Chapter 4 : A Framework for an Adaptable and Personalised E-Learning System
4.5 Content Delivery Model
4.5.2 The Adaptation Process
The planner contains adaptation rules used to modify the learning content based on learners’
feedback, and thus, this would be advantageous for the next generation of E-learning systems.
89
Accordingly, four questions were devised and implemented in the evaluation section of the
module specification page. These are:
1- How satisfied are you with the content?
2- How satisfied are you with completeness of the content?
3- How satisfied are you with academic quality of the content?
4- How satisfied are you with the learning experience?
The answer of these questions can be rated from 5 to 1 where “5” Strongly satisfied, “4”
Satisfied,”3” Neutral, “2” Not satisfied, and “1” very dissatisfied.
Questions 1, 2 and 3 were designed in order to investigate the learners’ opinion about the quality content delivered, whether it is relevant and clear which helps learners to fully comprehend concepts. Whereas, question 4 is associated with the learning style of the learner, which was used to update the learning style based on the learner’s feedback, which will be
explained in this section. Moreover, it was used to know the extent to which the learners are
satisfied with the learning experience.
To evaluate the produced content, the system calculates the average score of the first three
learner’s answers using a simple equation (4.2), which helps devise decisions in order to update the content and re-rank the webpages in the system.
User rating = answer for question 1+ answer for question 2+ answer for question 34 (4.2)
Where 4 represents the total number of questions.
For example, if “Satisfied” is selected in the first question by the users, the second question is “Neutral”, and the third question shows “Very dissatisfied”, then the final score is computed using a simple equation and illustrated as:
4 (Satisfied) + 3 (Neutral) + 1 (very dissatisfied) = 8 then calculate average = 8 / 4 = 2.00
This average score will be stored in the user’s rating database and this plays a vital role in ranking the webpages in the system based on the learner’s feedback. The system updates the
90
content of the URL in Recommendation link by finding the higher score in user rating which
will be recommended to other users. For example, if the learner would like to study Function
topic as part of Fundamental programming concepts, and he was not satisfied with the content,
as a result he gave a low average score. Then the system exchanges the learning content
presentation with one that has a higher score. Over time the system keeps evaluating the
presented content based on learner’s feedback, in order to assist them in learning in a better
and more effective and efficient manner.
A vital instrument that assists individuals and improves learning experiences is achieved
through the utilisation of learning styles within the remit of education as this enables
personalised design of the content of the course according to the way they learn (Sadler-Smith,
1996). Moreover, adapting the learning content to the learner based on his/her learning style
will provide an enjoyable learning environment, which will facilitate making a good learning
experience (Graf and Kinshuk, 2007). The system first identified the specific learning style of
the learner through the VARK questionnaire (Fleming, 2016). This type of learning style can
be updated based on the answers of the fourth question of the learner’s feedback. Moreover,
the following equation (4.2) was introduced to calculate the score of learning style based on
the answer of the fourth question.
LSS = y- (∑3𝑖=1(5 − 𝑠𝑐𝑜𝑟𝑒𝑄𝑢𝑒𝑠𝑡𝑖𝑜𝑛[𝑖])/3) (4.2) Where:
LSS is the learning style score.
y is the answer to question 4.
i is the answer to question 1-3
91
For example, if “Neutral” is selected in the first question by the users, the second question is “Not satisfied”, the third question shows “Neutral”, and fourth question is “satisfied “then the calculation score is shown as: LSS = 4 – (((5-3) + (5-1) + (5-3)) /3) = 1.33
This score of a particular learning style will be stored and then the planner automatically update
the present content of the learner based on the learning style. For example, if the learner would
like to study Stack topic as part of Algorithms and data structures, and s/he was not satisfied
with the learning experience, and the score given for that was very low then, the system will
search for a better content which has a higher score for the user rating and learning style. The
algorithm used to adapt the content and learning style based on learner’s feedback is given in
Figure 4-20.
Figure 4-20 Content and learning style adaption algorithm Algorithm : Update the content based on learner’s feedback
1. Begin
2. Score1= answer for question 1, Score2= answer for question 3
Score3= answer for question 3, Score4= answer for question 4
3. User rating = + +
4. Update user rating in Database
5. Calculate learning style based on the formula
𝒕 𝒕𝒊 [ ] − ∑𝒊 ( − 𝒕𝒊 [𝒊])/ )
6. Update learning style score in Database
7. Order user rating and learning style by descending 8.end
92
4.6 Summary
APELS design was illustrated by including its three main models, which were employed for
extracting the information from the Web in order to satisfy learner’s requirements. We also
illustrated the components and processes in the learner model which is very crucial to support
the adaptability and personalisation processes of the E-learning system. In addition, this chapter
introduced the knowledge extraction model which is at the heart of the architecture of APELS
as it is responsible for the extraction of the learning resources from the Web. With respect to
the content validation, our proposed learning outcomes validation approach was presented in
order to evaluate the topic content against a set of learning outcomes as defined by standard
curricula. Finally, the content delivery model was presented in the form of a planner, which is
responsible for generating and structuring the learning plan for the module including the
content. In addition, adaptation rules were described in this model for content adaptation based
on the learner’s content preference. The adaptation process takes also advantage and uses the learner’s feedback and learning style.
93