PERSONALITYML: A MARKUP LANGUAGE TO STANDARDIZE THE USER PERSONALITY IN RECOMMENDER SYSTEMS

Abstract

In recent years the study of how human psychological aspects may improve the decision-making process in computers has became a new trend. This subject has attracted the attention from both academy and industry in areas such as human-computer interaction, computer in education, recommender systems and social matching systems, among others. However, one of the biggest problems faced by them is how effectively to use, model and implement those psychological aspects in computers. This paper comes to fill partly this gap by proposing a markup language to standardize the representation of personality. The PersonalityML proposes a set of recommender inputs to be used as starting data to classical cold-start problem in recommender systems, as well as, in personality-based recommender systems and others personality-based web applications.