THE WORKSHOP MOTIVATION

=================================================================

The use of teaching through computer tools (e-learning) started to widespread in the beginning of the 2000’s as a complementary resource to classroom education. Researchers/educators started to think about personalization in such environments, then discovered that “one-size-fits-all” solutions are not effective to foster learning. Different students should receive different resources that should be adapted to their profiles. Since the beginning of the confinement, due COVID pandemic, the e-learning is no longer used as only a complementary resource but has become the only possible way to teach. This sudden changing of teaching paradigm has generated a huge amount of digital learning resources but not always providing the proper tools to handle such resources. A learning-path (an ordered sequence of learning resources to achieve a specific learning goal) created by the educator is one of the ways to guide the students through the overwhelmingly number of resources available on the internet. Such construction of learning paths aims to avoid the students’ cognitive overload, lack of motivation, and consequently dropout. However, such learning-paths generated by educators are also limited by the educators’ capability to analyze a large amount of available learning resources. The construction of individual learning-paths that take in consideration each student's learning style, background, and preferences during the selection of resources seems like an impossible task to be executed by a human educator. We then propose this 1st International Workshop of Learning Path Recommendation Systems (LPRS) to receive and discuss papers that provide a way to guide the students in e-learning scenarios. The workshop will be held fully online within the UMAP conference.

TOPICS OF INTEREST

=================================================================

 Sorne topics of interest of the workshop are (but not limited to):

• Modeling of Learning Paths

• Modeling of Users’ Profiles to LPRS

• Modeling of Users’ Profiles to Sequential Recommendation

• New Approaches to LPRS

• New Techniques to Guide Students in E-learning Scenarios

• Learning Analytics to Guide Students Through Learning Resources

• New Approaches to Sequential Recommendations

• Adaptive Approaches to Handle E-learning Resources

• Explicable and Trustworthy LPRS

• LPRS that Looks Beyond the Accuracy

• LPRS Covering Multiple Sources and Types of Resources

• Modeling of Massive Amount of Educational Resources

• Use of Big Data in LPRS

• Privacy and Ethics in LPRS

• HCI Factors in LPRS

• LPRS to Support Disadvantaged Schools and Students

• Domain-specific LPRS

• Evaluation of LPRS

• Real World Applications of LPRS