The Journal of Bigdata (한국빅데이터학회지)

Korea Bigdata Society (한국빅데이터학회)
권호 표지
DOI QR코드

DOI QR Code

Emotion Analysis Using a Bidirectional LSTM for Word Sense Disambiguation

양방향 LSTM을 적용한 단어의미 중의성 해소 감정분석

  • 기호연 (이화여자대학교 일반대학원 빅데이터분석학 협동과정) ;
  • 신경식 (이화여자대학교 일반대학원 빅데이터분석학 협동과정)
  • Received : 2020.08.06
  • Accepted : 2020.08.25
  • Published : 2020.08.30
Download PDF
⟨ Previous Next ⟩

Abstract

Lexical ambiguity means that a word can be interpreted as two or more meanings, such as homonym and polysemy, and there are many cases of word sense ambiguation in words expressing emotions. In terms of projecting human psychology, these words convey specific and rich contexts, resulting in lexical ambiguity. In this study, we propose an emotional classification model that disambiguate word sense using bidirectional LSTM. It is based on the assumption that if the information of the surrounding context is fully reflected, the problem of lexical ambiguity can be solved and the emotions that the sentence wants to express can be expressed as one. Bidirectional LSTM is an algorithm that is frequently used in the field of natural language processing research requiring contextual information and is also intended to be used in this study to learn context. GloVe embedding is used as the embedding layer of this research model, and the performance of this model was verified compared to the model applied with LSTM and RNN algorithms. Such a framework could contribute to various fields, including marketing, which could connect the emotions of SNS users to their desire for consumption.

어휘적 중의성이란 동음이의어, 다의어와 같이 단어를 2개 이상의 의미로 해석할 수 있는 경우를 의미하며, 감정을 나타내는 어휘에서도 어휘적 중의성을 띄는 경우가 다수 존재한다. 이러한 어휘들은 인간의 심리를 투영한다는 점에서 구체적이고, 풍부한 맥락을 전달하는 특징이 있다. 본 연구에서는 양방향 LSTM을 적용하여 중의성을 해소한 감정 분류 모델을 제안한다. 주변 문맥의 정보를 충분히 반영한다면, 어휘적 중의성 문제를 해결하고, 문장이 나타내려는 감정을 하나로 압축할 수 있다는 가정을 기반으로 한다. 양방향 LSTM은 문맥 정보를 필요로 하는 자연어 처리 연구 분야에서 자주 활용되는 알고리즘으로 본 연구에서도 문맥을 학습하기 위해 활용하고자 한다. GloVe 임베딩을 본 연구 모델의 임베딩 층으로 사용했으며, LSTM, RNN 알고리즘을 적용한 모델과 비교하여 본 연구 모델의 성능을 확인하였다. 이러한 프레임워크는 SNS 사용자들의 감정을 소비 욕구로 연결시킬 수 있는 마케팅 등 다양한 분야에 기여할 수 있을 것이다.

Keywords

References

  1. 김해룡, 안광호, 마케팅을 결정하는 소비 감정의 힘: 감정을 팔아라, 서울:원앤원북스, 2019.
  2. 도재학, "국어 문장의 중의성에 대하여: 언표 및 발화 문장에 따른 유형 분류를 중심으로", 아시아문화연구, 제46권, pp.39-72, 2018. https://doi.org/10.34252/acsri.2018.46..002
  3. M. Munezero, "Are they different? Affect feeling emotion sentiment and opinion detection in text," IEEE Trans, Affective Comput. Vol.5, No.2, pp.101-111, 2014. https://doi.org/10.1109/TAFFC.2014.2317187
  4. A. Yadollahi, "Current State of Text Sentiment Analysis from Opinion to Emotion Mining," ACM Computing Surveys, Vol.50, No.2, pp.1-33, 2017. https://doi.org/10.1145/3057270
  5. P. Ekman, "Emotion in the human face: Guidelines for research and an integration of findings," New York, Permagon, 1972.
  6. R. Plutchik, "Emotion: Theory, Research and Experience," Academic Press, New York, NY, 1986.
  7. H. Lovheim, "A new three-dimensional model for emotions and monoamine neurotransmitters," Med Hypotheses, Vol.78, No.2, pp.341-348, 2012. https://doi.org/10.1016/j.mehy.2011.11.016
  8. P. Shaver, "Emotion knowledge: Further exploration of a prototype approach," J. Pers. Soc. Psychol, Vol.52, No.6, 1061, 1987. https://doi.org/10.1037/0022-3514.52.6.1061
  9. M, Lesk, "Automatic Sense Disambiguation Using Machine Readable Dictionaries: How to Tell a Pine Cone from an Ice Cream Cone," Proceedings of the 1986 SIGDOC Conference, pp.24-26, 1986.
  10. Lee, "Supervised Word Sense Disambiguation with Support Vector Machines and Multiple Knowledge Sources," Proceedings of Senseval-3: Third International Workshop on the Evaluation of Systems for the Semantic Analysis of Text, pp.137-140, 2004.
  11. A. Le, "High WSD Accuracy Using Naive Bayesian Classifier with Rich Features," PACLIC 18, Vol.18, pp.105-14, 2004.
  12. A. Yepes, "Word embeddings and recurrent neural networks based on Long-Short Term Memory nodes in supervised biomedical word sense disambiguation," Journal of biomedical informatics, Vol.73, pp.137-147, 2017. https://doi.org/10.1016/j.jbi.2017.08.001
  13. D. Yarowsky, "UNSUPERVISED WORD SENSE DISAMBIGUATION RIVALING SUPERVISED METHODS," In ACL 95, pp.189-196, 1995.
  14. C. Niu, "Context Clustering for Word Sense Disambiguation Based on Modeling Pairwise Context Similarities," In: SENSEVAL- 3: Third International Workshop on the Evaluation of Systems for the Semantic Analysis of Text, pp.187-190, 2004.
  15. A. Graves, A., and Schmidhuber, J. (2005). "Framewise Phoneme Classification with Bidirectional LSTM and Other Neural Network Architectures," Neural Networks, Vol.18 No.5-6, pp.602-610, 2005. https://doi.org/10.1016/j.neunet.2005.06.042
  16. 진승희, "온톨로지 지식 기반 특성치를 활용한 Bidirectional LSTM-CRF 모델의 시퀀스 태깅 성능 향상에 관한 연구", 지능정보연구, 제24권, 제1호, pp.253-267, 2018. https://doi.org/10.13088/jiis.2018.24.1.253
  17. V. Makarenkov, "Choosing the right word: Using bidirectional LSTM tagger for writing support systems," Engineering Applications of Artificial Intelligence, Vol.84, pp.1-10, 2019. https://doi.org/10.1016/j.engappai.2019.05.003
  18. A. Pesaranghader, "One Single Deep Bidirectional LSTM Network for Word Sense Disambiguation of Text Data," Springer Advances in Artificial Intelligence: 31st Canadian Conference on Artificial Intelligence Canada, pp.96-107, 2018.
  19. J. Min, "A Study on Word Sense Disambiguation Using Bidirectional Recurrent Neural Network for Korean Language," Journal of the Korea Society of Computer and Information, Vol.22, No.4, pp.41-49, 2017. https://doi.org/10.9708/jksci.2017.22.04.041
  20. C, Zhang, "Biomedical word sense disambiguation with bidirectional long short-term memory and attention-based neural networks," BMC Bioinformatics, Vol.20, No.502, 2019.
  21. Z, Li, "Context Embedding Based on Bi-LSTM in Semi-Supervised Biomedical Word Sense Disambiguation," IEEE Access, Vol.7, pp.72928-72935, 2019. https://doi.org/10.1109/ACCESS.2019.2912584
  22. P. Jeffrey, "Glove: Global vectors for word representation," Proceedings of the Empiricial Methods in Natural Language Processing, 2014.
  23. S. Mike, "Bidirectional recurrent neural networks," Signal Processing, IEEE Transactions on, Vol.45, No.11, pp.2673-2681, 1997. https://doi.org/10.1109/78.650093
  24. V. Nair, "Rectified Linear Units Improve Restricted Boltzmann Machines," In Proceedings of the 27th International Conference on Machine Learning, pp.807-814, 2010.

Cited by

  1. Polysemous Words in English Movies, Learning Obstacles or Gifted Talent? vol.22, pp.4, 2021, https://doi.org/10.16875/stem.2021.22.4.14