In this final HaSPI blog post, we look back at the project and present our key results. HaSPI applies imitation learning to the moderation of German-language online forums, making it possible to identify which words contribute most to a moderation de...

In this blogpost, we present the main results of Felix Krejca's master's thesis, which was carried out as part of the project.

Introducing HaSPI: We're developing an automatic content moderation system for German-language posts using imitation learning to help detect harmful content more effectively. By training AI on real-world data, our system aims to reduce the burden on ...