be tuned using labeled data from the target disaster, which is presumably not available. To address this limitation, we perform a study on one domain adaptation approach with the goal of understanding how much source data is needed to obtain good performance in a practical situation, and what parameter values of the approach give overall good performance. The results of our study provide useful insights into the practical application of domain adaptation algorithms in real crisis situations.
Twitter
Domain adaptation
Disaster
Classification
exported from refbase (http://idl.iscram.org/show.php?record=2057), last updated on Mon, 25 Nov 2019 14:42:27 +0100
text
http://idl.iscram.org/files/hongminli/2017/2057_HongminLi_etal2017.pdf
HongminLi_etal2017
Proceedings of the 14th International Conference on Information Systems for Crisis Response And Management
Iscram 2017
Tina Comes
F
B
editor
14th International Conference on Information Systems for Crisis Response And Management
2017
Iscram
Albi, France
conference publication
692
704
2411-3387
1