Managing Learning
14 Smart Learning Management Systems
Manuel Gentile and Giuseppe Città
E-learning and Learning Management Systems (LMS)
Thenumber of people making use of e-learning is constantly growing. The term e-learning refers to learning mediated by the use of technology in contexts where educators and learners are distant in space and/or time. The ultimate aim of e-learning is to improve students’ learning experience and practice.
Today,with the advancement of technology, it is more appropriate to refer to systems and platforms for the ‘delivery’ of e-learning rather than to single -purpose tools. Such systems are the result of integrating different software tools capable of building an ecosystem where flexible and adaptable learning paths can be exploited. An e-learning system enables the management of learning processes and the management of courses. It enables student-learning assessments, constructing reports, and creating and organising content. It facilitates communication between teachers/tutors and students. Among the most widely used e-learning systems, there are Learning Management Systems (LMS) (eg Moodle, Edmodo).
The acronym LMS refers to a web-based application designed to manage the learning process of trainees1 at different levels, in different ways and domains. An LMS, therefore, could be defined as a learning environment within which learning, content and assessment activities and tools are implemented. Student-student and/or student-educator interactions likewise are implemented and managed within this environment. Furthermore, the definition of LMSs includes their being platforms that generally can include whole course management systems, content management systems, and portals2.
LMS and AI: the Smart LMS
With the advent of AI, Education, in general, and LMSs, in particular, become possible and promising fields of application of this revolutionary force3. Specifically, LMSs, thanks to the functionalities supported by AI, represent a renewed learning tool capable of satisfying two of the fundamental traits of the education of the future: personalisation and adaptation4. It is from this combination of LMS and AI that the Smart LMS (SLMS) or Intelligent LMS emerges.
An efficient SLMS features algorithms that can provide and retrieve information from three fundamental clusters of knowledge: a) the learner b) the pedagogy and c) the domain. By acquiring information about (a) learners’ preferences, their emotional and cognitive states and their achievements and goals, an SLMS can implement those teaching strategies (b) that are most effective (specific types of assessment, collaborative learning, etc.) for learning to be most fruitful within the specific domain of knowledge being studied (c): eg geometry theorems, mathematical operations, laws of physics, text analysis procedures4.
An SLMS, therefore, can be defined as a learning system capable of adapting the contents proposed to the learner by calibrating them to the knowledge and skills the learner has displayed in previous tasks. In fact, by adopting a learner-centred approach, it can identify, follow and monitor learners’ paths by recording their learning patterns and styles. Referring to the description given by Fardinpour et al.5, an intelligent LMS provides the learner with the most effective learning path and the most appropriate learning content, through automation, the adaptation of different teaching strategies (scaffolding), and the reporting and knowledge generation. It also provides the learners with the possibility to keep track of and monitor their learning and learning goals. Furthermore, although these features and tools enable the LMS to operate more intelligently, an SLMS must provide learners with the possibility to disable the AI that manages their path, in order to have full access to all learning materials in the learning environment.
Some examples of AI-supported functionalities in the context of an SLMS
When an SLMS is functioning correctly, several AI-supported tools make it possible to realise a system with the features described above. Such AI-supported tools move transversally along the three aforementioned clusters of knowledge, to which the SLMS algorithms constantly refer (learner, pedagogy, domain).
AI-supported chatbots as virtual tutors
A chatbot is software that simulates and processes human conversations (written or spoken). In the context of an SLMS, it can function as a virtual tutor, capable of answering a learner’s questions concerning, for example, learning courses. The chatbot is also capable of providing suggestions to the learner, based on the analysis that the system makes of the learner’s previous performances and interactions6.
Learning Analytics
Learning Analytics – data relating to the details of individual learner interactions in online learning activities – allow teachers to monitor learner progress and performance in depth. Thanks to them, the system can implement automatic computer-assisted educational task activation7 to supplement the activities of learners who have shown performance deficits in specific tasks. In addition, it can automatically provide suggestions to teaching staff regarding the difficulty of proposed tasks or the need to supplement them with additional learning content.
Benefits for learners and teachers
These and other AI-supported tools4 contribute to making an SLMS a powerful learning and teaching tool that, instead of being perceived as a substitute for the teacher’s work, shows itself as a tool capable of “augmenting” the human aspects of teaching8 and bringing a series of fundamental benefits to the whole learning/teaching process.
Since an SLMS calibrates the contents to the student’s skills and level, it avoids the learner, in the different phases of his or her path, facing tasks that bore him or her because they are too simple, or that frustrate him or her because they are too complex. This ensures that the student’s motivation and attention are always at a high level and appropriate to the level of difficulty of the task to be addressed. This situation has the direct consequence of significantly reducing the dropout rate, as it allows teachers to detect any problems in time and intervene promptly, as soon as the student shows the first signs of difficulty.
Such a situation, as well as linear learning situations (without difficulties), can be addressed by proposing to the students, through the SLMS tools, different knowledge contents that are already stored in the course databases or are from third-party providers. This results in a direct benefit for the teacher, who does not have to create new teaching materials from time to time, and can use the saved time in other essential occupations such as refining their teaching methods and/or interacting directly with the students.
1 Kasim, N. N. M., and Khalid, F., Choosing the right learning management system (LMS) for the higher education institution context: A systematic review, International Journal of Emerging Technologies in Learning, 11(6), 2016.
2 Coates, H., James, R., & Baldwin, G., A critical examination of the effects of learning management systems on university teaching and learning, Tertiary education and management, 11(1), 19-36, 2005.
3 Beck, J., Sternm, M., & Haugsjaa, E., Applications of AI in Education, Crossroads, 3(1), 11–15. doi:10.1145/332148.332153, 1996.
4 Rerhaye, L., Altun, D., Krauss, C., & Müller, C., Evaluation Methods for an AI-Supported Learning Management System: Quantifying and Qualifying Added Values for Teaching and Learning, International Conference on Human-Computer Interaction (pp. 394-411). Springer, Cham, July 2021.
5 Fardinpour, A., Pedram, M. M., & Burkle, M., Intelligent learning management systems: Definition, features and measurement of intelligence, International Journal of Distance Education Technologies (IJDET), 12(4), 19-31, 2014.
6 HR Technologist: Emerging Trends for AI in Learning Management Systems, 2019, Accessed 31 Oct 2022.
7 Krauss, C., Salzmann, A., & Merceron, A., Branched Learning Paths for the Recommendation of Personalized Sequences of Course Items, DeLFI Workshops, September 2018.
8 Mavrikis, M., & Holmes, W., Intelligent learning environments: Design, usage and analytics for future schools, Shaping future schools with digital technology, 57-73, 2019.