Modelling the learner model based ontology in adaptive learning environment

Currently, the online learners are increasingly demanding more personalized learning since the web technology, and the learners have individual features of characteristics such as learning goals, experiences, interests, personality traits, learning styles, learning activities, and prior knowledge. A personalized learning process requires an adaptive learning system (ALS). In order to adapt, a learner model is required. Thus, modelling the learner model in an adaptive system environment is a key point to success in recommending the learner. The ontology-based approach was used to model the adaptive learning model in this research. Ontology is a graph structure that consists of a collection of contexts, relationships, and models which related to contexts. The ontology of the learner model enables to produce a description of learner’s properties which contains important information about domain knowledge, learning performance, interests, preference, goal, tasks, and personal traits.


Introduction
The advancement of the digital age has led to the development of technology which covers almost all of the aspects of life. One aspect is education which takes an in the imperative role in human life. E-learning is distance learning that is done in a virtual way using the internet. In the e-learning system, users can learn at any time, anywhere and in any situation. In this system, the learning process does not require communication that is only in class. In this way, learners can apply movies, sound files with music, games and various types of content. One of the most important things in an E-learning system is adaptive learning with the level of knowledge, personality, and the ability of learner behaviour (Baishuang, et al. 2009). To reveal this, the system can provide information about users by building learner models (learning models). The learner model is a specific user model to display learners' special characters. In general, the learner model is a system of knowledge about learners. If there is information about the goals, abilities, background knowledge, interests and behaviour of participants, the system can adjust to learners.
The adaptive system is adopted based on the learner model; Therefore, the accuracy of adaptation depends on the correctness of the learner model. Also, in some cases, the learner model is used to assess learner knowledge. Therefore the modelling process is very important.
Learner modelling helps the e-learning system to get learners' perceptions and recommend learning objects based on this perception. Personal learning processes and systems that support the process are called Adaptive Learning Systems (Wang, 2006;Winter, 2005). Therefore, the adaptive learning system can change its action to provide learning and environmental content or pedagogical methods for learners. The adaptive system is based on "learner's personal description" which is called the learner model. The process of gathering information to build learner models and updating is learner modeling. The adaptive system regulates learning material and teaching methods for learner models.

Contribution
The purpose of this study is to establish an ontological relationship between the formation of learner models with adaptive learning systems. The relationship that has been made is thoroughly investigated to test the suitability of the ontology model on the concept of relationship modelling of learners with an adaptive learning environment. The next goal is to identify the components of the characteristics of learners who can be the model variables of the learners. To verify the ontology relationship, what must be prepared is research related to the model of learners. Adaptive learning system and architectural development of learner models.
The objectives that must be analyzed and completed are as follows: a. How do learner models have to be compiled and modelled? Parameters for determining learner variables can be obtained from the ontology concept.
b. How do you build the ontology model of learner models in adaptive learning?

Related Study
The Learner Model contains learner characteristics that are important for adaptive learning. A  To provide personalization in an e-learning with adaptive learning system, it is necessary to store learner characteristics (e.g. abilities, preferences, prior knowledge, and learning styles) in the learner model (Suryono, 2011; Vesin, 2011). On the other hand, dynamic features are updated during the learning process based on the interaction of learners with the system, for example, the values, abilities, and knowledge of learners. Learner modeling allows the system to personalize interactions between learners and the content learned. To achieve this goal, the system must predict the needs of learners based on information in the learning model to then offer content in ways that can be understood by learners. There are several techniques for modeling learners and enhancing this model. Ontology has proven to be an effective method for presenting knowledge in a particular domain by means of semantics (Snae & Brueckner, 2007; Jeong, Choi, & Song, 2012). Therefore, the author proposes an approach in which an ontological model is used to present the characteristics of learners. The ontology learning model presents personal preferences and learning characteristics of learners who interact with the system. This information is updated according to learner interaction with content. Updated information is used by adaptation models to make adaptation decisions.

Learner Model Ontology
In this section, the architecture for building learner models will be explained. General description of this architecture is shown in Figure 2. Information regarding learners is divided into two parts; personal information and behavioral information in online learning. The system uses two approaches to obtain learner personal information (Korchi, et al., 2017). On the other hand, with the results of the pretest taken from learners, the system can estimate the level of initial knowledge of learners from different backgrounds (Brut, et al. 2009). This estimation can be served as a reference to what learners need in terms of learning content. To obtain information on learner behavior, learner behavior during interaction with the e-learning system must be tracked.  analysis, synthesis and evaluation. Level "1" refers to knowledge (h1), level "2" refers to comprehension (h2), level "3" refers to application (h3), level "4" refers to analysis (h4), level "5" refers to synthesis (h5), and level "6" refers to evaluation (h6). As for learners with basic abilities are entered at the level of "0" (h0), so that the relationship is obtained as follows:   Figure 3 show the ontology proposes that a modeling method consisting of several concepts that are semantically related to each other, namely:

a. Learners
Including personal data to be defined (for instance: Name, First Name, Age, Gender, This concept is related with the four other concepts which define learner, such as: • Knowledge.

c. Learning Activities and Resources
During learning activities related to learners, resources are functioned according to learner preferences in accordance with their profile. Ontology plays a role in the representation and organization of resources during the learning session.

d. Domain and Discipline
Ontology classifies various disciplines according to the field of knowledge. If the domain name is Science, then discipline can be in the form of Mathematics, Physics, or Natural Sciences. At the end of each learning session, the system has a set of information regarding learners that must be arranged and stored using an ontology to produce a new profile that will be taken into account in the next session. The system will interact intelligently with the learner dynamically adapting the subject to be presented to the learner in accordance with the results obtained and the learning mode that best suits the learner.

e. Authentification Process
Once the participant is connected to the learning platform, learner identity is stored, which will later allow the learner to find his or her workplace. Through this identity, the learner profile is associated with pedagogical activities to adjust it to the right profile.

f. Learner's Profile Updating Process
The update of the learner model consists of modifying values that represent the level of learner knowledge for a given number of resources from the concept given.
The learner profile is updated before or after the study session. Some techniques are used to update profiles, namely: • Test level.
• Determination of learner interactions.
• Determination of behavior.
• The preferred type of material (learning content).

g. Interaction
Learner interaction with one of the proposed resources can determine the renewal of the profile. For instance, the length of time learners learns during reading a material content. The length of time will be determined by the time spent in this activity.

h. Behavior
Learner's behavior during the learning session determines profile detecting and updating.
i. History The learner model should store all relevant information about learners, including knowledge and attitudes (Brut, et al. 2009). The adaptive environment keeps all information about learners to be utilized at any time by the ontology. Learning records allow learners to know their background.

Conclusion
Ontology in learner modeling and adjustment of learning processes work by considering learner profiles. The contribution of the ontology model focuses on the following elements: behavioral analysis and evaluation, detection of learning styles, development of learner profiles that take into account learners' knowledge, preferences and attitudes. This ontology model can realize an adaptive learning system that allows the adaptation of pedagogical content according to current learner needs by evaluating the learner's self during the learning sequence. This ontology can detect more parameters, particularly with the contribution of the semantic Web to design better adaptive learning with more numbers of learners.