Serendipität und Open Data. Richtlinien für die Implementierung von Empfehlungssystemen auf Entdeckungsplattformen

From Google's English:  Abstract:  The ever-growing number of scientific publications forces researchers to spend a lot of time finding the resources relevant to their academic work. Discovery platforms provide support by aggregating research data, publications, and other research resources and supporting their discoverability through recommender systems (RS). However, the use of such technologies can lead to certain biases in the selection of resources that are useful for research and can affect the choice of topics to work on, the arguments used, and ultimately the innovation potential of research. These effects are not yet well understood, and there is a lack of concrete recommendations and best practices for the development of RS for scientific discovery platforms. In this paper, guidelines for the application of RS in scientific discovery platforms are formulated, about a possible application in the Open Data Navigator, an open data discovery platform being developed as part of the Swiss project Connectome. The concept of serendipity – the phenomenon of making unexpected but valuable discoveries – is proposed as a touchstone for the usefulness of RS. The recommended guidelines aim to ensure the possibility of experiencing serendipity in a virtual environment as one of the prerequisites for innovative research.