Using 'core documents' for the representation of clusters and topics.
Wolfgang GlänzelBart ThijsPublished in: Scientometrics (2011)
Keyphrases
- document clusters
- document clustering
- document set
- information retrieval
- text documents
- keywords
- information retrieval systems
- latent topics
- topic models
- related documents
- clustering algorithm
- document collections
- similar documents
- highly relevant
- key concepts
- topic detection
- metadata
- newspaper articles
- image representation
- user interests
- document retrieval
- topic specific
- topic discovery
- wikipedia pages
- relevance assessments
- keyphrases
- latent semantic analysis
- document representation
- vector space model
- hierarchical clustering
- vector space
- web documents
- wordnet
- data points