Journal of Korea Society of Industrial Information Systems (한국산업정보학회논문지)

Korea Society of Industrial Information Systems (한국산업정보학회)
권호 표지
DOI QR코드

DOI QR Code

A Study of Customer Review Analysis for Product Development based on Korean Language Processing

한글 정형화 방법에 기반한 상품평 감성분석의 제품 개발 적용 방법 연구

  • 우제혁 (한국과학기술원 산업 및 시스템공학과) ;
  • 정민규 (한국과학기술원 산업 및 시스템공학과) ;
  • 이재현 (대구대학교 융합산업공학과) ;
  • 서효원 (한국과학기술원 산업 및 시스템공학과)
  • Received : 2021.11.23
  • Accepted : 2021.12.27
  • Published : 2022.02.28
Download PDF
⟨ Previous Next ⟩

Abstract

Online customer review data can be easily collected on the Internet and also they describe sentimental evaluation of a product in different aspects. Previous sentiment analysis studies evaluate the degree of sentiment with review data, which may have multiple sentences describing different product aspects. Since different aspects of a product can be described in a sentence, the proposed method suggested analyzing a sentence to build a pair of a product aspect terms and sentimental terms. Bidirectional LSTM and CRF algorithms were used in this paper. A pair of aspect terms and sentimental terms are evaluated by pre-defined evaluation rules. The paper suggested using the result of evaulation as inputs of QFD, so that the quantified customer voices effect on the requirements of a new product. Online reviews for a hair dryer were used as an example showing that the proposed approach can derive reasonable sentiment analysis results.

온라인 상품평 데이터는 제품의 특성에 대한 구체적인 평가를 담고 있으면서도 인터넷상에서 쉽게 수집할 수 있기에 제품의 장단점 및 긍정/부정 척도를 판단하기에 높은 효용 가치를 가진다. 기존의 감성 분석 연구들은 여러 문장으로 구성된 상품평 전체 단위의 감성 평가 방법을 제안하였다. 제품의 여러 속성별로 감성 평가 결과를 얻을 수 있으면 후속 제품 개발 과정에 유효한 입력이 될 수 있다. 본 논문에서는 제품의 속성 단위의 감성 분석을 하기 위해 상품평의 문장 단위로부터 제품 속성을 추출하여 감성 평가를 수행하는 방법을 제안한다. 먼저 양방향 LSTM과 조건부 무작위장(CRF)을 활용한 문장분석 모델을 통해 제품 속성과 감성어를 추출한다. 추출된 제품 속성별 감성 평가 결과는 본 논문에서 제안하는 감성 평가 규칙을 활용하여 계산된다. 제품 속성별 감성평가 결과는 품질 전개 기법에 적용되어 후속 제품 개발과정에 반영된다. 제안하는 방법론은 헤어드라이기 제품 사례를 통해 적정성을 보여준다.

Keywords

Acknowledgement

이 논문은 산업통상자원부 '소비재 제품 고객평가 데이터 AI 분석 및 제조 활용 서비스 개발' (Project No: 20 9185), 국토교통부 'AI기반 가스·오일 플랜트 운영·유지관리 핵심기술개발' (Project No: 21ATOG-C161933-01), 산업통상자원부 '화학플랜트 수직형 통합 스마트팩토리 패키지 개발' (Project No: 20009324) 프로젝트에 의해 지원되었음.

References

  1. Alvarez-Lopez, T., Juncal-Martinez, J., Fernandez-Gavilanes, M., Costa-Montenegro, E., & Gonzalez-Castano, F. J. (2016). SemEval-2016 task 5: SVM and CRF for aspect detection and unsupervised aspect-based sentiment analysis. Proceedings of the 10th international workshop on semantic evaluation (SemEval-2016), Jun. 16-17, San Diego, CA, USA.
  2. Basiri, M. E., & Kabiri, A. (2017). Sentence-level sentiment analysis in Persian, International Conference on Pattern Recognition and Image Analysis (IPRIA), 84-89. https://doi.org/10.1109/PRIA.2017.7983023.
  3. Chung, S. J. (2020). Aspect-Level Analysis and Predictive Modeling for Electric Vehicle Based on Aspect-Based Sentiment Analysis Using Machine Learning, M.E. Thesis, Graduate School of Seoul National University, Seoul, Korea.
  4. Ding, X., Liu, B., & Yu, P. S. (2008). A holistic lexicon-based approach to opinion mining. Proceedings of the 2008 international conference on web search and data mining, Feb. 11-12, Palo Alto, California.
  5. Hasan, A., Moin, S., Karim, A., & Shamshirband, S. (2018). Machine learning-based sentiment analysis for twitter accounts. Mathematical and Computational Applications, 23(1), 11, https://doi.org/10.3390/mca23010011.
  6. Hauser, J. R., & Clausing, D. (1988). The house of quality, Harvard Business Review, 1-13.
  7. Hu, M., & Liu, B. (2004). Mining and summarizing customer reviews. Proceedings of the 10th ACM SIGKDD international conference on Knowledge discovery and data mining, Aug. 22-25, Seattle WA, USA.
  8. Huang, Z., Xu, W., & Yu, K. (2015). Bidirectional LSTM-CRF models for sequence tagging. arXiv preprint arXiv:1508.01991.
  9. Kim, D. I. (2018). Consumer Sentiment Analysis Using Smartphone Review Comments, M.E. Thesis, Graduate School of engineering, Yonsei University, Seoul, Korea.
  10. Marstawi, A., Sharef, N. M., Aris, T. N. M., & Mustapha, A. (2017). Ontology-based aspect extraction for an improved sentiment analysis in summarization of product reviews. Proceedings of the 8th International Conference on Computer Modeling and Simulation, Jan. 20-23, Canberra, Australia.
  11. Park, H. J., Song, M. C., & Shin, K. S. (2018). Sentiment analysis of korean reviews using cnn: Focusing on morpheme embedding. Journal of intelligence and information systems, 24(2), 59-83. https://doi.org/10.13088/JIIS.2018.24.2.059
  12. Patra, B. G., Soumik, M., Das, D., & Sivaji, B. (2014). Ju_cse: A conditional random field (crf) based approach to aspect based sentiment analysis. Proceedings of the 8th International Workshop on Semantic Evaluation (SemEval 2014), Aug. 23-24, Dublin, Ireland.
  13. Pontiki, M., Galanis, D., Papageorgiou, H., Androutsopoulos, I., Manandhar, S., Al-Smadi, M., Al-Ayyoub, M., Zhao, Y., Qin, B., & De Clercq, O. (2016). SemEval-2016 task 5: Aspect based sentiment analysis. Proceedings of the 10th international workshop on semantic evaluation (SemEval-2016), Jun. 16-17, San Diego, CA, USA.
  14. Sarawgi, K., & Pathak, V. (2017). Opinion mining: aspect level sentiment analysis using SentiWordNet and Amazon web services. International Journal of Computer Applications, 158(6), 31-36. https://doi.org/10.5120/ijca2017912830
  15. Singh, J., Singh, G., & Singh, R. (2016). A review of sentiment analysis techniques for opinionated web text. CSI transactions on ICT, 4(2-4), 241-247. https://doi.org/10.1007/s40012-016-0107-y
  16. Song, M., Park, H., & Shin, K. S. (2019). Attention-based long short-term memory network using sentiment lexicon embedding for aspect-level sentiment analysis in Korean. Information Processing & Management, 56(3), 637-653. https://doi.org/10.1016/j.ipm.2018.12.005
  17. Timoshenko, A., & Hauser, J. R. (2019). Identifying customer needs from user-generated content. Marketing Science, 38(1), 1-20. https://doi.org/10.1287/mksc.2018.1123
  18. Wang, Y., Mo, D. Y., & Tseng, M. M. (2018). Mapping customer needs to design parameters in the front end of product design by applying deep learning. CIRP Annals, 67(1), 145-148. https://doi.org/10.1016/j.cirp.2018.04.018
  19. Zhang, L., Ghosh, R., Dekhil, M., Hsu, M., & Liu, B. (2011). Combining lexicon -based and learning-based methods for Twitter sentiment analysis. HP Laboratories, Technical Report HPL-2011, 89.