Spam detection on social networks using cost-sensitive feature selection and ensemble-based regularized deep neural networks.
Aliaksandr BarushkaPetr HájekPublished in: Neural Comput. Appl. (2020)
Keyphrases
- cost sensitive
- spam detection
- feature selection
- neural network
- fraud detection
- social networks
- multi class
- naive bayes
- base classifiers
- support vector machine
- web graph
- cost sensitive learning
- misclassification costs
- cost sensitive classification
- class imbalance
- class distribution
- text classification
- classification accuracy
- ensemble classifier
- text categorization
- social network analysis
- active learning
- feature ranking
- spam filtering
- feature set
- feature extraction
- feature subset
- network structure
- machine learning
- rule extraction
- training data
- ensemble methods
- support vector
- complex networks
- k nearest neighbor
- boosting algorithms
- data sets
- random walk
- unsupervised learning
- knn
- link prediction