Literature review
Artificial intelligence and machine learning have gained massive popularity in education, especially due to their ability to result in better academic performance and student outcomes. Academic scheduling is a key area that AI-based systems can significantly impact, as these systems have the ability to analyze schedules of students on the basis of their interests and preferences and assist them in making decisions that are better informed in regard to their academic schedule, enabling them to perform better in their academics. The literature review will analyze the research studies which have been conducted under this research domain to help in understanding the current state of knowledge on this approach and the possible research gaps that exist within this field.
History and Development of Academic Scheduling
In past years the task of scheduling courses has been a significant challenge to academic institutions, a this is a complex process. Conventionally the process of scheduling courses involves manually processing the various course-related information, which is tedious and very time-consuming; this is because, during the scheduling process, the institutions must consider several factors, including the availability of faculty, prerequisites of courses, student demand, and availability of the courses. Recently academic institutions have employed technology to assist with the automation of the scheduling process, and AI-based scheduling systems are among the latest advancements in this field.
AI-based machine learning in education
Artificial intelligence and machine learning are technologies that have been employed in different areas in the field of education; these technologies have made major advancements in the area of adaptive learning, personalized tutoring, and analysis of student performance (Luan & Tsai, 2021). The list of applications has increased in size with the addition of AI-based scheduling systems, and these systems leverage the capability of machine learning techniques to examine data obtained from past semesters; these data include student enrollment data, courses provided, and performance of students to produce personalized recommendations to the students according to each individual’s interests and preferences (Rahman et al., 2020).
Effectiveness of personalized course suggestions
There are many research studies that have been conducted to assess the effectiveness of personalized course recommendations in enhancing the academic performance of students. Fan et al. (2020) carried out a study, and the findings of the study revealed that personalized course suggestions enhanced the performance of the students by 13% compared to non-personalized systems. Further, the study identified that the personalized system significantly impacted the engagement of students and motivation. A similar study carried out by Zhang et al. (2018) discovered that a personalized course recommendation system resulted in significant improvements in the performance of students by up to 12% compared to a no-personalized system. In addition, the study also identified the increase in satisfaction among students and the reduced rate of dropout among students.
Challenges and limitations in the implementation of AI-based scheduling systems
Even though these AI-based scheduling systems are associated with enhanced academic scheduling and increased performance among students, they are also associated with numerous challenges and limitations related to their implementation. According to Roh et al. (2019), Data collection and cleansing is one of the key challenges that affect the implementation of these systems, and making sure that data obtained is clean, accurate, and up to date is very crucial so as to guarantee its quality and reliability before being utilized in the training of the machine learning techniques. In addition, data privacy and ethical considerations are other challenges that affect the implementation of these systems, and steps should be taken to guarantee the privacy and confidentiality of data by ensuring data anonymity and protection from being accessed by unauthorized individuals (Gupta et al., 2020).
Achieving a learning model that is effective in accurately analyzing the schedule of the students is another major challenge, and this process requires careful and informed selection of machine learning techniques that are appropriate, optimization of the parameters of the model, and model validation performance metrics which are appropriate (Bird et al., 2020). Continuous evaluation and maintenance of the systems are also crucial in ensuring that the system remains effective and relevant throughout its use.
Research gaps
Even though there have been several research studies carried out to gain a comprehensive understanding of AI-based scheduling systems in the field of education, there are still several areas that have not been thoroughly researched. One key area that still requires further research is the effects of personalized course suggestions on the motivation of students and their engagement. While the reviewed studies have illustrated the potential of personalized course recommendations to enhance the engagement and motivation of students, further research is still required to better comprehend how the systems can be optimally designed to realize maximum benefit.
The other potential area for further research is the ethical and social consequences that are associated with the use of these AI-based scheduling systems in the field of education. There are significant issues that are associated with these systems to further enhance inequalities and biases within the academic system; this issue requires additional research to better comprehend how better these systems can be designed and implemented in a way that adheres to ethical requirements ensuring that they do not further portray existing biases or perpetuate discrimination against specific groups of students. In addition, there is also a need to carry out research to comprehend how AI-based system-based scheduling can be integrated with other educational technologies creating a more comprehensive and effective learning environment.
In summary, an analysis of past research studies on AI-based scheduling systems has revealed that they can potentially revolutionize the education sector by improving how students schedule their courses and improve their performance; these systems operate by leveraging machine learning techniques to analyze historical data and produce personalized suggestions to students taking into consideration their interests and preferences. The studies have identified that these systems are associated it significant improvements in the performance and engagement of students. However, some of these studies have also identified several limitations and challenges associated with the implementation of these systems. In addition, the analysis has revealed several research gaps which should be addressed to make sure that the full potential of this system is realized. Implementation of these systems should be done in an ethical and responsible manner, also ensuring integration with other educational technologies and creating a learning environment that is more comprehensive.
Potential challenges in the research
Data privacy and security is a key potential issue in the research as AI-based scheduling systems operate by collecting and analyzing sensitive student information. The issue can be solved through secure data collection and storage and adhering to regulations pertaining to data protection and privacy.
Technical challenges are the second potential challenge, as significant technical expertise is required for developing and implementing these systems. The challenge can be solved through collaboration with experts in the field of AI and educational technology in the development and implementation of the systems.
Finally, ethical and legal consideration is another potential challenge; these systems gives rise to numerous ethical a legal concern which includes transparency, accountability, and fairness. The challenge can be solved by ensuring that the development and implementation of the system are done in a way that is responsible and ethical.
References
Bird, S., Dudík, M., Edgar, R., Horn, B., Lutz, R., Milan, V., … & Walker, K. (2020). Fairlearn: A toolkit for assessing and improving fairness in AI. Microsoft, Tech. Rep. MSR-TR-2020-32.
Fan, J., Jiang, Y., Liu, Y., & Zhou, Y. (2022). Interpretable MOOC recommendation: a multi-attention network for personalized learning behavior analysis. Internet Research, 32(2), 588-605.
Gupta, R., Tanwar, S., Al-Turjman, F., Italiya, P., Nauman, A., & Kim, S. W. (2020). Smart contract privacy protection using AI in cyber-physical systems: tools, techniques and challenges. IEEE Access, 8, 24746–24772.
Luan, H., & Tsai, C. C. (2021). A review of using machine learning approaches for precision education. Educational Technology & Society, 24(1), 250-266.
Rahman, M. M., Noor, S. B., & Siddiqui, F. H. (2020, December). Automated Large-scale Class Scheduling in MiniZinc. In 2020 2nd International Conference on Sustainable Technologies for Industry 4.0 (STI) (pp. 1–6). IEEE.
Roh, Y., Heo, G., & Whang, S. E. (2019). A survey on data collection for machine learning: a big data-ai integration perspective. IEEE Transactions on Knowledge and Data Engineering, 33(4), 1328–1347. Zhang, H., Huang, T., Lv, Z., Liu, S., & Zhou, Z. (2018). MCRS: A course recommendation system for MOOCs. Multimedia Tools and Applications, 77, 7051–7069.
write