Comparer des méthodes

	Embeddings BERT	Analyse des sentiments	Apprentissage par transfert
Domaine	Fouille de textes	Fouille de textes	Apprentissage automatique
Famille	Process / pipeline	Process / pipeline	Machine learning
Année d'origine	2019	—	2010 (formalized); 1990s (early roots)
Auteur d'origine	Devlin, Chang, Lee & Toutanova (Google AI)	—	Pan, S. J. & Yang, Q. (survey); Bengio, Y. (deep learning framing)
Type	Contextual transformer text-representation method	NLP text-classification task	Learning paradigm
Source fondatrice	Devlin, J., Chang, M.-W., Lee, K. & Toutanova, K. (2019). BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. NAACL-HLT, 4171-4186.	Pang, B. & Lee, L. (2008). Opinion Mining and Sentiment Analysis. Foundations and Trends in Information Retrieval, 2(1-2), 1-135.	Pan, S. J., & Yang, Q. (2010). A Survey on Transfer Learning. IEEE Transactions on Knowledge and Data Engineering, 22(10), 1345–1359.
Alias	contextual embeddings, transformer embeddings, BERT Tabanlı Metin Gömülmeleri	opinion mining, polarity detection, duygu analizi	TL, domain adaptation, fine-tuning, pre-trained model adaptation
Apparentées	4	3	3
Résumé	BERT-based text embeddings, introduced by Devlin and colleagues at Google AI in 2019, turn text into context-sensitive dense vectors using a bidirectional Transformer encoder. Because the meaning of a word shifts with its context, BERT produces richer representations than static methods such as Word2Vec or topic models like LDA.	Sentiment analysis, also called opinion mining, is a natural-language-processing task that detects the emotional tone of text — typically classifying it as positive, negative, or neutral. It turns unstructured opinion text into structured, quantifiable polarity signals using one of three families of approaches: sentiment lexicons, trained machine-learning classifiers, or pretrained transformer models.	Transfer learning is a machine learning paradigm in which knowledge gained from training a model on a source task or domain is reused to improve learning on a different but related target task or domain. It is especially powerful when labeled data for the target task is scarce, and it underlies most modern deep learning applications in computer vision, natural language processing, and beyond.