Learner Model s Utilization in the e-Learning Environments Vija

Learner Model’s Utilization in the e-Learning Environments Vija Vagale, Laila Niedrite Faculty of Computing, University of Latvia, Riga, Latvia vija. vagale@du. lv, laila. niedrite@lu. lv 10 th International Baltic Conference on Databases and Information Systems July 8 -11, 2012, Vilnius, Lithuania

Introduction • One of the most actual tasks for educational quality improvement is the utilization of e-learning environments. • Learning environments can be divided into: – passive systems; – active systems. • Adaptive e-lerning environments can be used: – – for preschool age children; at schools; at universities; for life-long education. 10 th International Baltic Conference on Databases and Information Systems July 8 -11, 2012, Vilnius, Lithuania 2 / 19

Adaptive e-Learning system scheme • Domain model • Learner model (user model, student model) • Adaptive model (interaction model) 10 th International Baltic Conference on Databases and Information Systems July 8 -11, 2012, Vilnius, Lithuania 3 / 19

The aim and the tasks of research • The aim of the research is to explore in the user model included data. • The work tasks are: – to explore adaptive system structure models; – to explore learner model structure; – to analyze data obtaining types for user profile; – to make an analysis of data included in user model and split into categories; – to explore the stages of the user model creation; – to analyze construction techniques of the user model of an adaptive system. 10 th International Baltic Conference on Databases and Information Systems July 8 -11, 2012, Vilnius, Lithuania 4 / 19

User profile • User profile data can serve as the base for the user model creation. • User profile is created when the learner logs into the system for the first time. • Profile data contains learner personal data as well as data on his individual features and habits. • Profile keeps static information about the user without any additional description or interpretation. • User profile creation, modification and maintenance process is called user profiling. 10 th International Baltic Conference on Databases and Information Systems July 8 -11, 2012, Vilnius, Lithuania 5 / 19

Learner model • A learner model is an abstract representation of the system user. • Learner model includes: – profile data that gathers static information; – specific or dynamic data obtained by the system about a certain person during the learning process. • The user model contains all information that the system has on the user and maintains live user accounts in the system. • In general, the profile concept is narrower than the user model concept. • In a simplified case, user profile and learner model can coincide. 10 th International Baltic Conference on Databases and Information Systems July 8 -11, 2012, Vilnius, Lithuania 6 / 19

Obtaining data for the learner model 1. Directly - when user creates his profile on his own and data are taken from the user registration form and questionnaires – for example, birth date and gender. 2. Indirectly – when a system creates a profile by itself by collecting necessary information about the user from his activities. 3. Mixed approach, when one part of information is input by the user, but the other part of the information the system gains indirectly. 4. By integrating data to the adaptive e-Learning environments from other informational systems. 5. Gaining data from e. Portfolio. 10 th International Baltic Conference on Databases and Information Systems July 8 -11, 2012, Vilnius, Lithuania 7 / 19

In the learner model included possible data categories 10 th International Baltic Conference on Databases and Information Systems July 8 -11, 2012, Vilnius, Lithuania 8 / 19

Personal data and Pedagogical data Personal data: Pedagogical data: • name; • programs; • surname; • topics; • login; • course collections; • password; • course sequence. • language; • gender; • date of birth. 10 th International Baltic Conference on Databases and Information Systems July 8 -11, 2012, Vilnius, Lithuania 9 / 19

Preference data and Personality data Preference data: Personality data: • language; • learning style; • presentation format; • concentration skills; • sound value; • video speed; • web design personalization. 10 th International Baltic Conference on Databases and Information Systems July 8 -11, 2012, Vilnius, Lithuania • collective work skills; • relationship creating skills; • individual features; • attitudes. 10 / 19

System experience, Goal, Cognitive data and History data • System experience obtained certificates and skills in e. Learning system utilization. • Goal – data about the system user long-term interests. 10 th International Baltic Conference on Databases and Information Systems July 8 -11, 2012, Vilnius, Lithuania • Cognitive data – data that represents reference types of the learner. • History data – data about all learner’s activities. 11 / 19

Device data and Acquired knowledge Device Data: data that characterizes working environment of the system user: • hardware; • download speed; Acquired knowledge: • Student knowledge at the current moment of time – data that describes student knowledge gained in the learning process. • screen resolution; • learner’s location; • time; • used devices. 10 th International Baltic Conference on Databases and Information Systems July 8 -11, 2012, Vilnius, Lithuania 12 / 19

Analyzed articles in this research • [29]: Nebel et. al. , 2003, “A user profiling component with the aid of user ontologies”; • [3]: Brusilovsky, 1996, “Methods and techniques of adaptive hypermedia”; • [25]: Liu et. al. , 2009, “A survey on user profile modeling for personalized service delivery systems”; • [41]: Sosnovsky & Dicheva, 2010, “Ontological technologies for user modeling”; • [13]: Gomes et. al. , 2006, “Using Ontologies for e. Learning Personalization”; • [10]: Frias-Martinez et. al. , 2006, “Automated User Modeling for Personalized Digital Libraries”; • [27]: Martins et. al. , 2008, “User Modeling in Adaptive Hypermedia Educational Systems”; • [1]: Behaz & Djoudi, 2012, “Adaption of learning resources based on the MBTI theory psychological types”. 10 th International Baltic Conference on Databases and Information Systems July 8 -11, 2012, Vilnius, Lithuania 13 / 19

The frequency of the learner model data category Data category type [29] Personal data Personality data Cognitive data/style Pedagogical data Preference data History Device Context/Environment Interests of user Interests gathered system Goal/Motivation System Experience Domain Expertise Results of assessment Acquired knowledge Deadline extend + + [3] [41] [13] [10] [27] [1] + + + [25] + + + + + + + by + + + + 10 th International Baltic Conference on Databases and Information Systems July 8 -11, 2012, Vilnius, Lithuania + + + + 14 / 19

Formation stages of the learner model • Initialization – basic data gathering for model; • Reasoning – gaining new data about the learner from already existing data; • Updating – learner model data actualization. 10 th International Baltic Conference on Databases and Information Systems July 8 -11, 2012, Vilnius, Lithuania 15 / 19

LM construction techniques • Stereotype model – is based on the system-offered stereotypes; • Overlay model – based on the user progress in the system; • Combination model – employs both of the previously mentioned models; • Differential model –similar to overlay model plus must-learn knowledge; • Perturbation model – similar to overlay model plus mal-knowledge; • Plan model – incorporates successive student actions for achieving certain goals and desires. 10 th International Baltic Conference on Databases and Information Systems July 8 -11, 2012, Vilnius, Lithuania 16 / 19

User data modeling methods • Static data elements are modeled with Attribute-Value Pairs. – Attributes are terms, concepts, variables and facts that are important for both the system and the user. – Their values can be of the following types: boolean, real or string. • Dynamic data elements are modelled using rules based on if-then logic. • To represent the relationship between data elements the hierarchy tree modeling approach or ontology are used. 10 th International Baltic Conference on Databases and Information Systems July 8 -11, 2012, Vilnius, Lithuania 17 / 19

Conclusions 1. Depending on the type of the adaptive system, model names included in it may differ but their essence and tasks remain similar; 2. Each adaptive learning system must have at least three components: (a) a domain model for keeping system-offered knowledge; (b) a learner model (user model, student model) which describes a person who is sitting in front of the computer and willing to learn in an understandable way for the system; (c) an adaptive model (interaction model) – with its help system-offered knowledge is delivered to the learner in an understandable way. (a) All data included in the learner model can be divided into some basic categories: Personal data, Personality data, Pedagogical data, Preference data, System experience, Cognitive data, History data and Device data. 10 th International Baltic Conference on Databases and Information Systems July 8 -11, 2012, Vilnius, Lithuania 18 / 19

Thanks for your attention! 10 th International Baltic Conference on Databases and Information Systems July 8 -11, 2012, Vilnius, Lithuania 19 / 19