ASCEND combines thresholded supervised contrastive learning, word-level attention, and sentiment, emotion, and toxicity features to detect implicit sexism, reporting top macro-F1 scores on EXIST 2021 and MLSC.
User-aware multilingual abusive content detection in social media,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
baseline 1
citation-polarity summary
fields
cs.CL 1years
2025 1verdicts
REJECT 1roles
baseline 1polarities
baseline 1representative citing papers
citing papers explorer
-
An Adaptive Supervised Contrastive Learning Framework for Implicit Sexism Detection in Digital Social Networks
ASCEND combines thresholded supervised contrastive learning, word-level attention, and sentiment, emotion, and toxicity features to detect implicit sexism, reporting top macro-F1 scores on EXIST 2021 and MLSC.