Linked-data based suggestion of relevant topics

In this paper we propose an alternative method for generating topic suggestions for the needs of expert finding in Open Innovation. An important requirement of Open Innovation scenarios is to be able to identify topics lateral to a given innovation problem, and use them to broaden the broadcast of the problem without compromising on relevancy. We propose an approach based on DBpedia -- a Linked Data version of Wikipedia -- which enables us to recommend topics facilitating their proximity in the DBpedia concept graph. Relying on this source we can also filter out certain types of concepts irrelevant to industrial problem solving. We evaluate our approach against the adWords keyword suggestion system here we also show the ability of our system to predict lateral topics that appeared in the actual solutions submitted to past problem challenges. Secondly we evaluate user satisfaction with the proposed keywords from both systems, in terms of relevancy and unexpectedness. Finally we show the significant impact of the use of suggested lateral keywords to the raised awareness about the problem in a real Open Innovation problem broadcast.