Design of Self-Actualized Ad Recommendation Systems
Abstract
Traditional recommender systems trap users in filter bubbles, in an attempt to personalize the suggestions to users’ preferences, these systems can limit users’ perspectives and promote complacency. This paper takes a user-centered design approach towards creating a self-actualized ad recommendation system, that supports self-discovery, goal achievement, and seeking of relevant recommendations that encourage users’ self-actualization needs and go beyond algorithmic recommendations.
This paper has been withdrawn.