[Defended thesis] Sarah Valentin: Extraction and aggregation of information from multi-source data for international monitoring of infectious animal diseases

Extraction and aggregation of information from multi-source data for international monitoring of infectious animal diseases

I'm a PhD student at CIRAD's UMR TETIS. A veterinary surgeon by training, after completing a Master2 in Biostatistics, Biomathematics, Bioinformatics and Health (B3S) at the Université Claude Bernard Lyon 1, I started this thesis, supervised by Mathieu Roche and Renaud Lancelot.

• Starting date: Septembre 2017
• University: Montpellier Université d’Excellence, MUSE
• PhD school:  I2S (Information, Structures, Systèmes)
• Scientific field:  IT, épidemiology
• Thesis supervisors: Mathieu Roche (Cirad, UMR Tetis), Renaud Lancelot (Cirad, UMR ASTRE)
• Funding: Cirad
• #DigitAg : Labeled PhD – Challenge 8 – Axes 4 et 5

Keywords: Epidemiological intelligence, animal health, unstructured data, web

Abstract: Monitoring animal health worldwide, especially the early detection of outbreaks of emerging and exotic pathogens, is one of the means of preventing the introduction of infectious diseases in France. In that context, the French epidemic intelligence team for international monitoring of animal health has created a tool dedicated to automatic surveillance of electronic media. This tool is based on a text mining approach, which detects, collects, classifies and extracts information from non-structured textual data available in the media reports on the Web. In addition to methodological improvements (spatial uncertainty, automatic classification), the thesis will focus on identification, combination and qualification of information and indicators from multi-sources data to detect the emergence of animal diseases.

Contact :  mathieu.roche [AT] cirad.fr

Social networks: LinkedIn – ResearchGate

Communications & Papers

• R. Goel, S. Valentin, A. Delaforge, S. Fadloun, A. Sallaberry, M. Roche, P. Poncelet (2020) EpidNews: Extracting, exploring and annotating news for monitoring animal diseases, Journal of Computer Language 
• Valentin Sarah, Arsevska Elena, Falala Sylvain, De Goër Jocelyn, Lancelot Renaud, Mercier Alizé, Rabatel Julien, Roche Ma thieu. 2020. “PADI-web: A multilingual event-based surveillance system for monitoring animal infectious diseases ”. Computers and Electronics in Agriculture , 169, 105163, 5 p. https://doi.org/10.1016/j.compag.2019.105163
• Rohan Goel, Samiha Fadloun, Sarah Valentin, Arnaud Sallaberry, Mathieu Roche, Pascal Poncelet (2018). EpidNews: An Epidemiological News Explorer for Monitoring Animal Diseases. VINCI ’18 Proceedings of the 11th International Symposium on Visual Information Communication and Interaction, Växjö, Sweden — August 13 – 15, 2018, pp 1-8 – https://doi.org/10.1145/3231622.3231624
• Elena Arsevska, Sarah Valentin, Julien Rabatel, Jocelyn de Goër de Hervé, Sylvain Falala, Renaud Lancelot, Mathieu Roche (2018). Web monitoring of emerging animal infectious diseases integrated in the French Animal Health Epidemic Intelligence System. PLOS One – https://doi.org/10.1371/journal.pone.0199960
• Sarah Valentin, Renaud Lancelot, Mathieu Roche  (2018). Surveillance automatisée de sources non-officielles pour la veille sanitaire internationale : évaluation rétrospective sur la fièvre aphteuse en Afrique. LIRIMA Workshop « Agriculture numérique en Afrique », Montpellier, France, 4 Avril 2018 – http://agritrop.cirad.fr/587790/
• Sarah Valentin, Sylvain Falala, Jocelyn De Goër,Elena Arsevska, Julien Rabatel, Mathieu Roche, Renaud Lancelot (2018). An automatic animal diseases surveillance system based on textual media analysis. InnovSur 2018 : ‘INNOVATION in Health Surveillance’ International Forum, Montpellier, France, 16 Mai 2018 (poster) – http://agritrop.cirad.fr/588023/