Preclude: Conflict detection in textual health advice
Authors:
- 1 March 2017
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 286-296
Abstract
With the rapid digitalization of the health sector, people often turn to mobile apps and online health websites for health advice. Health advice generated from different sources can be conflicting as they address different aspects of health (e.g., weight loss, diet, disease) or as they are unaware of the context of a user (e.g., age, gender, physiological condition). Conflicts can occur due to lexical features, (such as, negation, antonyms, or numerical mismatch) or can be conditioned upon time and/or physiological status. We formulate the problem of finding conflicting health advice and develop a comprehensive taxonomy of conflicts. While a similar research area in the natural language processing domain explores the problem of textual contradiction identification, finding conflicts in health advice poses its own unique lexical and semantic challenges. These include large structural variation between text and hypothesis pairs, finding conceptual overlap between pairs of advice, and inference of the semantics of an advice (i.e., what to do, why and how). Hence, we develop Preclude, a novel semantic rule-based solution to detect conflicting health advice derived from heterogeneous sources utilizing linguistic rules and external knowledge bases. As our solution is interpretable and comprehensive, it can guide users towards conflict resolution too. We evaluate Preclude using 1156 real advice statements covering 8 important health topics that are collected from smart phone health apps and popular health websites. Preclude results in 90% accuracy and outperforms the accuracy and F1 score of the baseline approach by about 1.5 times and 3 times, respectively.Keywords
This publication has 23 references indexed in Scilit:
- Rapid evidence-based development of mobile medical IoT apps2016
- EyePhy: Detecting Dependencies in Cyber-Physical System Apps due to Human-in-the-LoopEAI Endorsed Transactions on e-Learning, 2015
- Validating Contradiction in Texts Using Online Co-Mention Pattern CheckingACM Transactions on Asian Language Information Processing, 2012
- Your mobility can be injurious to your health: Analyzing pervasive health monitoring systems under dynamic context changes2012
- HumMod: A Modeling Environment for the Simulation of Integrative Human PhysiologyFrontiers in Physiology, 2011
- The pathophysiology of medication errors: how and where they ariseBritish Journal of Clinical Pharmacology, 2009
- Impact of Web Searching and Social Feedback on Consumer Decision Making: A Prospective Online ExperimentJournal of Medical Internet Research, 2008
- Health literacy and knowledge of chronic diseasePatient Education and Counseling, 2003
- Patients’ use of the internet for medical informationJournal of General Internal Medicine, 2002
- Measuring nominal scale agreement among many raters.Psychological Bulletin, 1971