Beyond Binary Classification: Detecting Fine-Grained Sexism in Social Media Videos
#sexism detection #multimodal AI #fine‑grained classification #online misogyny #social media videos #machine learning #NLP #computer vision
📌 Key Takeaways
- Online sexism manifests in diverse, often subtle forms.
- Current automated detection tools are limited to binary (sexist vs. non‑sexist) classification.
- FineMuSe introduces fine‑grained, context‑sensitive labels to capture nuanced sexism.
- The framework employs multimodal analysis, leveraging multiple data sources.
- The approach targets social media videos, a common platform for misogynistic content.
- The study aims to improve detection accuracy and reduce unnoticed sexist manifestations.
📖 Full Retelling
This study, posted on arXiv in February 2026, presents FineMuSe—a multimodal framework designed to detect fine‑grained sexism in social media videos. The authors argue that sexism appears in various subtle forms, which makes it challenging to identify with existing automated tools that typically rely on binary classification. Their contribution is to provide a context‑sensitive labeling system capable of uncovering nuanced sexist content beyond overt examples.
🏷️ Themes
Gender discrimination, AI ethics, Multimodal machine learning, Online harassment, Content moderation, Natural language processing, Computer vision
Entity Intersection Graph
No entity connections available yet for this article.
Original Source
arXiv:2602.15757v1 Announce Type: cross
Abstract: Online sexism appears in various forms, which makes its detection challenging. Although automated tools can enhance the identification of sexist content, they are often restricted to binary classification. Consequently, more subtle manifestations of sexism may remain undetected due to the lack of fine-grained, context-sensitive labels. To address this issue, we make the following contributions: (1) we present FineMuSe, a new multimodal sexism de
Read full article at source