How text-mining could improve epidemiological surveillance?

Roche Mathieu. 2022. How text-mining could improve epidemiological surveillance?. In : Identify signs and drivers of zoonotic diseases emergence and digital data resources for Epidemic Intelligence: Book of abstracts. Rizzoli Annapaola (ed.), Marin Floriana (ed.), Rosà. San Michele all'Adige : Fondazione Edmund Mach, Résumé, 33-34. ISBN 978-88-7843-058-7 MOOD workshop: Identify Signs and Drivers of Zoonotic Diseases Emergence and Digital Data Resources for Epidemic Intelligence, Trento, Italie, 28 Septembre 2022/29 Septembre 2022.

Résumé : The ability to identify emerging and re-emerging diseases is challenging for the health domain. In this context, event-based surveillance (EBS) gathers information from heterogenous data sources, including online news articles. EBS systems integrate text-mining methods to deal with huge amounts of textual data. Text mining aims at discovering new information from textual datasets (i.e. corpus). This talk focuses on the use text-mining and multidisciplinary approaches in order to mine news data dealing with the health domain. These data science approaches are integrated in an EBS system called PADI-Web (Platform for Automated extraction of Disease Information from the web). PADIWeb dedicated to animal health surveillance tackles disease-based and symptom-based surveillance. To address these issues different text-mining methods associated with labeled textual datasets are integrated in the main steps of EBS systems: data acquisition, information retrieval (i.e. identification of relevant texts), epidemiological information extraction, information to communicate to end-users. In our work, specific methods are proposed to extract epidemiological events in multilingual news. First, a fine-grained classification enables to highlight texts dealing with "Outbreak declaration" (i.e. sentence classification). Second, a group of epidemiological information (i.e. locations, hosts, symptoms, etc.) is automatically extracted in relevant documents. Based on these approaches, different strategies and associated algorithms are proposed and discussed for improving EBS systems.

Mots-clés libres : Epidemic intelligence, Event-based surveillance, Text Mining, Natural Language Processing, One Health, PADI-web

Agences de financement européennes : European Commission

Programme de financement européen : H2020

Auteurs et affiliations

• Roche Mathieu, CIRAD-ES-UMR TETIS (FRA) ORCID: 0000-0003-3272-8568

Source : Cirad-Agritrop (https://agritrop.cirad.fr/603243/)

Métriques

[ Page générée et mise en cache le 2023-09-24 ]