Presentation on theme: "Personalized and adaptive eLearning Applications in LSMs"— Presentation transcript:
1Personalized and adaptive eLearning Applications in LSMs Phạm Quang DũngDept. of Computer Science
2Content Main issues of personalized and adaptive eLearning Learning customization and web services approachDevelopment and design of adaptive learning contentStudent modellingTailoring learning materials to the individual learning styles
3ProblemEvery learner has individual characteristics: learning preference, self-efficacy, knowledge, goal, experience, interest, background, etc.How to enhance learning process effectively?Solution: personalized and adaptive learningAdaptive system tunes learning material & teaching method to learner model
4Learner modelLearner profile: contains personal information without inferring or interpreting.Learner model: description of learner’s propertieshas a higher level than profile, expresses abstract overview of learnerLearner modelling
5Learning objectsany digital resource that can be reused to support learning (D.A. Wiley, 2000)digital images or photos, video or audio snippets, small bits of text, animations, a web pageCharacteristicsShare and reuseDigitalMetadata-taggedDescription information: title, author, format, content description, instructional functionInstructional and Target-Oriented
6Main issues of personalized and adaptive learning The personalization is a function able to adapt the eLearning content and services to the user profile. It include:- how to find and filter the learning materials that fit the user preferences, needs, background, learning style, etc.;- how to present them;- how to customize the learning process i.e. deliver just the right material to the learner on Demand and Just in Time;- how to give user tools to reconfigure the system;- how to construct effective user model and tracking of its continuous changes, etc.
7Main issues of personalized and adaptive learning Types of personalization:Personalization of the learning context, based on the learner’s preferences, background, experience, learning style, etc.Personalization of the presentation manner and form of the leaning content (for example, adaptive learning sequences of learning objects);- Full personalization, which is a combination of the previous two types.Adaptive learning means the capability to modify the learning content and/or any individual student’s learning experience as a function of information obtained through its performance and progress on situated tasks or assessments.
8Main issues of personalized and adaptive learning Personalization in current LMSs includes:Editable user profile;Changeable graphics design of the learning material;Personal calendar tracking learning progress events;Access to learning objects conditioned on part of the personal data including achievements, experience, preferences, etc. (rarely);Information about the learner behaviour during the learning process and the system’s reactions – personalized instructional flows, adaptive learning content, etc. (rarely);Presentation manner and form of the learning content according to learner’s style (rarely), etc.
9Learning customization and web services approach Wlliam Blackmon and Daniel Rehak define the following ways for learning customization:At random – repeat random selection of learning objects;By profile – choose the course/content based on the learner’s profile (role, skills, learning style, etc.);By discovery – for given learning objective, find a learning object that best meets the learning objective given the learning’s current skill set, learning platform, learning style, language preference, etc.;By response – choose the next learning activity based on the learner’s responses to questions.
10Learning customization and web services approach Wlliam Blackmon and Daniel Rehak offer a web-services-based methodology for customization by profile in particular a methodology for eliminating learning objects (LOs) from the course because either:- the learner’s current role does not require the learning objective taught by the LO, or- the learner’s profile indicates that the learner has already achieved the objective taught by the LO.The learning content and data used for customization are presented in a set of standards-based data models.
11Learning customization and web services approach The overall web-services architecture for learning is divided into layered services. The layers from top to bottom are:- User agents - provide interface between users and the learning services and major element of LMS – authoring of content, management of learning, content delivery, etc.;- Learning services – they are collection of data models and independent behaviours. They are grouped into logical collections- tool layer – provide public interface to the learning tools (simulators, assessment engines, collaboration tools, registration tools, etc.)- common application layer (sequencing, managing learner profiles, content management, competency management, etc.)- basic services layer – core features and functionality that are not specific for the learning (storage, management, workflow, right management, query/data interfaces, etc.)
12Learning customization and web services approach
13Development and design of adaptive learning content Adaptive learning content can be defined as a relevant sequence of learning objects (LOs), each of them associated with learning activity that fulfill given learning objective. The flows of learning activities can be described by rules and actions that specify:- the relative order in which LOs have to be presented, and- the conditions under which a pieces of content have to be selected, delivered or skipped during sequence presentationaccording to the outcomes of learner’s interactions with content.
14Development and design of adaptive learning content The process of defining a specific sequence of learning activities begins with the creation of a learning strategy for the achievement of the determined pedagogical aim/s. Learning strategy specifies:- types of learning activities;- their logical organization;- the prerequisites, and- expected results for each activities.IMS Simple Sequencing Specification and the SCORM standard allow the learning strategies to be translated into sequencing rules and actions based on learner progress and performance.
15Student modelling The student model enables the system to: provide individualized course content and study guidance;suggest optimal learning objectives;determine students’ profiles and their actual knowledge;dynamically assemble courses based on individual training needs and learning styles;join a teacher for guidance, help and motivation, etc.
16Student modelling - standards Incorporation between IEEE LTSC’s Personal and Private Information (PAPI) Standard and the IMS Learner Information Package (LIP)IEEE Learning Technology Standards Committee (LTSC)The formal name for IMS is IMS Global Learning Consortium, Inc., also sometimes referred to as IMS GLC. The original name, when IMS first started in 1997 was the Instructional Management Systems (IMS) project.
17Student modelling SeLeNe learner profile The Self e-Learning Networks Project (SeLeNe) is a one-year Accompanying Measure funded byEU FP5, running from 1st November 2002 to 31st October 2003, extended until 31st January
19Problems with collaborative student modelling that use a questionnaire Uncertainty because of:a lack of students’ motivationa lack of self-awareness about their learning preferencesthe influence of expectations from othersQuestionnaires are static and describe the learning style of a student at a specific point of timeThe result depends much on students’ mood
20Benefits of using automatic student modeling does not require additional effort from studentsis free of uncertaintycan be more fault-tolerant due to information gathering over a longer period of timecan recognise and update the change of students’ learning preferences
22Automatic student modelling approaches data-driven vs. literature-based
23Automatic student modelling The data-driven approach uses sample data in order to build a model for identifying learning styles from the behaviour of learnersaims at building a model that imitates the ILS questionnaireAdvantage: the model can be very accurate due to the use of real dataDisadvantage: the approach strictly depends on the available data and is developed for specific systems
24Automatic student modeling The literature-based approach uses the behaviour of students in order to get hints about their learning style preferencesthen applies a rule-based method to calculate LSs from the number of matching hintsAdvantage: generic and applicable for data gathered from any courseDisadvantage: might have problems in estimating the importance of the different hints
25Tailoring learning materials to the individual learning styles Filteringof theKeyword-based search of LOsRankingresult LOsLearnerPresentationUser profile (individual learning style)Personalized learner’s view of the LO information spacePersonalized LO browsing process according to:Learner’s preferences help to the system to recommendindividualized LOs or categories of LOs.