Bengali sentiment analysis models exhibit persistent identity-based biases across datasets and developer backgrounds despite similar semantic content.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
roles
background 1polarities
background 1representative citing papers
A fairness-aware multi-group target detection approach reduces bias across groups and outperforms existing fairness-aware baselines in toxicity detection tasks.
citing papers explorer
-
How do datasets, developers, and models affect biases in a low-resourced language?: The Case of the Bengali Language
Bengali sentiment analysis models exhibit persistent identity-based biases across datasets and developer backgrounds despite similar semantic content.
-
Fairness-Aware Multi-Group Target Detection in Online Discussion
A fairness-aware multi-group target detection approach reduces bias across groups and outperforms existing fairness-aware baselines in toxicity detection tasks.