Transcript Adaptive learning paths for improving Lifelong learning

Adaptive learning paths
for improving Lifelong
Learning experiences
Ana Elena Guerrero Roldán, Julià Minguillón
Universitat Oberta de Catalunya (UOC)
Manchester, 2007
Contents
Motivation and goals
Open University of Catalonia environment
Ateneu courses and Data Mining subject
Adaptive learning paths
Conclusions
Current and future research
Manchester, 2007
Motivation and Goals
Motivation: To improve lifelong learning experiences in UOC’s
virtual learning environment, focusing on competences
Main goal: To design adaptive learning paths for developing
competences using a case study (Data Mining)
Specific goals:
- To identify the main competences of a Data Mining course,
and recognize the student professional experience
-
To design adaptive learning paths for improving lifelong
learning experiences, integrating them into the official
courses
-
To evolve towards a competence based learning design
Manchester, 2007
Open University of Catalonia
•
•
•
•
Virtual university was created in 1995 with a user-centered
pedagogical model
19 official degrees, masters, Ph.D and Ateneu courses
35.000 students with different profile than traditional
university students
Under a major evolution process:
 Adaptation to the Bologna process
 Towards a lifelong learning model
 Integration of e-learning standards (SCORM, IMS LD)
Manchester, 2007
Ateneu courses
•
Our lifelong learning scenario is called Ateneu courses
•
Courses are selected from subjects offered as part of the
official degrees
•
They are oriented towards lifelong learning students who
want to improve their knowledge and professional
competences
•
Virtual classrooms (and learning environment) are the same
for all students (official and Ateneu)
•
Students enroll into Ateneu courses without any university
access prerequisite → large diversity of student profiles
Manchester, 2007
Data Mining course (I)
•
Data mining is one of Ateneu courses, such as history,
languages or economics (Lifelong Learning courses)
•
Available as an optional course in the Computer Science
degree and free choice in other degree programs, even for
other universities → diversity of student profiles
•
Students choose this subject for the real possibilities of
immediately applying the acquired competences
•
28% of students wanted to improve in the exercise of their
professions
Manchester, 2007
Data Mining course(II)
•
The course aims to provide an introduction to the basic
principles, methods, and applications of data mining
•
It combines the application of previous knowledge with new
concepts and techniques from multiple fields: Statistics,
Databases, Artificial Intelligence, …
•
Students learn to identify a problem and to address it with a
complete analysis using a data mining process
•
Students apply competences learned during the course in a
final practice following a case of study, adopting several roles
Manchester, 2007
Our proposal
•
To identify which are the main competences (goals) to enable
students with professional skills and abilities
•
To identify the competences required for data mining course
•
To design adaptive learning paths for improving the learning
process, integrating the different user profiles
•
To provide lifelong learning scenarios with adaptive itineraries
at the Open University of Catalonia
•
To study the possibilities of the IMS-LD standard for describing
such proposal
Manchester, 2007
Data mining learning process
•
All data mining students have to:
•
acquire some basic competences
•
study several didactical materials (M1, M2, M3)
•
do some learning exercises (E1, E2, E3)
•
do some evaluation activities (A1, A2, A3)
•
But usually….
•
Ateneu students (among others) need also reinforced
didactical materials (M1’, M2’) and also reinforced exercises
(E1’, E2’)
•
Students’ previous knowledge is not the same for some topics
for all students, depending on their background
•
Some topics are not required but they may be very useful for
some students (i.e. Java for Computer Science)
•
In order to improve the learning process, adaptive learning paths
could be designed as follows
Manchester, 2007
Example:
Adaptive learning path
E1’
M1
E1
E2’
A1
M1’
M1-3: Didactical materials
E1-3: Exercises
A1-3: Evaluation activities
M2
E2
A2
M3
E3
A3
M2’
Reinforced theory learning path: M1’, M2’
Reinforced exercises: E1’ and E2’
Manchester, 2007
Learning design?
•
It stores more information than simple learning
objects, including competences and activities
•
Learning environment, roles, activities, methods
and all the relationships need to be defined
•
Complex scenarios such as the Data Mining
subject case can be described
•
Adaptive learning paths can be created
Manchester, 2007
Conclusions
•
•
European universities need to include competences in their
degrees and curricula
The Bologna process may improve subjects related to
professional scenarios such as Data Mining
•
Subject competences have to be defined as a part of the
learner’s profile and must be incorporated into a lifelong learning
curricula
•
A flexible and adaptive learning process needs to be designed:
personalization, learning paths, …
•
Activity-oriented formative itineraries can be built by means of
combining required and acquired competences
•
IMS-LD is a first step towards describing the learning process,
but it needs further study
Manchester, 2007
Current and future research
•
To identify all the elements involved in the learning
process in the UOC virtual campus, according to the
IMS-LD standard
•
To create professional formative itineraries based on
the evaluation of acquired competences in an truly
open lifelong learning scenario
•
To offer more flexibility and personalization in the
learning process, improving user experience
•
To implement a pilot course part of the Ateneu courses
using IMS-LD
Manchester, 2007
Thank you!
Ana Elena Guerrero
[email protected]
Julià Minguillón
[email protected]
Manchester, 2007