Developing Annotated Resources for Internal Displacement Monitoring
This work addresses the need for improved accuracy in disaster monitoring infrastructure for organizations like the Internal Displacement Monitoring Centre, though it is incremental as it builds on existing monitoring efforts.
The paper tackles the problem of monitoring internal displacement by developing a novel annotation framework and annotated resources for the IDETECT platform, resulting in a multi-faceted schema that includes event details like cause and quantity, and a case study applying machine learning to document classification tasks.
This paper describes in details the design and development of a novel annotation framework and of annotated resources for Internal Displacement, as the outcome of a collaboration with the Internal Displacement Monitoring Centre, aimed at improving the accuracy of their monitoring platform IDETECT. The schema includes multi-faceted description of the events, including cause, quantity of people displaced, location and date. Higher-order facets aimed at improving the information extraction, such as document relevance and type, are proposed. We also report a case study of machine learning application to the document classification tasks. Finally, we discuss the importance of standardized schema in dataset benchmark development and its impact on the development of reliable disaster monitoring infrastructure.