Choice-Based User Interface Design of a Smart Healthy Food Recommender System for Nudging Eating Behavior of Older Adult Patients with Newly Diagnosed Type II Diabetes

Information Retrieval (IR) and Recommender System (RS) has its potential to assist patients to make an informed decision on healthy food and influence their food choices which inferring the chance of nudging dietary behavior. However, the potential users of the system, older adult patients, is a unique group of people with heterogeneity of the computer proficiency and the latency of technology acceptance. In this context, the effective User Interface (UI) design of such a personal health decision support system for older adults remains undetermined. To fill in the research gap, a choice-based UI of healthy food recommender system for older adults was proposed based on the literature review of ageing-centered design principles. A further user testing study was conducted to systematically examine the effectiveness of the critical UI design variables, search result layouts and nutrition information formats, in a 2 × 2 full factorial experiment. Fifteen older adults aged 60 years and older (mean = 66.8) were recruited to participate a scenario-based evaluation of the proposed prototype system, another fifteen college students between the ages of 20–35 (mean = 28.6) were recruited as the control group of the study. The results are collected by both quantitative data of subjective questionnaires and qualitative data of the transcriptions from interview and think aloud notes. This article presented and discussed the results of older adults’ perceptions of the system collected by mixed methods in comparison to the student groups.