2017/03/11 by Paolo Missier, Missier, Paolo, Callum McClean +13
Computer Science · Physics and Astronomy · Social Sciences · #Complex Network Analysis Techniques #FOS: Computer and information sciences #ICT in Developing Communities #Machine Learning (cs.LG) #Social Media and Politics #Social and Information Networks (cs.SI)
paper · pdf · doi:10.48550/arxiv.1703.03928
openalex publication_date 2017/03/11 · openalex created_date 2022/09/08 · openalex updated_date 2026/07/28
Tropical diseases like \Chikungunya and \Zika have come to\nprominence in recent years as the cause of serious, long-lasting,\npopulation-wide health problems. In large countries like Brasil, traditional\ndisease prevention programs led by health authorities have not been\nparticularly effective. We explore the hypothesis that monitoring and analysis\nof social media content streams may effectively complement such efforts.\nSpecifically, we aim to identify selected members of the public who are likely\nto be sensitive to virus combat initiatives that are organised in local\ncommunities. Focusing on Twitter and on the topic of Zika, our approach\ninvolves (i) training a classifier to select topic-relevant tweets from the\nTwitter feed, and (ii) discovering the top users who are actively posting\nrelevant content about the topic. We may then recommend these users as the\nprime candidates for direct engagement within their community. In this short\npaper we describe our analytical approach and prototype architecture, discuss\nthe challenges of dealing with noisy and sparse signal, and present encouraging\npreliminary results.\n