Detecting Sexism in German Online Newspaper Comments with Open-Source Text Embeddings (Team GDA, GermEval2024 Shared Task 1: GerMS-Detect, Subtasks 1 and 2, Closed Track)

Florian Bremm, Patrick Gustav Blaneck, Tobias Bornheim, Niklas Grieger, Stephan Bialonski
9/16/2024
cs.CL

No official code found. Best implementation: dslaborg/germeval2024 (1 star, Apache-2.0, last commit 2024-07-25).

Abstract

Sexism in online media comments is a pervasive challenge that often manifests subtly, complicating moderation efforts as interpretations of what constitutes sexism can vary among individuals. We study monolingual and multilingual open-source text embeddings to reliably detect sexism and misogyny in German-language online comments from an Austrian newspaper. We observed classifiers trained on text embeddings to mimic closely the individual judgements of human annotators. Our method showed robust performance in the GermEval 2024 GerMS-Detect Subtask 1 challenge, achieving an average macro F1 score of 0.597 (4th place, as reported on Codabench). It also accurately predicted the distribution of human annotations in GerMS-Detect Subtask 2, with an average Jensen-Shannon distance of 0.301 (2nd place). The computational efficiency of our approach suggests potential for scalable applications across various languages and linguistic contexts.

View on arXivView PDF

Code Implementations(1)

dslaborg/germeval2024Community100%
Apache-2.0
10Jupyter NotebookJul 2, 20242 years agoApache-2.0

Similar Papers

Bilingual Sexism Classification: Fine-Tuned XLM-RoBERTa and GPT-3.5 Few-Shot Learning

84% match2024

Anti-Sexism Alert System: Identification of Sexist Comments on Social Media Using AI Techniques

84% match2023

Explaining Matters: Leveraging Definitions and Semantic Expansion for Sexism Detection

83% match2025

Stanford MLab at SemEval-2023 Task 10: Exploring GloVe- and Transformer-Based Methods for the Explainable Detection of Online Sexism

83% match2023

FHSTP@EXIST 2025 Benchmark: Sexism Detection with Transparent Speech Concept Bottleneck Models

83% match2025

Beyond Binary Classification: Detecting Fine-Grained Sexism in Social Media Videos

82% match2026

Cite this paper

@article{bremm2024detecting,
  title  = {Detecting Sexism in German Online Newspaper Comments with Open-Source Text Embeddings (Team GDA, GermEval2024 Shared Task 1: GerMS-Detect, Subtasks 1 and 2, Closed Track)},
  author = {Florian Bremm and Patrick Gustav Blaneck and Tobias Bornheim and Niklas Grieger and Stephan Bialonski},
  year   = {2024},
  eprint = {2409.10341},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2409.10341v2}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2409.10341.svg)](https://codeofpaper.com/paper/2409.10341)

Discussion