The users’ perspective on the privacy-utility trade-offs in health recommender systems

摘要: Abstract Privacy is a major good for users of personalized services such as recommender systems. When applied to the field health informatics, privacy concerns may be amplified, but possible utility also high. Despite availability technologies k-anonymity, differential privacy, privacy-aware recommendation, and trade-offs, little research has been conducted on users’ willingness share data usage in In two conjoint-decision studies (sample size n = 521 ), we investigate importance privacy-preserving techniques related sharing personal k-anonymity privacy. Users were asked pick preferred scenario depending recipient data, benefit type parameterized disagreed with commercial purposes regarding mental illnesses high de-anonymization risks showed concern when used scientific physical illnesses. Suggestions system development are derived from findings.