Adaptive Hypermedia Techniques
Wednesday 30 July, 14:00 - 15:30Chair: Carlo Tasso
Using Decision Models for the Adaptive Generation of Learning Spaces (page 153)Eric Ras and Dimitri Ilin
This paper presents an approach that uses a decision model for resolving variations in a so-called learning space, which aim is to enhance the reuse of explicitly documented experiences by providing context-aware learning content. Decision models promise a better possibility to separate the variabilities in e-learning content, and address the problem of closed corpus of adaptive hypermedia systems. Adaptation is not coupled to a fixed set of learning resources, but to types of learning space concepts. The system adapts and personalizes the learning space to the learner's situation. A controlled experiment provides first statistically significant results, which show an experience package reuse improvement regarding knowledge acquisition and application efficiency. Further, it provides a baseline for future evaluations of different adaptation methods and techniques.
Evaluation of ACTSim: A Composition Tool for Authoring Adaptive Soft Skill Simulations (page 113)Conor Gaffney, Declan Dagger, and Vincent Wade
Adaptivity in technology enhanced learning has proven to be an effective and efficient approach in education. While simulations are include in the top end of eLearning there has been few if any real attempts to develop adaptive educational simulations. The key problem with their incorporation is their expense, cost and the effort involved in developing them. This ground breaking paper is the first publication to show a unique way for non-technical domain experts to compose and generate adaptive eLearning simulations. In particular it presents ACTSim, an innovative and unique composition tool used to author adaptive soft skill simulations.
Adaptive Retrieval of Semi-structured Data (page 32)Yosi Ben-Asher, Shlomo Berkovsky, Paolo Busetta, Yaniv Eytani, Sadek Jbara, and Tsvi Kuflik
The rapidly growing amount of heterogeneous semi-structured data available on the Web is creating a need for simple and universal access methods. For this purpose, we propose exploiting the notion of UNSpecified Ontology (UNSO), where the data objects are described using a list of attributes and their values. To facilitate efficient management of UNSO data objects, we use LoudVoice, a multi-agent channeled multicast communication platform, where each attribute is assigned a designated communication channel. This allows efficient searches to be performed by querying only the relevant channels, and aggregating the partial results. We implemented a prototype system and experimented with a corpus of real-life E-Commerce advertisements. The results demonstrate that the proposed approach yields a high level of accuracy and scalability.