Integrating textual data for enhanced explanation of food crises at subnational scale

Valentin Sarah, Menya Edmond, Interdonato Roberto, Roche Mathieu, Owuor Dickson. 2024. Integrating textual data for enhanced explanation of food crises at subnational scale. In : Proceedings of the Discovery Science Late Breaking Contributions 2024 (DS-LB 2024). Naretto Francesca (ed.), Pellungrini Roberto (ed.). Aachen : CEUR Workshop Proceedings, 4 p. (CEUR Workshop Proceedings, 3928) International Conference on Discovery Science. 27, Pise, Italie, 14 Octobre 2024/16 Octobre 2024.

Résumé : In an attempt to anticipate Food Security (FS) crises and overcome the limits of existing early warning systems, predictive models can forecast risk indices by combining heterogeneous data. While using different data sources (e.g., satellite imagery, agroclimatic data, food prices) allows to consider various factors that may impact food crises, the explainability of these models remains challenging. In this work, we propose a Food Security indicator solely based on textual data, discerning among different triggers and accounting for possible biases in the spatial coverage of news. We evaluate our approach on a corpus of French-language documents from Burkina Faso and highlight its significance, paving the way for more open and explainable data sources for monitoring food insecurity.

Mots-clés libres : Text Mining, Food Security, West Africa, Natural Language Processing

Auteurs et affiliations

• Valentin Sarah, CIRAD-ES-UMR TETIS (FRA) ORCID: 0000-0002-9028-681X
• Menya Edmond, CIRAD-ES-UMR TETIS (FRA)
• Interdonato Roberto, CIRAD-ES-UMR TETIS (FRA) ORCID: 0000-0002-0536-6277
• Roche Mathieu, CIRAD-ES-UMR TETIS (FRA) ORCID: 0000-0003-3272-8568
• Owuor Dickson, Strathmore University (KEN)

Source : Cirad-Agritrop (https://agritrop.cirad.fr/613635/)

Métriques

[ Page générée et mise en cache le 2025-09-22 ]