biirrr / manifesto

Manifesto on Resource Reuse in Interactive Information Retrieval
1 stars 0 forks source link

Sharing data #4

Open marijnkoolen opened 3 years ago

marijnkoolen commented 3 years ago

(for transparency and future understanding, this message is added based on the discussion of our manifesto during CHIIR 2021, just so the contributions of others are visible and can be used as starting points to update the manifesto where needed.)

Udo Krusewitz: The way the sharing of data is described seems limited to a very academic perspective. There are important differences between research in academia and industry [1]. There many research data in industry that cannot be shared.

David Elsweiler: There is a similar issue with private data.

Marijn Koolen: Yes, our principles state that data sharing should follow laws and regulations, as well as consent from people involved in generating the data. In many or most IIR studies, not all data can be shared, but the aim of researchers, in publishing their work and therefore contributing their knowledge to the community, should be to include as much as can be shared within those constraints.

[1] Karlgren, J. (2019). Adopting systematic evaluation benchmarks in operational settings. In Information Retrieval Evaluation in a Changing World (pp. 583-590). Springer, Cham. https://link.springer.com/chapter/10.1007%2F978-3-030-22948-1_25 (https://www.diva-portal.org/smash/get/diva2:1503901/FULLTEXT01.pdf)