Unveiling the Potential of Learning Analytics in Game-Based Learning: Case Studies With a Geometry Game

Background

Technology is gradually being applied into our everyday life affecting many fundamental processes, including education. Accordingly, in recent years, we see a considerable change in the way of teaching and learning (Dabbagh et al., 2016). In this sense, a key transformative approach is gamification, which has been broadly defined as “the use of game design elements in non-game contexts” (Deterding, Dixon, Khaled, & Nacke, 2011), and is frequently implemented with these new technologies. There are multiple elements that are being implemented in this context, such as points, badges, levels, leader boards, virtual goods, avatars, or even whole games (Hamari, Koivisto, & Sarsa, 2014). We focus on this last item, since nowadays it is common to involve game-based learning (GBL) in order to motivate students, improve their knowledge and increase the enjoyment of such an essential process as education (Plass, Homer, & Kinzer, 2015). However, while there are obvious benefits, current educational systems are still suffering from numerous issues that require transformative changes. GBL holds the potential to improve many of the problems that are currently present within the educational process (De Freitas, 2006). One issue is that even though many teachers report a positive attitude towards games being used in K12 classrooms and believe that they can improve learning and curriculum, the actual number of teachers who are implementing digital games in their curriculum is contrarily low. There are several factors affecting the possibility of implementing games into as formative assessment, including the doubts on how to effectively implement games in the classroom, how to support evidence-based decisions based on game data, or how to assess students using the games (Watson & Yang, 2016).

Within the context of these challenges, we argue that learning analytics (LA) could be a vital novelty being able to address the problems as mentioned earlier. LA was defined in 2011 in the first Learning Analytics and Knowledge (LAK) conference as the “the measurement, collection, analysis and reporting of data about learners and their contexts, for purposes of understanding and optimising learning and the environments in which it occurs” (Society for Learning Analytics Research (SoLAR), 2021). While the work presented in this article focuses on the process for implementing LA, there are numerous other cross-cutting factors to consider during this process that are highly important for success. In the first place, it should be noted that the rise of research in LA has been given by the introduction of technology in education and that as it continues to be introduced more in the educational fabric (US Department of Education, 2016), we could expect a greater demand for implementing it. In turn, it could lead to greater ease in certain parts of introducing this process into education. Secondly, there is a need to highlight the need to anchor LA projects in real educational applications that can improve learning. However, there is a risk of implementing technology and analytics that are totally disconnected from the best pedagogical practices and educational theories developed in recent decades (Gašević, Dawson, & Siemens, 2015). Third, nowadays, people are more concerned about their privacy, and it is especially crucial to guarantee the privacy of students and teachers for the ethical development of this technology, which is a problem that has already been tackled by numerous policies (H. Drachsler & Kalz, 2016). On the other hand, it is a critical question whether educational systems want to move in the same direction as the large Internet companies, which continuously monitor their users (Slade & Prinsloo, 2013).