Home // International Journal On Advances in Intelligent Systems, volume 9, numbers 3 and 4, 2016 // View article
Authors:
Christopher Krauss
Rakesh Chandru
Agathe Merceron
Troung-Sinh An
Miggi Zwicklbauer
Stefan Arbanowski
Keywords: Smart Learning; Forgetting; Learning Companion; Recommendation Engine; Learning Analytics
Abstract:
In digital learning environments, analysis of students' interactions with the learning objects provides important information about students' behavior. This can lead to a better understanding of the learning process and thus, optimizes teaching and learning. The aim of the ongoing research project "Smart Learning" is to introduce a novel mobile Learning Companion App in order to support a blended-learning approach in the training of Energy Consultants at the Chamber of Crafts Berlin, university lecturers as well as company internal summer schools. Thereby, students can keep track of their individual predicted knowledge level on different learning objects at every point in time and get personalized learning recommendations based on the expected learning progress. Moreover, teachers make use of learning analytics in order to get an overview of students' progress and so, be aware of possible weaknesses. The relevance of learning items change significantly over the period of a course - students may start with a low knowledge level, learn specific topics and afterwards slowly forget the lessons learned. Thus, learning environments require a new prediction paradigm for recommender systems: The relevance score of an item depends on different contextual factors. Especially forgetting plays a crucial role as people tend to forget lessons learned. Information stored in individual's memory is either erased or cannot be retrieved due to several reasons. This process is influenced by different parameters: external ones, such as the item's media type, difficulty level and so on, as well as the individual's memory strength. This paper introduces the main ideas of the overall system, its architecture, app design and mathematical concepts as well as a novel approach to include the effect of forgetting in a time-dependent recommender system that is specialized in the area of Technology Enhanced Learning.
Pages: 472 to 484
Copyright: Copyright (c) to authors, 2016. Used with permission.
Publication date: December 31, 2016
Published in: journal
ISSN: 1942-2679