User interface adaptation based on user feedback and machine learning

Abstract

With the growing need for intelligent software, exploring the potential of Machine Learning (ML) algorithms for User Interface (UI) adaptation becomes an ultimate requirement. The work reported in this paper aims at enhancing the UI interaction by using a Rule Management Engine (RME) in order to handle a training phase for personalization. This phase is intended to teach to the system novel adaptation strategies based on the end-user feedback concerning his interaction (history, preferences...). The goal is also to ensure an adaptation learning by capitalizing on the user feedbacks via a promoting/demoting technique, and then to employ it later in different levels of the UI development.