Multifactorial user models for personalized mobile-assisted language learning
Troussas Christos, Maria K. Virvou, Alepis Efthimios · Frontiers in artificial intelligence and applications · 2014
In this paper, we present our multilingual mobile-assisted language learning system which incorporates multifactorial clustering. This means that it provides machine learning techniques for clustering of multiple user characteristics. Multifactorial classification is conducted by the k-means clustering algorithm which takes as input seven important users' characteristics in order to initialize the process. The clustering is conducted by k-means clustering algorithm, which takes as input multiple user characteristics, in order to initialize the process. The aforementioned characteristics tend to influence the educational procedure. K-means algorithm creates clusters based on data from empirical studies. After determining in which cluster each new student belongs, the system can reason about this specific student, adapting its behavior to the user's needs. The resulting adaptation emerges from the analysis of each cluster's characteristics that derive from each cluster as a superset of already existing user models. The communication between the system and its potential users as students is accomplished through the use of web services.