Performance evaluation of Latent Dirichlet Allocation in text mining
2011pp. 2695–2698
Citations Over TimeTop 20% of 2011 papers
Abstract
This paper introduces three classic models of statistical topic models: Latent Semantic Indexing (LSI), Probabilistic Latent Semantic Indexing (PLSI) and Latent Dirichlet Allocation (LDA). Then a method of text classification based on LDA model is briefly described, which uses LDA model as a text representation method. Each document means a probability distribution of fixed latent topic sets. Next, Support Vector Machine (SVM) is chose as classification algorithm. Finally, the evaluation parameters in classification system of LDA with SVM are higher than other two methods which are LSI with SVM and VSM with SVM, showing a better classification performance.
Related Papers
- → A Survey of Topic Modeling in Text Mining(2015)364 cited
- → Latent Dirichlet Allocation - An approach for topic discovery(2022)18 cited
- → Applying Latent Dirichlet Allocation to Automatic Essay Grading(2006)39 cited
- → A Study of Topic Modeling Methods(2018)24 cited
- Broadcast News Story Segmentation Using Manifold Learning on Latent Topic Distributions(2013)