방법 비교

	BERT 임베딩	Doc2Vec	GloVe 임베딩	감성 분석
분야	텍스트 마이닝	텍스트 마이닝	텍스트 마이닝	텍스트 마이닝
계열	Process / pipeline	Process / pipeline	Process / pipeline	Process / pipeline
기원 연도	2019	2014	2014	—
창시자	Devlin, Chang, Lee & Toutanova (Google AI)	Quoc V. Le & Tomas Mikolov	Pennington, Socher & Manning	—
유형	Contextual transformer text-representation method	Document-embedding representation learning	Static word-embedding model	NLP text-classification task
원전	Devlin, J., Chang, M.-W., Lee, K. & Toutanova, K. (2019). BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. NAACL-HLT, 4171-4186.	Le, Q. V. & Mikolov, T. (2014). Distributed Representations of Sentences and Documents. Proceedings of the 31st International Conference on Machine Learning (ICML), 1188-1196.	Pennington, J., Socher, R. & Manning, C. D. (2014). GloVe: Global Vectors for Word Representation. EMNLP.	Pang, B. & Lee, L. (2008). Opinion Mining and Sentiment Analysis. Foundations and Trends in Information Retrieval, 2(1-2), 1-135.
별칭	contextual embeddings, transformer embeddings, BERT Tabanlı Metin Gömülmeleri	paragraph vector, document embeddings, Doc2Vec Belge Gömülmeleri	GloVe, global vectors, GloVe Kelime Gömülmeleri	opinion mining, polarity detection, duygu analizi
관련	4	4	3	3
요약	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.	Doc2Vec, also known as Paragraph Vector, is a representation-learning method introduced by Le and Mikolov (2014) that maps whole documents to fixed-length dense vectors. These vectors place similar documents close together in space, supporting document comparison and classification.	GloVe (Global Vectors for Word Representation) is a static word-embedding model introduced by Pennington, Socher and Manning (2014) that learns word vectors directly from global word-word co-occurrence statistics gathered across an entire corpus. The resulting vectors place semantically related words close together and perform strongly on semantic analogy tasks.	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.