Enabling remote learning system for virtual personalized preferences during COVID-19 pandemic.

Area of Science:

• Education Technology
• Online Learning Systems
• Pandemic Response

Background:

• The COVID-19 pandemic significantly disrupted global education, halting traditional learning and assessments.
• E-learning platforms emerged as crucial tools, but challenges remain in resource selection for diverse users, especially in developing nations.
• Internet technology unfamiliarity and the need for effective virtual learning environments pose significant obstacles.

Purpose of the Study:

• To propose an intelligent mechanism for predicting user preferences in online learning resource selection.
• To enhance the effectiveness of E-learning platforms and remote work policies during the pandemic.
• To support teachers in delivering quality online education and familiarize users with advanced online technologies.

Main Methods:

• Development of a novel mechanism for intelligent and accurate prediction of user preferences for online learning resources.
• Consideration of diverse user capabilities and requirements for personalized resource allocation.
• Semantic prediction of virtual assistance preferences for users needing to learn new online tools.

Main Results:

• The proposed virtual personalized preferences system demonstrated significant improvements in overall academic activities compared to existing methods.
• Enhanced user learning abilities and facilitated the selection of relevant short courses.
• Improved the adoption and effectiveness of online education tools for classes, seminars, and webinars.

Conclusions:

• The developed system effectively addresses challenges in online resource selection for diverse learners.
• It contributes to more effective and progressive online education delivery, supporting both students and educators.
• The system enhances the quality and accessibility of education in a remote learning environment.