pic 57

Nowcasting internal migration movements by using an AI-enabled news analyses tool

Key information
Region/s
Data sources

AI / Machine learning

Fill 58 Created with Sketch.

Summary

The Internal Displacement Event Tagging Extraction and Clustering Tool (IDETECT) of the Internal Displacement Monitoring Centre (IDMC) is a platform that monitors incidents likely to increase internal displacement – such as violent conflicts and natural hazards – by using AI-enabled analyses methodologies. In a first step, it reads the world’s news, as well as UN and NGO reports, filters it for articles relevant to internal displacement, and, finally, extracts key information, such as causes, locations and number of displacements. All information is stored in the database, helping the algorithms improve accuracy to monitor internal displacements in near real-time.

Results

IDETECT supports IDMC’s work in monitoring internal displacements globally in numerous ways. The large amounts of data that are analyzed quickly and accurately using AI-enabled methodologies support the team to cover incidents relevant to international displacement on a global scope and in near real-time. This allows the team to report and inform about the internal displacements in a timely and accurate manner, facilitating political dialogues and humanitarian emergency operations on the ground. In addition to the current sources of reports and news from the media, NGOs, and the UN, IDMC has recently begun integrating satellite imagery and anonymized, aggregated social media data to infer different patterns of displacement, particularly where there is no other data was available. Overall, this approach can be replicated in other contexts as well, especially where information about “push factors” – social, political, or agricultural impacts with a likelihood to lead to displacement – is required to monitor and predict human mobility movements on the national and international level.

 

(Image: © IDMC.com)

Last modified
22 September 2022