Enhancing social network hate detection using back translation and GPT-3 augmentations during training and test-time.
Seffi CohenDan PresilOr KatzOfir ArbiliShvat MessicaLior RokachPublished in: Inf. Fusion (2023)
Keyphrases
- social networks
- detection algorithm
- object detection
- social interaction
- automatic detection
- training set
- detection method
- social media
- training process
- false alarms
- detection rate
- personal interests
- neural network
- survey instrument
- statistical significance
- detection accuracy
- social networking
- statistically significant
- social network analysis
- test set
- anomaly detection
- random walk
- supervised learning