Improving tweet clustering using bigrams formed from word associations.
Khadija Ali VakeelShubhamoy DeyPublished in: RACS (2015)
Keyphrases
- n gram
- named entities
- clustering algorithm
- k means
- co occurrence
- language model
- clustering method
- bag of words
- social media
- word segmentation
- data clustering
- information theoretic
- self organizing maps
- latent topics
- categorical data
- hierarchical clustering
- cluster analysis
- sentiment analysis
- document clustering
- social networks
- question answering
- web documents
- unsupervised learning
- association rules
- training corpus