Adult Content Filtering through Compression-Based Text Classification.
Igor SantosPatxi Galán-GarcíaAitor Santamaría-IbirikaBorja Alonso-IslaIker Alabau-SarasolaPablo García BringasPublished in: CISIS/ICEUTE/SOCO Special Sessions (2012)
Keyphrases
- text classification
- feature selection
- text data
- image compression
- data cleaning
- web content
- text categorization
- text mining
- machine learning
- semantic features
- data compression
- text classifiers
- bag of words
- multi label
- filtering algorithm
- knn
- compression algorithm
- user generated content
- digital content
- multimedia
- neural network
- metadata
- information filtering
- image processing
- compression scheme
- labeled data
- compression ratio
- sentiment analysis
- n gram
- semi supervised