Abstract:

Traditional lectures where the author mostly reads prepared materials with limited opportunity for interaction are not effective and most of the time does not lead towards higher quality learning processes. These legacy (deprecated) teaching approaches are mostly boring for the lecturers and motivation depriving for recipients.

Active learning however is an approach that involves actively engaging students with the course material through discussions, problem solving, case studies, role plays and other methods. These student centric teaching approaches place a greater degree of responsibility on the learner than passive approaches such as traditional lectures. Though instructor guidance is still crucial in the active learning environment. Active learning and collaborative activities may range in length from a couple of minutes to whole sessions or may take place over multiple interactions [1].

Knowledge discovery in the active learning ecosystem can be addressed by collecting and analyzing data from within the given environment. The learning feedback data collected can be used to better understand the audience, gain insights and to foster active feedback back to students. Obtained knowledge can be applied in a way that creates room for improvement in the active and collaborative work. Aforementioned approach is being developed and approbated as a part of a larger project in Vidzeme University of Applied Sciences.

One of the technologies that can assist in knowledge discovery is machine learning as it provides potential to obtain insights into previously overlooked data [2]. This paper focuses on how to apply machine learning for active learning support as a part of a larger meta-framework [3]. Active learning ecosystem supportive knowledge discovery framework is introduced for Teaching Support.

References:
[1] Queensu.ca. 2020. What Is Active Learning. [online] Available at: <https://www.queensu.ca/teachingandlearning/modules/active/04_what_is_active_learning.html> [Accessed 12 July 2020].
[2] Jansevskis, M., Osis, K., Knowledge discovery and framework for purchase behavior analysis in mobile gaming applications. 5th International Conference on Big Data Analytics, Data Mining and Computational Intelligence, Zagreb, Croatia, July 2020 (submitted).
[3] Jansevskis, M. and Osis, K., 2018. Machine Learning and on 5G Based Technologies Create New Opportunities to Gain Knowledge. 2018 2nd European Conference on Electrical Engineering and Computer Science (EECS).

Keywords:

Machine Learning, Knowledge Discovery, Active Learning Ecosystem, Learning Feedback Data, Student Centric Teaching, Teaching support.