Logo des Repositoriums
 

ABIS 2007 – 15th Workshop on Adaptivity and User Modeling in Interactive Systems

Halle, 24.-26. September 2007

Autor*innen mit den meisten Dokumenten  

Auflistung nach:

Neueste Veröffentlichungen

1 - 9 von 9
  • Konferenzbeitrag
    Prediction Algorithms for User Actions
    (15th Workshop on Adaptivity and User Modeling in Interactive Systems, 2007) Hartmann, Melanie; Schreiber, Daniel
    Proactive User Interfaces (PUIs) aim at facilitating the interaction with a user interface, e.g., by highlighting fields or adapting the interface. For that purpose, they need to be able to predict the next user action from the interaction history. In this paper, we give an overview of sequence prediction algorithms (SPAs) that are applied in this domain, and build upon them to develop two new algorithms that base on combining different order Markov models. We identify the special requirements that PUIs pose on these algorithms, and evaluate the performance of the SPAs in this regard. For that purpose, we use three datasets with real usage-data and synthesize further data with specific characteristics. Our relatively simple yet efficient algorithm FxL performs extremely well in the domain of SPAs which make it a prime candidate for integration in a PUI. To facilitate further research in this field, we provide a Perl library that contains all presented algorithms and tools for the evaluation.
  • Konferenzbeitrag
    State of the Art of Adaptivity in E-Learning Platforms
    (15th Workshop on Adaptivity and User Modeling in Interactive Systems, 2007) Hauger, David; Köck, Mirjam
    Adaptivity has been an important research topic during the past two decades, especially in the field of e-learning. This paper deals with the question of whether and to what extent adaptivity is actually being used in e-learning systems. It describes the state of the art of adaptivity features and gives an overview on the most frequently used learning management systems (LMSs) as well as on a number of research projects and systems providing adaptivity.
  • Konferenzbeitrag
    Taking the Teacher’s Perspective for User Modeling in Complex Domains
    (15th Workshop on Adaptivity and User Modeling in Interactive Systems, 2007) Janssen, Christian P.; van Rijn, Hedderik
  • Konferenzbeitrag
    Context-adaptation based on Ontologies and Spreading Activation
    (15th Workshop on Adaptivity and User Modeling in Interactive Systems, 2007) Hussein, Tim; Westheide, Daniel; Ziegler, Jürgen
    Ontologies and spreading activation are known terms within the scope of information retrieval. In this paper we introduce SPREADR, an integrated adaptation mechanism for web applications that uses ontologies for representing the application domain as well as context information like location, user history and local time. Those context factors can be modeled in an ontology and be linked to certain domain nodes. In each session a Spreading Activation Network is build based on those ontologies and recognized con- text factors or user actions can trigger an activation flow through this network. A node’s resulting activation value then represents its importance according to the current circumstances. While identically in structure, the Spreading Activation Networks are personalized by automatically modifying link weights and activation levels of nodes. As a result the system learns about the user preferences and can adjust its adaptation mechanism for future runs through implicit feed- back.
  • Konferenzbeitrag
    Concept of an adaptive training system for production
    (15th Workshop on Adaptivity and User Modeling in Interactive Systems, 2007) Odenthal, Barbara; Mayer, Marcel Ph.; Grandt, Morten; Schlick, Christopher M.
  • Konferenzbeitrag
    Towards Learning User-Adaptive State Models in a Conversational Recommender System
    (15th Workshop on Adaptivity and User Modeling in Interactive Systems, 2007) Mahmood, Tariq; Ricci, Francesco
    Typical conversational recommender systems support interactive strategies that are hard-coded in advance and followed rigidly during a recommendation session. In fact, Reinforcement Learning techniques can be used in order to autonomously learn an optimal (user-adaptive) strategy, basically by exploiting some information encoded as features of a state representation. In this regard, it is important to determine the set of relevant state features for a given recommendation task. In this paper, we address the issue of feature relevancy, and determine the relevancy of adding four different features to a baseline representation. We show that adding a feature might not always be beneficial, and that the relevancy could be influenced by the user behavior. The results motivate the application of our approach online, in order to acquire the right mixture of online user behavior for addressing the relevancy problem.
  • Konferenzbeitrag
    Mediating expert knowledge and visitor interest in art work recommendation
    (15th Workshop on Adaptivity and User Modeling in Interactive Systems, 2007) van Maanen, Leendert
    In this paper we will present an outline for an online recommender system for artworks. The system, termed Virtual Museum Guide, will take the interest that visitors of an online museum express into account in recommending suitable art works, as well as the relationships that exist between art works in the collection. To keep the Virtual Museum Guide similar to a human museum guide, we based its design on principles from research on human memory. This way the Virtual Museum Guide can 'remember' which is the most suitable art work to present, based on its perception of the visitor's interests and its knowledge of the works of art.
  • Konferenzbeitrag
    Adaptive Reading Assistance for Dyslexic Students: Closing the Loop
    (15th Workshop on Adaptivity and User Modeling in Interactive Systems, 2007) Schmidt, Andreas; Schneider, Michael
    Adaptive reading assistance can improve the reading performance of students, but current dyslexia pedagogical theories do not yet provide sound results on a micro-level. We want to provide a reading assistance solution that both helps the learner and the dyslexia researcher. In order to archive this, we encode adaptation knowledge in a descriptive way by making use of state-of-the-art ontology-based techniques. This enables a closed-loop approach of continuous improvement. In this paper, we want to present the overall approach as well as initial results of our work within the EU project AGENT-DYSL.
  • Konferenzbeitrag
    Towards Asynchronous Adaptive Hypermedia: An Unobtrusive Generic Help System
    (15th Workshop on Adaptivity and User Modeling in Interactive Systems, 2007) Putzinger, Andreas
    First, this paper introduces the concept and the upcoming features of Asynchronous Adaptive Hypermedia Systems (AAHS). The design of a concrete system will show how the new principles can successfully be applied to build a generic adaptive help module which can be put on top of existing adaptive or non-adaptive web application without the need of refactoring.