Using machine learning for automatic identification of evidence-based health information on the web

Al-Jefri, Majed M, Evans, Roger, Ghezzi, Pietro and Uchyigit, Gulden (2017) Using machine learning for automatic identification of evidence-based health information on the web. Published in: Conference Proceedings of the 2017 International Conference on Digital Health; London, UK; 2-5 July 2017. 167-174. Association for Computing Machinery ISBN 9781450352499

[img] PDF - Accepted Version
Download (466kB)

Abstract

Automatic assessment of the quality of online health information is a need especially with the massive growth of online content. In this paper, we present an approach to assessing the quality of health webpages based on their content rather than on purely technical features, by applying machine learning techniques to the automatic identification of evidence-based health information. Several machine learning approaches were applied to learn classifiers using different combinations of features. Three datasets were used in this study for three different diseases, namely shingles, flu and migraine. The results obtained using the classifiers were promising in terms of precision and recall especially with diseases with few different pathogenic mechanisms.

Item Type: Conference Proceedings
Keywords: digital health, information quality, natural language processing, machine learning
Schools and Departments: Brighton and Sussex Medical School > Clinical and Experimental Medicine
Subjects: R Medicine > R Medicine (General) > R858 Computer applications to medicine. Medical informatics
R Medicine > RA Public aspects of medicine > RA0001 Medicine and the state. Including medical statistics, medical economics, provisions for medical care, medical sociology > RA0418 Medicine and society. Social medicine. Medical sociology
R Medicine > RA Public aspects of medicine > RA0418 Medicine and society. Social medicine. Medical sociology
Related URLs:
Depositing User: Pietro Ghezzi
Date Deposited: 08 Jun 2017 14:16
Last Modified: 05 Oct 2017 18:25
URI: http://sro.sussex.ac.uk/id/eprint/68420

View download statistics for this item

📧 Request an update