Franziska Sofia Hafner

According to our database, Franziska Sofia Hafner authored at least 5 papers between 2024 and 2025.

Collaborative distances:

• Dijkstra number of five.
• Erdős number of four.

2025

'Slightly disappointing' vs. 'worst sh** ever': tackling cultural differences in negative sentiment expressions in AI-based sentiment analysis.

Franziska Sofia Hafner, Lena Hafner, Roberto Corizzo

J. Comput. Soc. Sci., August, 2025

Training language models to be warm and empathetic makes them less reliable and more sycophantic.

Lujain Ibrahim, Franziska Sofia Hafner, Luc Rocher

CoRR, July, 2025

Gender Trouble in Language Models: An Empirical Audit Guided by Gender Performativity Theory.

Franziska Sofia Hafner, Ana Valdivia, Luc Rocher

Proceedings of the 2025 ACM Conference on Fairness, Accountability, and Transparency, 2025

2024

Mitigating social bias in sentiment classification via ethnicity-aware algorithmic design.

Roberto Corizzo, Franziska Sofia Hafner

Soc. Netw. Anal. Min., December, 2024

Equal accuracy for Andrew and Abubakar - detecting and mitigating bias in name-ethnicity classification algorithms.

Lena Hafner, Theodor Peter Peifer, Franziska Sofia Hafner

AI Soc., August, 2024