Empirical Study on Personality Trait Classification by Food Related Preferences

摘要

Human personality is a combination of the behavior, emotion, motivation and thinking pattern and has great impact on a person's life, health, and other related preferences. Food preferences provide rich information for studying personality of a person. In this paper, we conduct an empirical study to predict human personality based on restaurant review on food and other related preferences. We choose the category to `judge/perceive' from the 4 categories of 16 personality traits. A data set is built from a survey of 100 people based on a questionnaire about their food related behavior along with standard personality traits. A classification algorithm is proposed to classify the participant's personality from his/her food preference and surrounding environment on a restaurant, using reinforcement learning that utilizes temporal difference, model based, and on policy techniques. We compare our proposed classification results with standard classification solutions for personality detection to determine the performance accuracy of our proposed model.