Leveraging LDA Topic Modeling and BERT Embeddings for Thematic Unsupervised Classification of Tourism News in Rest-Mex Competition.
Erika Rivadeneira-PérezCipriano Callejas-HernándezPublished in: IberLEF@SEPLN (2023)
Keyphrases
- topic modeling
- unsupervised classification
- topic models
- latent dirichlet allocation
- unsupervised learning
- supervised classification
- news articles
- clustering ensemble
- data clustering
- text classification
- latent topics
- remote sensing data
- dimensionality reduction
- text mining
- text documents
- low dimensional
- vector space
- land cover
- latent semantic analysis
- remote sensing images
- lda model
- supervised learning
- bag of words
- hyperspectral images
- generative model
- collaborative filtering
- probabilistic latent semantic analysis
- training set
- object recognition
- pattern recognition