[1]

Use case: Gamified eLearning

Teaching and learning via electronic media and information and communication technologies defines eLearning. It includes several types of media and game mechanics to increase retention of participants, e.g., video stream, text, audio, image, animation and interactive application.

The meaning of eLearning increases steadily due to the technological progress. Various concepts have been established in the last few years and efforts have been made to join these concepts with gamification characteristics and thus improve the learning experience for members. To apply our models of player experience we can launch our analysis at this joint.

Churn management is an essential tool for a successful gamification platform. Therefore the prediction and prevention of churn is interesting to increase the number of members and besides increase the quality of the platform. To do this we want to detect patterns of behavior that lead to churn and analyze the causes in order to provide proactive recommendations or provide personalized content, like quests or feedback messages. The basis for the interpretation of these patterns are models of player types and learning styles. Due to generic parts of the model, the hybrid player experience model is applicable to other gamified environments.

With the combination of learning styles with player types we can cover a variety of platform. In almost every activity your learning style plays an important role. In order to approve our models it is of great significance to us to analyze an eLearning-platform.

Since many different models of learning styles have been introduced we have to select to most suitable for our demands. Thus we need a model that we can easily transfer to the provided data. One relatively adaptable model was developed by R. Felder, who does not define certain learning styles, but offers for dimension to differentiate the individual process of learning [2].

  • Active ↔ reflective
  • Sensorial ↔ intuitive
  • Visual ↔ verbal
  • Sequential ↔ global

The first dimension concerns the difference between active discussion and application and reflective observation of the learning content. The distinction between sensorial and intuitive describes the process of learning. On the one hand, process is gained through structured methods (sensorial) and on the other hand, the person explores possibilities and relations (intuitive). The third dimension considers the preference visual or spoken content. And finally, the fourth dimension covers another aspect of the process of learning. Sequential learner handle the learning content step-by-step, whereas global learners jump from one part to the other without any logic.

Some of these characteristics can be found in the Bartle player types, too, like the active Socializer who likes to interact with others by discussing the learning content or the Achiever who might be classified as a sequential learner. The fact that we can additionally cover these characteristics with the provided data led to the decision to base our analysis on this model. In addition the model is intuitive, hence serving as a communication platform with stakeholders.

Our aim is to predict member behavior, especially possible drop-outs. The deep analysis of member behavior in real-time enables proactive techniques, improving the learning experience. For instance, personalized recommendations could be created paving the way to become an even more effective learner.

References:
[1] https://www.gws.ms/aktuelles/elearning/
[2] R. Felder & B.Soloman: "Learning styles and strategies"

Cooperation Partner

Integrated Science

Our models are theoretically based on established research and are applied in real-world games with thousands of players. This leads to high generalizability of our methods and results and transfers our research from science to industry.

©2014 TECO – Technology for Pervasive Computing