방법 비교
선택한 방법을 나란히 검토하세요. 서로 다른 행은 강조 표시됩니다.
| 준지도 학습 감성 분석× | 자기 지도 감성 분석× | |
|---|---|---|
| 분야 | 딥러닝 | 딥러닝 |
| 계열 | Machine learning | Machine learning |
| 기원 연도≠ | 2002–2008 | 2019–present |
| 창시자≠ | Zhu, X.; Pang, B. & Lee, L. (foundational works) | Devlin et al. (BERT paradigm); extended by Sun et al. and others |
| 유형≠ | Semi-supervised classification | Pre-train then fine-tune NLP pipeline |
| 원전≠ | Zhu, X. (2005). Semi-Supervised Learning Literature Survey. Technical Report 1530, Computer Sciences, University of Wisconsin-Madison. link ↗ | Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2019). BERT: Pre-training of deep bidirectional transformers for language understanding. In Proceedings of NAACL-HLT 2019 (pp. 4171–4186). Association for Computational Linguistics. DOI ↗ |
| 별칭 | SSSA, semi-supervised opinion mining, label-propagation sentiment classification, self-training sentiment analysis | SSL-based sentiment analysis, self-supervised opinion mining, pre-training for sentiment, unsupervised pre-training sentiment |
| 관련≠ | 4 | 2 |
| 요약≠ | Semi-supervised sentiment analysis combines a small set of manually labeled text samples with a large pool of unlabeled text to train opinion classifiers. By propagating sentiment signals from labeled seeds to unlabeled data through self-training, label propagation, or consistency regularization, the approach achieves competitive accuracy without the cost of labeling large corpora. | Self-supervised sentiment analysis combines large-scale unsupervised pre-training — through objectives such as masked language modeling or contrastive prediction — with fine-tuning on a small labeled sentiment corpus. The approach, popularized by BERT and its variants, dramatically reduces the need for hand-labeled data while achieving state-of-the-art accuracy on positive/negative/neutral opinion classification tasks. |
| ScholarGate데이터셋 ↗ |
|
|