Comparer des méthodes

	Modèle de Topic NMF Explicable	Modèle de Topics LDA Explicable
Domaine	Apprentissage profond	Apprentissage profond
Famille	Machine learning	Machine learning
Année d'origine	2001 (NMF); XAI integration ~2017–present	2003 (LDA); 2018–present (explainability extensions)
Auteur d'origine	Lee, D. D. & Seung, H. S. (NMF); XAI layer attributed to community practice post-2016	Blei, D. M., Ng, A. Y., & Jordan, M. I. (LDA seminal); explainability extensions by multiple authors
Type	Interpretable unsupervised topic model	Probabilistic generative topic model with interpretability enhancements
Source fondatrice	Lee, D. D., & Seung, H. S. (2001). Algorithms for non-negative matrix factorization. Advances in Neural Information Processing Systems, 13, 556–562.	Blei, D. M., Ng, A. Y., & Jordan, M. I. (2003). Latent Dirichlet Allocation. Journal of Machine Learning Research, 3, 993–1022.
Alias	XAI-NMF, interpretable NMF topic model, explainable NMF, transparent NMF topic modeling	Explainable LDA, Interpretable LDA, XAI-LDA, Transparent Topic Model
Apparentées	6	4
Résumé	An Explainable NMF Topic Model combines Non-negative Matrix Factorization — a parts-based decomposition of a document-term matrix — with explicit interpretability techniques such as coherence metrics, word contribution scores, and SHAP-style attribution to make discovered topics transparent and auditable by human readers.	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.