한국어 코퍼스에서 딥러닝 기반 감성 분석 모델
Deep Learning-based Sentimental Analysis Model in Korean Corpus
1
조회
0
다운로드
1
인용
0
참고문헌
키워드
초록
본 연구는 한국어 코퍼스에서 딥러닝 기반의 감성 분석 모델을 분석하고, 주요 연구 성과와 기술 발전을 논의한다. 감성 분석은 텍스트에서 주관적 정보를 추출하고 분류하는 과정으로, 딥러닝의 발전은 감성 분석 분야에서 많은 변화를 가져왔다. 전통적인 감성 분석 방법으로 시작하여, RNN과 CNN을 활용한 초기 딥러닝 모델의 발전을 살펴보며, Transformer 기반 모델을 통해 텍스트의 복잡한 문맥 이해와 처리 능력을 크게 향상시킨 과정을 분석한다. 이 과정에서 BERT와 GPT 등의 모델은 높은 성능을 보이며, 다양한 언어와 도메인으로의 확장 가능성을 보인다. 또한 다중 언어 및 도메인 감성 분석의 연구 동향을 분석하며, Zero-shot 및 transfer learning을 활용한 사례를 통해 모델의 일반화 능력을 높이는 방법을 제안한다. 더불어서, 주요 데이터셋과 평가지표에 대해서도 소개한다. 마지막으로, 실제 응용에서의 윤리적 문제 등 여러 도전 과제에 대해 언급하며, 향후 연구 방향을 제시한다.
Abstract
This study comprehensively analyzes the emotional analysis model using deep learning in the Korean corpus, and discusses major research achievements and technological advances. Emotional analysis is the process of extracting and classifying subjective information from text, and the development of deep learning has brought many changes in the field of emotional analysis. Starting with the traditional emotional analysis method, the development of early deep learning models using RNN and CNN is examined, and the process of greatly improving the complex context understanding and processing ability of text through Transformer-based models is analyzed. In this process, models such as BERT and GPT show high performance and potential for expansion to various languages and domains. In addition, it analyzes the research trends of multi-lingual and domain emotional analysis and discusses how to increase the generalization ability of the model through cases using zero-shot and transfer learning. In addition, it also introduces major datasets and evaluation indicators. Finally, it mentions various challenges such as ethical issues in practical applications and suggests future research directions.
참고문헌 (20)
- M. Wankhade, "A survey on sentiment analysis methods, applications, and challenges", Artificial Intelligence Review, 55(7), pp.5731~5780 (2022)
- M. Birjali, "A comprehensive survey on sentiment analysis: Approaches, challenges and trends", Knowledge-Based Systems, 226, pp.107134~ (2021)
- S. Dong, "A survey on deep learning and its applications", Computer Science Review, 40, pp.100379~ (2021)
- W. Van Atteveldt, "The validity of sentiment analysis : Comparing manual annotation, crowd-coding, dictionary approaches, and machine learning algorithms", Communication Methods and Measures, 15(2), pp.121~140 (2021)
- A. Mitra, "Sentiment analysis using machine learning approaches", Journal of Ubiquitous Computing and Communication Technologies (UCCT), 2(03), pp.145~152 (2020)
- R. DiPietro, "Handbook of medical image computing and computer assisted intervention", pp.503~519 (2020), Academic Press
- I. Priyadarshini, "A novel LSTM–CNN–grid search-based deep neural network for sentiment analysis", The Journal of Supercomputing, 77(12), pp.13911~13932 (2021)
- A. Vaswani, "Attention is all you need", Advances in neural information processing systems, 30 (2017)
- J. Delvin, "BERT : Pre-training of Deep Bidirectional Transformers for Language Understanding", Proceedings of naacL-HLT, 1, pp.4171~4186 (2019)
- "Improving Language Understanding by Generative Pre-Training" (2018)[URL]
- "Language Models are Few-Sot Learners" (2020)[URL]
- (2024)[URL]
- "GPT-4 Technical Report" (2024)[URL]
- F. Pourpanah, "A review of generalized zero-shot learning methods", IEEE transactions on pattern analysis and machine intelligence, 45(4), pp.4051~4070 (2022)
- C. Raffel, "Exploring the limits of transfer learning with a unified text-to-text transformer", The Journal of Machine Learning Research, 21(1), pp.5485~5551 (2020)
- D. Valero-Carreras, "Comparing two SVM models through different metrics based on the confusion matrix", Computers & Operations Research, 152, pp.106131~ (2023)
- S. E. Lee, "Pose Pattern Mining using Transformer for Motion Classification", Applied Intelligence, 54(5), pp.3841~3858 (2024)
- S. H. Park, "A Web-Based University Cafeteria Review Management System", Journal of Artificial Intelligence Convergence Technology, 2(3), pp.93~97 (2022)
- J. S. Lee, "Development of an Artificial Intelligence Educational Recommendation System Program using Google App Script", Journal of Artificial Intelligence Convergence Technology, 2(3), pp.98~107 (2022)
- S. M. Lee, "A Design of Metaverse Platform Utilization Educational Program to Restore Lost Space", Journal of Artificial Intelligence Convergence Technology, 2(3), pp.73~78 (2022)