A MapReduce based parallel SVM for large scale spam filtering.
Godwin CaruanaMaozhen LiMan QiPublished in: FSKD (2011)
Keyphrases
- spam filtering
- string kernels
- spam classification
- parallel processing
- support vector machine svm
- feature mapping
- support vector
- text classification
- high performance data mining
- parallel programming
- distributed processing
- parallel computing
- support vector machine
- machine learning models
- knn
- anti spam
- data parallelism
- data intensive
- cloud computing
- machine learning
- spam detection
- data partitioning
- spam filters
- map reduce
- real world
- shared memory
- parallel algorithm
- svm classifier
- multi class
- training data
- feature selection
- artificial intelligence
- parallel computation
- distributed memory
- support vectors
- parallel implementation
- hyperplane
- information extraction
- feature vectors
- mapreduce framework
- neural network