BERT-based Classifiers for Fake News Detection on Short and Long Texts with Noisy Data: A Comparative Analysis.
Elena ShushkevichMikhail AlexandrovJohn CardiffPublished in: TSD (2022)
Keyphrases
- noisy data
- training data
- keywords
- noise tolerant
- missing data
- short texts
- news articles
- learning from noisy data
- noise free
- training set
- high dimensional
- detection rate
- object detection
- neural network
- classification algorithm
- social media
- support vector
- decision trees
- naive bayes
- class labels
- anomaly detection
- change detection
- input data
- feature vectors
- ensemble learning
- discriminative classifiers
- data mining
- data sets