A Rule-Based Adaptive Mobile Application to Learn Android in a Personalized Learning Environment

Abstract

Learners are different; they have different learning styles, different prior knowledge, different learning preferences, and different learning rates. Still, in current teaching methods, students learn the same content, the same way, and at the same rate. This pedagogical perspective in learning has attracted researchers and professionals for years to describe how learning occurs and whether the findings can be theorized. These methods do not provide the most effective learning experience as it is more teacher oriented than student oriented. The lack of personal approach and immediate personal feedback result in a “one size fit all” paradigm of learning. Moreover, with modern mobile devices which are owned by most students, learning could easily be extended outside the classroom as smartphones remove all the time and distance barriers previously attached to learning. This research presents a novel rule-based adaptive mobile application to learn Android in a personalized learning environment. The mobile application was developed using Android Studio and Google’s Firebase as cloud infrastructure to provide an easy way of representing data through the JSON database while ensuring smooth performance and high bandwidth. The adaptive feature of the system was achieved through a custom inference engine that was used with forward chaining for knowledge propagation. Factors considered for content adaptation include learning style, current knowledge, learner responses, and weaknesses. The results obtained were very promising and demonstrated that the proposed system dynamically adapts to the learner’s needs while he/she is learning and makes the learning process more engaging and effective.