"Individualized learning in a course with a tight schedule"

Area of Science:

• Artificial Intelligence
• Educational Technology

Background:

• Traditional e-learning systems face challenges in time-constrained courses.
• Individualized learning requires adaptive content delivery mechanisms.
• Organizational hurdles in short-schedule courses necessitate specialized tools.

Purpose of the Study:

• To present a novel Intelligent Tutoring System (ITS) for personalized learning in accelerated academic programs.
• To enhance the adaptability and content relevance of e-learning platforms for students with immediate learning needs.

Main Methods:

• Development of an Intelligent Tutoring System (ITS) integrated with an e-learning content repository.
• Implementation of content modularization and logical division using the UCTS taxonomy.
• Content description using domain-specific concepts for accurate ITS selection.
• Deployment of the ITS for an 'Applications of Fuzzy Logic' course within an Artificial Intelligence program.

Main Results:

• The ITS successfully provided individualized content selection based on real-time student needs.
• Modularized and concept-tagged content facilitated flexible and relevant learning material delivery.
• The system proved effective even within the compressed timeframe of a COVID-19 impacted academic term.

Conclusions:

• The proposed ITS offers a flexible and effective solution for personalized e-learning in demanding, short-schedule courses.
• Dynamic content adaptation is crucial for optimizing learning outcomes in time-sensitive educational settings.
• The UCTS taxonomy and concept-based resource description enhance the ITS's ability to deliver targeted educational content.