Structure-Tags Improve Text Classification for Scholarly Document Quality Prediction.
Gideon Maillette de Buy WennigerThomas van DongenEleri AedmaaHerbert Teun KruitboschEdwin A. ValentijnLambert SchomakerPublished in: CoRR (2020)
Keyphrases
- text classification
- quality prediction
- document classification
- text documents
- term frequency
- bag of words
- keywords
- document collections
- training corpus
- text classifiers
- image quality
- feature selection
- training documents
- text categorization
- semantic features
- information retrieval
- topic discovery
- automatic text classification
- information retrieval systems
- text mining
- data analysis
- metadata
- semantic information
- text data
- document representation
- web documents
- knn
- image data
- social annotations
- machine learning