摘要：This study compares the characteristics of a self-report questionnaire (SRQ) and eye tracking (ET) based on a simple human–beverage visual cognition model. The young participants were mainly defined by their gender and body mass index (BMI). The beverage samples consisted of milk, coffee, cup, and coaster. SRQs allow the participants to clearly express their overall cognition of the samples in the form of vocabulary, while ET captures their hidden thinking process. The analysis, using a random forest (RF) classifier, found that participant parameters (gender and BMI) played a more important role for SRQ, while ET was related to beverage parameters (color and shape). This work reiterates that these two methods have their advantages and complement each other in food sensory analysis.
