Article Preview
TopIntroduction
With the development of the internet, several approaches such as CSCL (Computer-Supported Collaborative Learning) have emerged, although these approaches have begun to revolutionize the field of education, many still struggle to provide an environment in which actor systems can interact and communicate with each other (Lafifi et al., 2010; Rojano-Cáceres et al., 2017). In fact, in the CSCL research field, researchers are mainly interested in the collaboration between learners as a means for supporting collaborative learning, which allows the learner to work with the group to achieve a common goal (Lafifi et al., 2012; Rojano-Cáceres et al., 2017). This is why Collaborative learning is an active part of distance learning and several researchers consider it as an environment where learners benefit from each other and collaborate to improve their knowledge and their profiles.
CSCL applies several strategies, one of the most important in environments being is the learners' grouping. This latter allows the learners to regulate their activities (Mehta et al., 2012). Learners should be assigned to an appropriate group that can maximize their learning (Ounnas et al., 2007) in the context of CSCL. The majority of CSCL systems neglect the aspect of group formation by grouping the learners randomly (Alfonseca et al., 2006). Recently, many types of research using several criteria for grouping learners: we can cite among these criteria: their profiles, personal information (e.g. age, gender, class) (Analoui et al., 2014), behaviors, and knowledge (Mujkanovic et al., 2012), learning styles (Zakrzewska, 2008; Grigoriadou et al., 2006). Other works group learners using their abilities (Henry, 2013) and their thinking styles (Wang et al., 2007).
Many techniques were used to group learners, Artificial intelligence and Bio-inspired techniques are among the most used techniques. In the context of bio-inspired techniques, Montazer and Rezaei (2012) have introduced an optimization approach in the e-learning field to improve the grouping methods. The authors propose a new method HCM (Hybrid Clustering Method) based on feedback from basic clustering methods such as C-means and K-means. According to Abnar et al. (2012) learning groups form by an iterative process based on a genetic algorithm. They were using another bio-inspired approach. Ghorbani and Montazer (2012) found that grouping learners by PSO (Particle Swarm Optimization) technique based on their cognitive styles improved the accuracy of grouping. In another approach, Lin et al. (2009) proposed a Genetic Algorithm (GA) to select some important learner's characteristics, and make an optimal classification through the SVM (Support Vector Machines) classifier. Zedadra et al. (2016) presented a new approach of learner grouping in collaborative learning systems. This grouping process is based on traces left by learners. The proposed approach consists of two main algorithms: (1) the circular grouping algorithm and (2) the dynamic grouping algorithm (used to update groups). The circular grouping is a novel algorithm to group learners based on their learning and collaborative traces. Its goal is to form heterogeneous groups based on their profiles. The dynamic grouping algorithm is based on the behavior of penguins when they are moving in the winter season to stay safe. The authors' proposed approach used the same behavior of a penguin colony. There are many papers on grouping learners and learner collaboration, however, collaboration between learners is not sufficient to solve some problems, because some learners have difficulty communicating and sharing their experiences when working in groups. Therefore, tutoring functionality is necessary for these environments. Tutoring is a key component of any distance learning system. Tutoring is a human activity, which has been applied in several areas. In the field of education, this task has become indispensable, especially in higher education institutions.