Dessislava Vassileva

Architectural design of a software engine for adaptation control in the ADOPTA e-learning platform

In recent years, the field of adaptive web-based systems becomes one of the key research e-learning areas. Efforts are focused on tools for creating and managing content that on the one hand can be adapted to various goals, preferences, knowledge and learning style of a learner and, on the other hand, can be reused by various authors and exchanged between different systems. Our article discusses a proposal for software engine construction to adaptable content delivery and to adaptive process management. This adaptation control engine is a part of the ADOPTA - adaptive technology-enhanced platform for edutainment. Our approach is based on web services that enables, besides reusing and exchanging of learning content, also reusing of application functionality.

Courseware Adaptation to Learning Styles and Knowledge Level

According to initial design of adaptive e-learning, content of an adaptive course should be suitable for students with different profiles (Brusilovsky, 1996). These profiles may contain information about goals, preferences, knowledge level, learning style, rendering psychological profile, and more. Typically, the learning content is developed for some groups of students that have similar values of one or several parameters of the student’s profile. For more groups of students an adaptive course is designed, the more personalized it is.

Affect-based adaptation of an applied video game for educational purposes

Purpose This paper aims to clarify how affect-based adaptation can improve implicit recognition of playing style of individuals during game sessions. This study presents the “Rush for Gold” game using dynamic difficulty adjustment of tasks based on both player performance and affectation inferred through electrodermal activity and facial expressions of the player. The game applies linear regression for calculating playing styles to be applied for achieving a style-based adaptation in other educational video games. Design/methodology/approach The experimental procedure included subject selection, demonstration, informed consent procedure, two game sessions in random order – one without and another with affective adaptation control – and post-game self-report. The experiment was conducted with participation of 30 master students and university lecturers in informatics. Findings This study presents experimental results concerning the impact of affective adaptation over playing style recognition, game session time, task’s effectiveness, efficiency and difficulty and, as well, player’s assessment of affectively adaptive gameplay obtained by an adaptation control panel embedded into the game and by post-game self-report. Research limitations/implications The proposed adaptive game limits recognised styles to such based on the Kolb’s Learning Style Inventory model. Another limitation of the study is the relatively small number of participants constrained by the extended experimental procedure and the desktop game version. Originality/value The paper presents an original research on the effect of affect-based adaptation on a novel approach for implicit recognition of playing styles.

DYNAMIC GAME ADAPTATION BASED ON DETECTION OF BEHAVIORAL PATTERNS IN THE PLAYER LEARNING CURVE

In educational serious games, the learning curve of a player represents his/her progress in acquiring cognitive abilities and new knowledge necessary for solving the game challenges. Hence, it is very important for an adaptive serious game to have a mechanism for detection of patterns of player´s learning curve in playing time. The paper presents the application of a game adaptation method based on automatic and dynamically detection of specific learning curves at runtime within a 3D video game of car driving in various weather conditions. The method uses a client-side software component called “Player-centric rule-and-pattern-based adaptation asset” and developed within the scope of the RAGE (Realising and Applied Gaming Ecosystem) H2020 project. The component is incorporated into a 3D car driving video game in order to enable a dynamic detection of different patterns of player performance. It allows the video game scenario to be adapted to each player by providing appropriately for him/her challenges and game features. We carried out a practical experiment with students from Sofia University, Bulgaria, where we found that adaptation of game difficulty by applying the RAGE software component resulted to improved game playability.

Playing styles based on experiential learning theory

Abstract In recent years, researchers have reported positive outcomes and effects from applying computer games to the educational process. The preconditions for an effective game-based learning process include the presence of high learning interest and the desire to study hard. Therefore, educational video game design has to tailor gameplay to the style of the playing learner, i.e. to the psycho-cognitive abilities, attitudes, and skills of the individual player, in order to foster the players motivation and creativity. To achieve this goal, it is necessary to draw a parallel between learning styles and styles of playing video games, and to investigate the correlations between these types of constructs. The article presents a new family of playing styles based on Kolbs experiential learning theory that is appropriate to be used for educational video games. This family is composed of four playing styles: Competitor, Dreamer, Logician, and Strategist, and corresponds to Honey and Mumfords learning styles based also on the theory of experiential learning, namely Activist, Reflector, Theorist, and Pragmatist. To measure the four playing styles, a 40-item questionnaire was designed. In order to verify the consistency, validity, and reliability of that questionnaire as an accurate tool for recognizing the four suggested player styles, a pilot study was conducted. The article reports the results obtained from the study, along with their analysis and applicability.

CEVS – A Corporative E-voting System Based on EML

In recent years, e-voting systems become more and more important as they contribute to the overall democratic process worldwide. CEVS (Corporative E-Voting System) is a new Internet voting application developed by means of EML (Election Markup Language) technologies. The article presents an overview of the EML structure and extensions and, as well, a JAXB (Java Architecture for XML Binding) technology, both used for building the CEVS application. Next, we describe in details the CEVS software architecture and discuss aspects of its system functionality. There are given directions for elaboration of CEVS and future works according to the state-of-the-arts trends in the area.