An Adaptive Learning System
Juan Rodriguez
New Jersey City University
Dr. Carnahan
August 3, 2020:
An Adaptive Learning System
Rationale
The critical element for the popularization of the adaptive education system is that it will enable the usage of the standardized models for information sharing and reuse of learning objects. It will include standardized data models, which will ensure the interoperability of services and content. In times of the increasing dynamic technology, lifelong learning is becoming a necessity. The requirements are satisfied by the typical learning method instituted, particularly the e-learning method (Vesin et al., 2018). The reason for such a move is that unlike the ideal class approach E-learning offers a chance to perform asynchronous lessons. E-learning is learning where students and educators are not bound to a particular time or place. Conversely, e-learning has some drawbacks as compared to the conventional type of learning. Some of them have low effectiveness of the education process because of the lack of straightforward contact and the incapacity to apply an individual approach to teach learners. Therefore, Adaptive e-learning systems intend to address such a problem.
Background
Over the years, the creation and modules delivery for adaptive learning system contents is becoming crucial during designing advanced platforms for e-learning. To be accepted, a learning process needs to develop teaching tools and putting them in an accessible place on websites as in conventional e-learning. For effectiveness in the teaching processes, inadequate learning materials are available through the internet (Khosravi et al., 2020). This steers the adaptive e-learning invasion. The understanding of materials needs to be tailor-made to several student attributes, including the specific objectives, knowledge, preferences, and the learning styles to enable appropriate educative strategies to be used (Colchester et al., 2017). The principal aim of asynchronous learning is the interest of these areas, and its popularity remains to advance.
The current state of the field
The present implementation of the adaptive learning systems differs in complexities (Marienko et al., 2020). The rudimentary system integrates a more direct rule-based architecture. The widespread usage of the rudimentary systems is reinforcing mathematics skills. For instance, a student is presented with a math quiz to solve. When correctly replied to, a more challenging question is demonstrated. Conversely, an incorrect answer during presentation makes it an easy problem or requires some additional instructions.
The more complex learning system changes the presentation of instructional requirements based on the evaluating of the users’ abilities to understand a concept. The adaptive learning system evaluates conceptual comprehension and integrates information-driven algorithms (Haldorai et al., 2019). For instance, a student studying the idea of uncertainty in physics is presented with many questions. The student answers are then compared to the responses of other students who used it to evaluate the conceptual understandings’ deficiencies. A student is then presented the learning materials with a focus on the knowledge points in which he or she feels deficient. A more comprehensive adaptive learning system will help adapt the student’s learning environment through several instructional objectives that reflect teaching approaches such as animation, case studies, and video. Notably, the student’s learning path will be guided by the performance and the inference of the preferred style of learning (Rodríguez et al., 2018).
The technicality execution of the adaptive learning systems is viewed to be diverse; however shares a standard model constituting three models, namely, adaptation model, domain model, and the student model (Stepanova et al., 2018). The student model represents the relevant student attributes, including cognitive traits, personal information, and educative likings. The omnipresent student model defines the parameters through which instructional adaptations happen and is liable to obtain and maintain a precise representation of student’s attributes. A static ideal initializes the students’ characteristics after a dynamic model continually updates the students’ values. The student’s attributes are obtained via means such as students’ questionnaires and assessment instruments or even through tracking students’ interaction with the system. A robust student model integrates the various attributes of learning, offers diagnosis mechanisms, and infers the students’ characteristics and also gives tools used to assess students’ performance.
Assessment Plan
Students will be assigned various collaborative exercises through an adaptive learning product that will be developed. This learning system will comprise a set of questions for different formats such as multiple-choice, fill in the blank spaces, and matching. The arrangements and questions will be the same as the products.
In this adaptive learning product that will be adopted, questions will be classified by content in learning units. The particular concept or vocabularies will be the examples of the learning units. Multiple questions will be related to every teaching. The adaptive learning exercise will comprise a compiling of learning units. In the adaptive learning product, learners will be presented with a quiz and asked to show confidence in their success to answer questions.
They will be provided with four alternatives: I know, Think so, Unsure, and No idea. Students are allowed to answer the quiz. A student’s answer of “No idea” or “Give up” results in the display of the right response; however, the learning unit will be incomplete. A student can choose to respond to a quiz, immediate feedback will be given, and the right answer is determined, despite the student’s response. The closure of a learning unit will be determined based on two factors: the right answers and the student’s degree of confidence in responding to the presented questions. A wrong response will prevent a unit marked complete and more quizzes associated with the teaching unit will be presented to the student at a later time (Ennouamani et al., 2017).
The follow-on queries will be randomly interjected as the student progresses in practice. In most instances, the confidence sign of a learning unit hinders the learning unit from being marked as done. For example, correct answers will lead to the teaching unit completion despite the assurance level shown by a learner. The precise set of solution which triggers the end of a unit is exclusive to the adaptive learning item. The learner’s progress will be grounded on the units done, and the results will be recorded as the unit percentages completed before the assignment deadline.
Conclusion
This is a presentation of an exciting proposition for education technology in the current times. Notably, advancement will continue hence a note of caution which needs to be active states that pedagogy as compared to technology will drive the emergence of the advanced learning systems (Phelps, 2020). Therefore, more studies from the standpoint for the learning systems to act as informing systems will be needed before the advanced learning systems to be accepted.
References
Colchester, K., Hagras, H., Alghazzawi, D., & Aldabbagh, G. (2017). A survey of artificial intelligence techniques employed for adaptive educational systems within e-learning platforms. Journal of Artificial Intelligence and Soft Computing Research, 7(1), 47-64.
Ennouamani, Soukaina & Mahani, Zouhir. (2017). An overview of adaptive e-learning systems. 342-347. 10.1109/INTELCIS.2017.8260060.
Haldorai, A., Ramu, A., & Murugan, S. (2019). Machine Learning and Big Data for Smart Generation. In Computing and Communication Systems in Urban Development (pp. 185-203). Springer, Cham.
Khosravi, H., Sadiq, S., & Gasevic, D. (2020, February). Development and adoption of an adaptive learning system: Reflections and lessons learned. In Proceedings of the 51st ACM Technical Symposium on Computer Science Education (pp. 58-64).
Marienko, M., Nosenko, Y., Sukhikh, A., Tataurov, V., & Shyshkina, M. (2020). Personalization of learning through adaptive technologies in the context of sustainable development of teachers education. arXiv preprint arXiv:2006.05810.
Rodríguez, S., Palomino, C. G., Chamoso, P., Silveira, R. A., & Corchado, J. M. (2018, August). How to create an adaptive learning environment by means of virtual organizations. In International Workshop on Learning Technology for Education in Cloud (pp. 199-212). Springer, Cham.
Stepanova, G. A., Tashcheva, A. I., Stepanova, O. P., Menshikov, P. V., Kassymova, G. К., Arpentieva, M. R., & Tokar, O. V. (2018). The problem of management and implementation of innovative models of network interaction in inclusive education of persons with disabilities. International journal of education and information technologies. ISSN, 2074-1316.
Vesin, B., Mangaroska, K., & Giannakos, M. (2018). Learning in smart environments: user-centered design and analytics of an adaptive learning system. Smart Learning Environments, 5(1), 24.