1.1
1
xml
info:srw/schema/1/mods-v3.2
A Human-is-the-Loop Approach for Semi-Automated Content Moderation
Daniel Link
author
Bernd Hellingrath
author
Jie Ling
author
2016
Federal University of Rio de Janeiro
Rio de Janeiro, Brasil
English
Online social media has been recognized as a valuable information source for disaster management whose volume, velocity and variety exceed manual processing capacity. Current machine learning systems that support the processing of such data generally follow a human-in-the-loop approach, which has several inherent limitations. This work applies the human-is-the-loop concept from visual analytics to semi-automate a manual content moderation workflow, wherein human moderators take the dominant role. The workflow is instantiated with a supervised machine learning system that supports moderators with suggestions regarding the relevance and categorization of content. The instantiated workflow has been evaluated using in-depth interviews with practitioners and serious games. which suggest that it offers good compatibility with work practices in humanitarian assessment as well as improved moderation quality and higher flexibility than common approaches.
Disaster Management
Social Media Analysis
Human-Is-The-Loop
Content Moderation
Supervised Machine Learning
exported from refbase (http://idl.iscram.org/show.php?record=1401), last updated on Sun, 22 May 2016 10:02:07 +0200
text
http://idl.iscram.org/files/daniellink/2016/1401_DanielLink_etal2016.pdf
DanielLink_etal2016
ISCRAM 2016 Conference Proceedings ? 13th International Conference on Information Systems for Crisis Response and Management
ISCRAM 2016
A. Tapia
editor
P. Antunes
editor
V.A. BaƱuls
editor
K. Moore
editor
J. Porto
editor
13th International Conference on Information Systems for Crisis Response and Management
2016
Federal University of Rio de Janeiro
Rio de Janeiro, Brasil
conference publication
978-84-608-7984-9
2411-3388
1