A team of computer scientists from the University of Southampton in the UK is embarking on a research program to develop strategies to sustain interest in crowdsourcing analysis of drone footage once the immediate emergency of a disaster has passed.
Currently, what happens is that once the story has dropped out of the daily news cycle volunteers tend to drift away.
Drones are now routinely used in emergency situations such as flooding events, to capture high-quality images of disaster-affected communities. Thanks to new technologies and social networks, the images can be spread quickly via smartphones and other devices where they are analyzed by citizens from all over the world.
Lots of media coverage during an emergency attracts many participants, however, when they fall in number as media attention fades this can cause problems.
“High levels of media coverage can attract a lot of volunteers to analyze drone footage during an emergency, but the number of participants can drastically decrease once the media attention fades,” explained Professor Elena Simperl from the School of Electronics and Computer Science at Southampton University, who is spearheading the project.
“This reduced participation can have a troubling impact on communities’ long term recovery, with less reliable data making it difficult to keep information up to date and assign resources in an effective manner.”
To develop strategies to increase participation Simperl’s team will test strategies such as task variation and sequencing to sustain crowdsourcing of drone footage analysis.
Researchers will also study how experts and volunteers learn over time and acquire skills and motivation to tackle more challenging image analysis tasks.
It is hoped that the outcome of the research will be beneficial to humanitarian relief efforts but also to all crowdsourcing projects that struggle to maintain participant engagement.