Stefanie N. Lindstaedt

Sustaining TEL: From Innovation to learning and practice

Wolpers, M., Kirschner, P. A., Scheffel, M., Lindstaedt, S., & Dimitrova, V. (Eds.) (2010). Sustaining TEL: From Innovation to learning and practice. Proceedings of the 5th European Conference on Technology Enhanced Learning, EC-TEL 2010. September, 28 - October, 1, 2010, Barcelona, Spain. Berlin: Springer Verlag.Scaffolding is a well-known approach to bridge the gap between novice and expert capabilities in a discovery-oriented learning environment. This paper discusses a set of knowledge representations referred to as Learning Spaces (LSs) that can be used to support learners in acquiring conceptual knowledge of system behaviour. The LSs are logically self-contained, meaning that models created at a specific LS can be simulated. Working with the LSs provides scaffolding for learners in two ways. First, each LS provides a restricted set of representational primitives to express knowledge, which focus the learner’s knowledge construction process. Second, the logical consequences of an expression derived upon simulating, provide learners a reflective instrument for evaluating the status of their understanding, to which they can react accordingly. The work presented here is part of the DynaLearn project, which builds an Interactive Learning Environment to study a constructive approach to having learners develop a qualitative understanding of how systems behave. The work presented here thus focuses on tools to support educational research. Consequently, user-oriented evaluation of these tools is not a part of this paper.

MoKi: The Enterprise Modelling Wiki

Enterprise modelling focuses on the construction of a structured description, the so-called enterprise model , which represents aspects relevant to the activity of an enterprise. Although it has become clearer recently that enterprise modelling is a collaborative activity, involving a large number of people, most of the enterprise modelling tools still only support very limited degrees of collaboration. Within this contribution we describe a tool for enterprise modelling, called MoKi (MOdelling wiKI), which supports agile collaboration between all different actors involved in the enterprise modelling activities. MoKi is based on a Semantic Wiki and enables actors with different expertise to develop an enterprise model not only using structural (formal) descriptions but also adopting more informal and semi-formal descriptions of knowledge.

Automatic image annotation using visual content and folksonomies

Automatic image annotation is an important and challenging task, and becomes increasingly necessary when managing large image collections. This paper describes techniques for automatic image annotation that take advantage of collaboratively annotated image databases, so called visual folksonomies. Our approach applies two techniques based on image analysis: First, classification annotates images with a controlled vocabulary and second tag propagation along visually similar images. The latter propagates user generated, folksonomic annotations and is therefore capable of dealing with an unlimited vocabulary. Experiments with a pool of Flickr images demonstrate the high accuracy and efficiency of the proposed methods in the task of automatic image annotation. Both techniques were applied in the prototypical tag recommender “tagr”.

21st Century Learning for 21st Century Skills

I want to argue in this lecture, that life – especially educational life – is never that simple. What exactly are 21 century skills? How, for example, do they differ from ‘knowledge’? And once we know what they are, does there follow a strategy – or at least a set of principles – for what learning should look like, and the roles we ascribe to technology? Most importantly, if 21 century knowledge is qualitatively different from the 19 and 20 century knowledge that characterises much of our existing curricula, we will need to consider carefully just how to make that knowledge learnable and accessible through the design of digital technologies and their evaluation.

Recommending Tags for Pictures Based on Text, Visual Content and User Context

Imagine you are member of an online social system and want to upload a picture into the community pool. In current social software systems, you can probably tag your photo, share it or send it to a photo printing service and multiple other stuff. The system creates around you a space full of pictures, other interesting content (descriptions, comments) and full of users as well. The one thing current systems do not do, is understand what your pictures are about. We present here a collection of functionalities that make a step in that direction when put together to be consumed by a tag recommendation system for pictures. We use the data richness inherent in social online environments for recommending tags by analysing different aspects of the same data (text, visual content and user context). We also give an assessment of the quality of thus recommended tags.

Recommending Knowledgeable People in a Work-Integrated Learning System

According to studies into learning at work, interpersonal help seeking is the most important strategy of how people acquire knowledge at their workplaces. Finding knowledgeable persons, however, can often be difficult for several reasons. Expert finding systems can support the process of identifying knowledgeable colleagues thus facilitating communication and collaboration within an organization. In order to provide the expert finding functionality, an underlying user model is needed that represents the characteristics of each individual user. In our article we discuss requirements for user models for the workintegrated learning (WIL) situation. Then, we present the APOSDLE People Recommender Service which is based on an underlying domain model, and on the APOSDLE User Model. We describe the APOSDLE People Recommender Service on the basis of the Intuitive Domain Model of expert finding systems, and explain how this service can support interpersonal help seeking at workplaces.

Conceptual Foundations for a Service-oriented Knowledge and Learning Architecture: Supporting Content, Process and Ontology Maturing

Effective learning support in organizations requires a flexible and personalized toolset that brings together the individual and the organizational perspective on learning. Such toolsets need a service-oriented infrastructure of reusable knowledge and learning services as an enabler. This contribution focuses on conceptual foundations for such an infrastructure as it is being developed within the MATURE IP and builds on the knowledge maturing process model on the one hand, and the seeding-evolutionary growth-reseeding model on the other hand. These theories are used to derive maturing services, for which initial examples are presented.

Use and Influence of Creative Ideas and Requirements for a Work-Integrated Learning System

In this paper, we describe a creativity workshop that was used in a large research project, called APOSDLE, to generate creative ideas and requirements for a work-integrated learning system. We present an analysis of empirical data collected during and after the workshop. On the basis of this analysis, we conclude that the work-shop was an efficient way of generating ideas for future system development. These ideas, on average, were used at least as much as requirements from other sources in writing use cases, and 18 months after the workshop were seen to have a similar degree of influence on the project to other requirements. We make some observations about the use of more and less creative ideas, and about the techniques used to generate them. We end with suggestions for further work.

Knowledge Maturing in the Semantic MediaWiki: A Design Study in Career Guidance

The evolutionary process in which knowledge objects are transformed from informal and highly contextualized artefacts into explicitly linked and formalized learning objects, together with the corresponding organisational learning processes, have been termed Knowledge Maturing. Whereas wikis and other tools for collaborative building of knowledge have been suggested as useful tools in this context, they lack several features for supporting the knowledge maturing process in organisational settings. To overcome this, we have developed a prototype based on Semantic MediaWiki which enhances the wiki with various maturing functionalities like maturing indicators or mark-up support.

Analysis of machine learning techniques for context extraction

dasiaContext is keypsila conveys the importance of capturing the digital environment of a knowledge worker. Knowing the userpsilas context offers various possibilities for support, like for example enhancing information delivery or providing work guidance. Hence, user interactions have to be aggregated and mapped to predefined task categories. Without machine learning tools, such an assignment has to be done manually. The identification of suitable machine learning algorithms is necessary in order to ensure accurate and timely classification of the userpsilas context without inducing additional workload. This paper provides a methodology for recording user interactions and an analysis of supervised classification models, feature types and feature selection for automatically detecting the current task and context of a user. Our analysis is based on a real world data set and shows the applicability of machine learning techniques.