- KonferenzbeitragEvaluating the Usability of Adaptive Recommendations(16th Workshop on Adaptivity and User Modeling in Interactive Systems, 2008) Weibelzahl, Stephan; Chihaia, Diana; Hartmann, Melanie; Krause, Daniel; Nauerz, AndreasIn the design, development and evaluation of adaptive systems, usability aspects are largely ignored so far. A correct but badly designed adaptation decision might spoil the purpose. This paper provides an example of a usability evaluation with an adaptive collaborative system. The results suggest that the representation format of recommendations did not strongly affect standard usability measures. However, comparing different design versions helped users to identify strengths and weaknesses.
- KonferenzbeitragTowards an Automatic Service Composition for Generation of User-Sensitive Mashups(16th Workshop on Adaptivity and User Modeling in Interactive Systems, 2008) Fischer, Thomas; Bakalov, Fedor; Nauerz, Andreas; Hartmann, Melanie; Krause, Daniel; Nauerz, AndreasIn today’s Web 2.0, mashups allow users to bring together data and services from various Web applications in order to create a new integrated tool that serves their needs. Nowadays, there is an increasing number of frameworks that provide users with a GUI environment to manually assemble different data sources and services into a mashup. However, in order to create such tools, the user must possess a certain level of technical knowledge. In this paper, we introduce a framework that automatically selects and combines Web services to create mashups. We also describe the user model that stores knowledge about user interests and expertise, which are used by the framework in order to generate mashups tailored to the needs of individual users.
- KonferenzbeitragDescribing User Actions in Adaptive Interfaces with Probabilistic Acceptors(16th Workshop on Adaptivity and User Modeling in Interactive Systems, 2008) Bezold, Matthias; Hartmann, Melanie; Krause, Daniel; Nauerz, AndreasAn important aspect of adaptive systems is the description of the user-system interaction, which can be used to derive new information about the user and to trigger adaptations, for instance by means of adaptation rules. In this paper, we present an approach that describes user actions by means of probabilistic deterministic finite- state automatons (PDFA), which are generated from an annotated corpus of user interactions. Based on a training set, different acceptors are created from recording data and can be employed by an adaptation framework to trigger adaptation rules. An evaluation of this approach with a prototype of an interactive TV system is presented.
- KonferenzbeitragFine-grained user models by means of asynchronous web technologies(16th Workshop on Adaptivity and User Modeling in Interactive Systems, 2008) Hauger, David; Hartmann, Melanie; Krause, Daniel; Nauerz, AndreasAlthough asynchronous HTTP technologies have grown in importance with the emergence of Web 2.0, most web-based Adaptive Hypermedia Systems (AHS) still exclusively use server- side monitoring of user behaviour to set up the user model. This paper discusses how asynchronous technologies and client-side observation may lead to more accurate and detailed user models, and how that might benefit next- generation AHS.
- KonferenzbeitragAdaptive Treemap Based Navigation Through Web Portals(16th Workshop on Adaptivity and User Modeling in Interactive Systems, 2008) Nauerz, Andreas; Schindler, Sirko; Bakalov, Fedor; Hartmann, Melanie; Krause, Daniel; Nauerz, AndreasToday, Portals most often present the navigation in form of tree-like structures to users. These trees follow a representation of data with a natural hierarchy. Single nodes are either parents or children. This representation style has several drawbacks: for reaching the leaves users have to traverse rather long paths. During the traversion of the tree users get often lost and, finally, the content relations remain unclear. It is not obvious where the ”most” content is located, too. We regard treemapping (a method for displaying tree-structured data using nested polygons) as a promising technology to overcome these draw- backs. We especially focus on adaptive treemaps displaying different treemaps to different users - always trying to satisfy each single users’ individual needs. Our main concepts have been prototypically embedded within IBM’s WebSphere Portal.
- KonferenzbeitragHybrid Personalization For Recommendations(16th Workshop on Adaptivity and User Modeling in Interactive Systems, 2008) Herder, Eelco; Kärger, Philipp; Hartmann, Melanie; Krause, Daniel; Nauerz, AndreasIn this paper we present the concept of hybrid personalization, the combination of multiple atomic personalization mechanisms. The idea of hybrid personalization is related to hybrid recommender systems, but works on a conceptual level—it is decoupled from the actual adaptation in the user interface. This has as an advantage that one can optimize the adaptation ‘behind the screens’ or—conversely—attach a new visualization mechanism to the personalization technique. We show the practical benefits of this layered, hybrid adaptation mechanisms by means of a case study on personalized curriculum planning where it is recommended which course could or should be followed at which state in the learning process.
- KonferenzbeitragAdaptive Portals: Adapting and Recommending Content and Expertise(16th Workshop on Adaptivity and User Modeling in Interactive Systems, 2008) Nauerz, Andreas; Bakalov, Fedor; König-Ries, Birgitta; Welsch, Martin; Hartmann, Melanie; Krause, Daniel; Nauerz, AndreasToday, Portals provide users with a central point of access to companywide information. Initially they focused on presenting the most valuable and widely used information to users providing them with quick and efficient information access. But the amount of information accessible quickly grew and finding the right information became more and more complex and time consuming. In this paper, we illustrate options for adapting and recommending content based on user- and context models that reflect users’ interests and preferences and on annotations of resources provided by users. We additionally leverage the entire communitys’ interests, preferences and collective intelligence to perform group-based adaptation. We adapt a Portal’s structure (e.g. navigation) and provide recommendations to be able to reach content being of interest easier. We recommend background in- formation, experts and users with similar interests. We finally construct a Portal’s navigation structure entirely based on the communitys’ behavior. Our main concepts have been prototypically embedded within IBM’s WebSphere Portal.
- KonferenzbeitragCapturing the needs of amateur web designers by means of examples(16th Workshop on Adaptivity and User Modeling in Interactive Systems, 2008) Hollink, Vera; de Boer, Victor; van Someren, Maarten; Hartmann, Melanie; Krause, Daniel; Nauerz, AndreasMany sites are created by people who lack professional training in web design. We present ‘SiteGuide’, a tool that helps amateur web designers to decide which information will be included in a new web site and how the information will be organized. SiteGuide takes as input URLs of web sites from the same domain as the site the user wants to create. It automatically searches the pages of these example sites for common topics and common structural features. On the basis of these commonalities it creates a model of the user’s needs. The model can serve as a starting point for the new web site. Also, it can be used to check whether important elements are missing in a concept version of the new site and, if necessary, to adapt the initial design.
- KonferenzbeitragUser Modeling and User Profile Exchange for Semantic Web Applications(16th Workshop on Adaptivity and User Modeling in Interactive Systems, 2008) Abel, Fabian; Henze, Nicola; Krause, Daniel; Plappert, Daniel; Hartmann, Melanie; Krause, Daniel; Nauerz, AndreasThe usage of applications, which are located on the Web, changes the usage of personalization massively: Users interact with most applications seldomly, often just once, but still can benefit from advantages of personalization. We present the User Modeling Service, a service to model a user across various applications. Our service is not restricted to a specific domain and can hence be integrated into arbitrary Web applications. To enable the reuse of user profile data from different applications, we adhere to wellknown Semantic Web technologies. In addition, we developed an easy-to-use Web interface, which allows users to inspect, control, and modify their data. This Web interface is also used to create access policies, which allow users to specify on a fine-grained level which application or Web Service is allowed to access which part of the user profile.
- KonferenzbeitragComputational Intelligence for Communication and Cooperation Guidance in Adaptive E-Learning Systems(16th Workshop on Adaptivity and User Modeling in Interactive Systems, 2008) Köck, Mirjam; Hartmann, Melanie; Krause, Daniel; Nauerz, AndreasAdaptivity has become a prominent research topic during the past decades. There is a variety of application areas where adaptation can add benefit to systems, reaching from shopping portals to e-learning platforms. Despite the large body of work, Computational Intelligence (CI) techniques have been under-explored and therefore also under-exploited within the area of useradaptive systems. This paper discusses the potential of employing CI approaches for the implementation of adaptivity within e-learning systems. Furthermore, it identifies scenarios where these techniques can improve the performance of an adaptive component. Specific focus is placed on the provision of guidance in e-learning systems, in particular with respect to communication/cooperation (as opposed to traditional focus on guiding learners through learning materials).