Knowing whether humanitarian action is effective requires feedback loops. Until now, these are predominantly of a qualitative nature. The ICRC currently relies on observations, interviews and status reports compiled by field analysts to monitor its work. This has several shortcomings:
1. Status reports are heavily dependent on personal assessment and thus fluctuate between different analysts.
2. The reports are in unstructured, textual form, making it difficult to extract information.
3. Although a large organization, the ICRC does not have the human resources to monitor incidents of armed violence across entire countries.
To address these issues, we propose incorporating large amounts of data, quantitative measures of conflict intensity and automated, machine-based event analysis. Such data can be matched against the ICRC’s data on its protection work that aims to influence armed forces and groups to fight in accordance with international humanitarian law (IHL). This would allow the ICRC to monitor the impact of its actions and facilitate more informed, data-driven decision-making in planning future actions.
EPFL PIs: Dr. Roberto Castello, Swiss Data Science Center (EPFL and ETHZ); Prof. Daniel Gatica-Perez, Social Computing group (LIDIAP)
Partner: Fiona Terry (ICRC), Niklas Stoehr (ETHZ)