M.Sc. / Guided Research Topic: Analysis of Context Dimensions on Creativity Techniques Recommendations
Master Thesis or Guided Research, Computer Science, Information Systems or related study programs
Introduction & Goals
Creativity techniques are methods that support individuals or teams in developing new ideas or improving products or services. Examples of such techniques are brainstorming, the stimulus word technique and the provocation technique. Choosing the right technique for an idea session is a big challenge. Different factors like the purpose of an idea session, the group size or the background of the participants highly influence the selection.
In previous research, we developed a knowledge-based recommender system which is capable of regarding context dimensions, such as task type, urgency and difficulty to generate appropriate recommendations of creativity techniques. These context dimensions were integrated as filters into the recommendation process, i.e., that a technique is rejected if at least one constraint is not fulfilled. The evaluation of this recommender has shown that this approach considerably limits the number of potential recommendations which may influence the user satisfaction. For this reason, this master thesis should investigate whether these constraints should be relaxed to improve the quality of the recommendations.
If you are interested in this topic, please send your application (CV, transcript of records and a short motivation statement) to Daniel Herzog (herzogd[AT]in.tum.de). Requirements are a strong academic record, interest in recommender systems and creativity techniques and very good programming skills.
Some useful references
Andreas Kammerloher (2017). Ein Recommender System für Kreativitätstechniken. Master’s Thesis. Technical University of Munich.
VanGundy, A. B. (1988). Techniques of Structured Problem Solving. Van Nostrand Reinhold.
Nagasundaram, M., & Bostrom, R. P. (1994). The structuring of creative processes using GSS: a framework for research. Journal of Management Information Systems, 11(3), 87-114.
Adomavicius, Gediminas, and Alexander Tuzhilin. "Toward the next generation of recommender systems: A survey of the state-of-the-art and possible extensions." IEEE transactions on knowledge and data engineering 17.6 (2005): 734-749.