Research at Know-Center for the Mobility Programme

If you are interested to work with us please contact: Stefanie Lindstaedt; Head of Research Unit Knowledge Services; Know-Center, Inffeldgasse 21a, 8010 Graz, Austria; email: slind@know-center.at

 TEL research at the Know-Center is primarily focused on Professional Learning (or workplace learning). We are interested in exploring how people learn during work (work-integrated learning), which barriers they encounter, and design support mechanisms to improve the effectiveness of professional learning. Together with FHG FIT (Martin Wolpers) we are running a special interest group on professional technology enhanced learning (http://www.sig-protel.eu).

We are an interdisciplinary research team in which computer scientists, psychologist, and information management researchers work closely together to create innovative professional learning solutions and to evaluate them in real work settings.

 We welcome PhD students who are interested in pursuing one of the following research challenges (or closely related ones) in close collaboration with our research team and related to some of our ongoing projects (e.g. APOSDLE, MATURE). We are specifically interested in hosting students who bring in new perspectives on these topics: 

(1) Constructing a conceptual framework for professional learning support: A large variety of studies has been performed to understand the anatomy of knowledge work, its characteristics and challenges. In order to build useful and usable computational support for professional learning, we need to build on these insights and create a framework that informs the design of computational support mechanisms. One approach which we are pursuing in this context is work-integrated learning. Examples of research activities are:

  • Performing in-depth studies of knowledge work and professional learning within one of our partner companies
  • Evaluating professional learning solutions within real world settings
  • Exploring and improving our conceptual models on work-integrated learning

(2) Getting to know the user: In order to effectively support a learner within her current work situation we need to get a good understanding of her (short term) tasks, goals, and needs; and in relationship to her (long term) prior knowledge, experiences, and interest build up over time (competency maintenance). This has to be achieved as much as possible automatically in the background without bothering her (too much). Example activties could include:

  • Researching user context detection approaches and developing related services
  • Researching user profile maintenance approaches and developing related services
  • Performing real world or lab experiments

(3) Offering contextualized, flexible, and integrated professional learning support: Monolithic knowledge management and learning management systems have proven too inflexible. We need to develop computational knowledge work support that is flexible, contextualized to the individual user, and taps into the organizational and social network of the user. This support needs to go beyond the dichotomy of working and learning and provide integrated support for both activities. Example activities could include:

  • Applying social network approaches to different aspects of professional learning
  • Researching recommender services for TEL and improving existing approaches by integrating semantic as well as text-based retrieval algorithms
  • Performing real world or lab experiments

 (4) Utilizing emergent knowledge structures: Traditionally knowledge work and knowledge engineering have been seen as two separate activities within an organization – typically performed by different people. In order to enable organizations to keep up with their rapidly changing environment, we need to support the individual knowledge worker to contribute to the emerging knowledge structures and improve knowledge maturing processes. Example activities could include:

  • Using exisiting knowledge maturing studies and survey results to add to a knowledge maturing process model
  • Utilizing Web 2.0 approaches to enable people to overtime evolve knowledge structures
  • Performing real world or lab experiments

If interested the PhD students will have the opportunity to work with the following two technological frameworks and (if applicable) apply them to their own research interests:

  • KnowSe: A framework of a large variety of (partially web-based) knowledge services. Our knowledge services analyze and make explicit the various relationships between three knowledge entities: agents (people or services), content (e.g. documents), and semantic structures (e.g. domain ontology, user profile). In doing so, adding knowledge to at least one of the three dimensions. Examples for KnowSe services include context detection services, user or community profile maintenance services, and semantic enrichment services. 
  • KnowMiner: An extensive service-based knowledge discovery framework which implements a large variety of text-analysis and machine learning algorithms (including all pre-processing steps). Examples of KnowMiner services include clustering services, object recognition services, and summarization services. KnowMiner is especially optimized for handling and processing huge amounts of unstructured textual data.