원문정보
한국인터넷방송통신학회
International Journal of Internet, Broadcasting and Communication
Vol.13 No.2
2021.05
pp.173-178
피인용수 : 0건 (자료제공 : 네이버학술정보)
초록
영어
In this paper, we find a suitable methodology for Korean Sentiment Analysis through a comparative experiment in which methods of embedding and natural network models are learned at the highest accuracy and fastest speed. The embedding method compares word embeddeding and Word2Vec. The model compares and experiments representative neural network models CNN, RNN, LSTM, GRU, Bi-LSTM and Bi-GRU with IKEA review data. Experiments show that Word2Vec and BiGRU had the highest accuracy and second fastest speed with 94.23% accuracy and 42.30 seconds speed. Word2Vec and GRU were found to have the third highest accuracy and fastest speed with 92.53% accuracy and 26.75 seconds speed.
목차
Abstract
1. Introduction
2. Related research
2.1 CNN
2.2 RNN
2.3 LSTM
2.4 GRU
2.5 BiLSTM
2.6 BiGRU
3. Experiment
4. Experiment result
5. Conclusion
References
1. Introduction
2. Related research
2.1 CNN
2.2 RNN
2.3 LSTM
2.4 GRU
2.5 BiLSTM
2.6 BiGRU
3. Experiment
4. Experiment result
5. Conclusion
References
저자정보
참고문헌
자료제공 : 네이버학술정보