Social Network Data and Epidemiological Intelligence: A Case Study of Avian Influenza

Purpose - Event Based Surveillance (EBS) systems detect and monitor diseases by analysing articles from online news papers reports health organizations (e.g. FAO, OIE, etc.). However, they partially integrate data social networks, even though these are present in large quantities on the web. The purpose of this study is to exploit network data, such as Twitter YouTube, provide epidemiological additional information for Avian Influenza surveillance. Methods & Materials In context, we propose new text-mining approaches combining lexical rules statistical order normalise textual Social Net- work ('h5 n8' 'H5N8') correct errors YouTube transcriptions 'birth u' 'bird u'). Another challenge consists extracting events automatically identifying spatial entities (Where?), thematic (What?), temporal (When?). For this, extended Named Entity Recognition (NER) tools like spaCy. Results We collected 100 automatic transcripts videos 268 tweets English dealing with avian influenza dedicated API. obtain encouraging results (i.e. accuracy around 0:6) recognise hosts, symptoms, etc.) con- tents. Extraction obtains better 0:7). Conclusion – final objective linking media based official organisations improvement monitoring.