In this course, you will learn how to use Structural Templates to create reusable and shareable lessons. With this development, the design of courses and study programs can be packed and shared. The teacher can save time by using these shared templates for creating learning units with the same structure.

QBL Introduction
Conceptual Design of Moodle Extensions for QBL
Initial User Manual

Contents

Lesson 1. Introduction in Natural Language Processing (NLP)
This lesson introduces basic concepts of Natural Language Processing (NLP) required for implementing e-learning mechanisms in specific learning activities. The lesson describes multiple AI centered approaches in the NLP field.

Lesson 2. The ReaderBench Framework
This lesson describes ReaderBench, a multi-lingual advanced NLP processing framework. Examples of incorporated services are provided, followed by explanations of sematic mechanisms from behind the scenes.

Lesson 3. Examples of Serious Games developed with ReaderBench
This lesson shows examples of serious games developed with the help of the ReaderBench framework. Multiple games were developed having in mind three directions: vocabulary acquisition, comprehension assessment, and collaboration evaluation.

Lesson 4. The ReaderBench API
This lesson presents the ReaderBench API which provides multiple NLP services as REST endpoints. Each endpoint developed within the RAGE project is explained in detail – i.e., how it can be used, what data is required and what are the corresponding results.

Summary

Serious games are becoming an effective tool for pedagogy and learning in general. In this domain, one of the questions we are interested in is how to assess a player’s learning progress. Player assessment can provide teachers and students with formative and summative information about learning progress. Data from the player assessment can be used to dynamically adjust game mechanics which in turn improves the learning experience. We introduce the Adaptation and Assessment (TwoA) component, an opensource library that offers automated game difficulty adaptation and a player’s learning assessment. TwoA is being developed within the RAGE project, an EU’s initiative for supplying serious game developers with portable and reusable open-source software components providing pedagogical utility. In TwoA, we implemented a modified version of the Computerized Adaptive Practice algorithm for game difficulty and player skill assessments and a real-time adaptation of the game difficulty to the player skill. The CAP algorithm offers many benefits. First, it was extensively validated in many studies involving human players. Second, it was specifically designed for serious games to assess and match game difficulty to player skill to promote learning. It is a major distinction from existing matchmaking algorithms, such as TrueSkill or variations of Elo, that are aimed at competitive matching of two human players. Finally, the CAP algorithm is not proprietary. TwoA’s version of the algorithm provides two main benefits over the original CAP algorithm. First, we describe and validate improvements to CAP’s real-time adaptation of game difficulty. Second, TwoA adopts a RAGE-client architecture making the TwoA component easy to integrate and use with game development platforms.

Goals

• Learn why difficulty adaptation is important in serious games.
• Learn how to use the Adaptation and Assessment (TwoA) component.
• Learn about the limitations of the relative assessment techniques.

Target audience

• Game developers
• Students on TEL, DGBL, and game development

This course is a tutorial on creating courses with the KM-EP Course Authoring Tool.

It contains information slides, example content and self-assessment exercises to test your own learning progress.

The learning goal is to understand the functionality of the CAT and to try yourself which content type you find useful in online learning.

In this course you learn about a LTI bridge for Moodle and the Unity Engine.

With this technoloogy an interactive Unity game can now be integrated into an online course and be executed at run time through an LTI call. Gaming analytics and accordingly learning analytics will be supported in this Unity technology scenario through the Unity Analytics service. In this way Gaming results can be mapped onto Learning results and reported back to the Learning Management System.

The following course introduces you to the concept of

• FAtiMA (FearNot! Affective Mind Architecture): an Agent Architecture with planning capabilities designed to use emotions and personality to influence the agent’s behaviour.
• And the FAtiMA Toolkit: a collection of tools/assets designed for the creation of characters with social and emotional intelligence. It is able to work on multiple application environments such as Windows, Mac, Browser, iOS and Android Systems.

The course is composed of 1 slide set, 4 video tutorials, the 2 related game components and 1 publication.