New Trends on Multimodal Learning Analytics: Using Sensors to Understand and Improve Learning

Dear Colleagues,

Educational environments are transforming with digital technologies. In the learning environments, the magistral class has been gradually abandoned, and the learners are changing from observers to the protagonists of their own learning. In this way, situations in which the learner produces unique solutions, interacts in groups, or must expose their ideas to their peers are challenging to assess and generate appropriate feedback [1]. Under that premise, the incorporation of sensors that allow capturing information of the transformations that occur inside educational settings together with them is essential for the continuous enhancement of educational processes.

Multimodal learning analytics (MMLA) is a subfield of learning analytics that deals with data collected and integrated from different sources, allowing a more panoramic understanding of the learning processes and the different dimensions related to learning [2]. MMLA allows the observation of interactions and nuances that are normally overlooked by traditional learning analytics methods, given that the latter frequently exclusively rely on computer-based data [3]. In this direction, introducing low-cost sensors allows access to information from learners’ interactions with each other and with their surroundings in physical space, which could not be possible with traditional log data only. A wide range of sensors have been used by MMLA experiments, ranging from those collecting students motoric (body, head) and physiological (heart, brain, skin) behavior, to those capturing social (proximity), situational, and environmental (location, noise) contexts in which learners are placed [4].

This Special Issue focuses on all kinds of sensors used for collecting data and conducting MMLA studies, as well as on the impacts of learning achieved through the use of those sensors.

The topics of interest include but are not limited to:

Wearable trackers;
Multimodal classroom analytics;
Real-time multimodal data collection;
Feedback from multimodal data provided by (and through) sensors;
Data collection, analysis methods, and frameworks for MMLA;
All kinds of learning experimentations based on multimodal data (collaboration, mobility/location, body postures, gestures, etc.) in different contexts (oral presentation, problem solving, lectures, etc.);
Multimodal data representation and visualization;
Challenges and limitations on processing and synchronizing data from multiple sources.

Prof. Dr. Roberto Muñoz
Prof. Dr. Cristian Cechinel
Dr. Mutlu Cukurova
Guest Editors

[1] Blikstein, P. Multimodal learning analytics. In Proceedings of the third international conference on learning analytics and knowledge, Leuven, Belgium, 8-12 April 2013, pp. 102-106.

[2] Blikstein, P.; Worsley, M. Multimodal Learning Analytics and Education Data Mining: Using Computational Technologies to Measure Complex Learning Tasks. J. Learn. Anal. 2016, 3, 220–238.

[3] Ochoa, X.; Lang, A.C.; Siemens, G. Multimodal learning analytics. In The Handbook of Learning Analytics. Society for Learning Analytics Research, 2017; pp. 129-141.

[4] Di Mitri, D.; Schneider, J.; Specht, M.; Drachsler, H. From signals to knowledge: A conceptual model for multimodal learning analytics. J. Comput. Assist. Learn. 2018, 34, 338–349.