{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/global-disease-monitoring-and-forecasting","title":"Global disease monitoring and forecasting with Wikipedia","arxiv_id":"1405.3612","date":"2014-05-14","proceeding":null,"authors":["Nicholas Generous","Geoffrey Fairchild","Alina Deshpande","Sara Y. Del Valle","Reid Priedhorsky"],"abstract":"Infectious disease is a leading threat to public health, economic stability,\nand other key social structures. Efforts to mitigate these impacts depend on\naccurate and timely monitoring to measure the risk and progress of disease.\nTraditional, biologically-focused monitoring techniques are accurate but costly\nand slow; in response, new techniques based on social internet data such as\nsocial media and search queries are emerging. These efforts are promising, but\nimportant challenges in the areas of scientific peer review, breadth of\ndiseases and countries, and forecasting hamper their operational usefulness.\n  We examine a freely available, open data source for this use: access logs\nfrom the online encyclopedia Wikipedia. Using linear models, language as a\nproxy for location, and a systematic yet simple article selection procedure, we\ntested 14 location-disease combinations and demonstrate that these data\nfeasibly support an approach that overcomes these challenges. Specifically, our\nproof-of-concept yields models with $r^2$ up to 0.92, forecasting value up to\nthe 28 days tested, and several pairs of models similar enough to suggest that\ntransferring models from one location to another without re-training is\nfeasible.\n  Based on these preliminary results, we close with a research agenda designed\nto overcome these challenges and produce a disease monitoring and forecasting\nsystem that is significantly more effective, robust, and globally comprehensive\nthan the current state of the art.","url_abs":"http://arxiv.org/abs/1405.3612v2","url_pdf":"http://arxiv.org/pdf/1405.3612v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"global-disease-monitoring-and-forecasting","repo_url":"https://github.com/reidpr/quac","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}