Preference extraction

Notes on how to improve the data collection process in the hackathon platform.


The UZH team with input from BFH have started working on the algorithm coding. The first two tests are in April 2025, both will use a simple skill typology provided by event organizers. We look towards developing a general nested category scheme.

Survey forms will be used to collect data from these first experiments. However, Dribdat recently got a feature to convert resume data from LinkedIn or other sites. Combined with texts of the user profiles ("My Story"), their tags, and challenge descriptions, Dribdat should be able to provide this directly for future tests.

It would be especially interesting to be able to extract skills-tags from text automatically, so that users can just approve and make changes rather than having to make extra effort. We will propose some ways of doing this in issue #485.

All attendees, sponsors, partners, volunteers and staff at our hackathon are required to agree with the Hack Code of Conduct. Organisers will enforce this code throughout the event. We expect cooperation from all participants to ensure a safe environment for everybody.

The contents of this website, unless otherwise stated, are licensed under a Creative Commons Attribution 4.0 International License. The application that powers this site is available under the MIT license.