Comparer des méthodes

	Modèle de Topics LDA Explicable	Factorisation de Matrices Non-Négatives (NMF)
Domaine	Apprentissage profond	Apprentissage automatique
Famille	Machine learning	Latent structure
Année d'origine	2003 (LDA); 2018–present (explainability extensions)	1999
Auteur d'origine	Blei, D. M., Ng, A. Y., & Jordan, M. I. (LDA seminal); explainability extensions by multiple authors	Lee, D. D. & Seung, H. S.
Type	Probabilistic generative topic model with interpretability enhancements	Matrix decomposition with non-negativity constraints
Source fondatrice	Blei, D. M., Ng, A. Y., & Jordan, M. I. (2003). Latent Dirichlet Allocation. Journal of Machine Learning Research, 3, 993–1022.	Lee, D. D., & Seung, H. S. (1999). Learning the parts of objects by non-negative matrix factorization. Nature, 401(6755), 788–791.
Alias	Explainable LDA, Interpretable LDA, XAI-LDA, Transparent Topic Model	NMF, NNMF, nonnegative matrix factorization, non-negative matrix approximation
Apparentées	4	4
Résumé	Explainable LDA combines Latent Dirichlet Allocation — the canonical probabilistic topic model introduced by Blei, Ng, and Jordan in 2003 — with post-hoc and intrinsic interpretability tools that make each discovered topic auditable, labeled, and trustworthy for human reviewers. It is widely used in NLP, social science text analysis, and computational humanities where transparency is required alongside discovery.	Non-negative Matrix Factorization (NMF) is a family of algorithms, introduced by Lee and Seung in their landmark 1999 Nature paper, that decomposes a non-negative data matrix V into the product of two lower-rank non-negative matrices W (basis components) and H (encoding coefficients). Unlike PCA or SVD, the non-negativity constraint forces the algorithm to learn strictly additive, parts-based representations, making the factors directly interpretable as building blocks of the original data.