DOI QR코드

DOI QR Code

A Study on the Product Planning Model based on Word2Vec using On-offline Comment Analysis: Focused on the Noiseless Vertical Mouse User

온·오프라인 댓글 분석이 활용된 Word2Vec 기반 상품기획 모델연구: 버티컬 무소음마우스 사용자를 중심으로

  • Ahn, Yeong-Hwi (Division of Computer Engineering, Kongju National University)
  • 안영휘 (국립공주대학교 컴퓨터공학과)
  • Received : 2021.08.31
  • Accepted : 2021.10.20
  • Published : 2021.10.28

Abstract

In this paper, we conducted word-to-word similarity analysis of standardized datasets collected through web crawling for 10,000 Vertical Noise Mouses using Word2Vec, and made 92 students of computer engineering use the products presented for 5 days, and conducted self-report questionnaire analysis. The questionnaire analysis was conducted by collecting the words in the form of a narrative form and presenting and selecting the top 50 words extracted from the word frequency analysis and the word similarity analysis. As a result of analyzing the similarity of e-commerce user's product review, pain (.985) and design (.963) were analyzed as the advantages of click keywords, and the disadvantages were vertical (.985) and adaptation (.948). In the descriptive frequency analysis, the most frequently selected items were Vertical (123) and Pain (118). Vertical (83) and Pain (75) were selected for the advantages of selecting the long/demerit similar words, and adaptation (89) and buttons (72) were selected for the disadvantages. Therefore, it is expected that decision makers and product planners of medium and small enterprises can be used as important data for decision making when the method applied in this study is reflected as a new product development process and a review strategy of existing products.

본 논문에서는 버티컬 무소음 마우스 10,000건에 대한 웹크롤링을 통해 수집된 정형화된 데이터셋을 Word2Vec을 이용하여 단어 간 유사도분석을 시행하고 컴퓨터공학과 대학생 92명에게 5일 동안 제시된 상품을 사용하게 하고 자가보고식 설문 분석을 시행하도록 하였다. 설문 분석은 서술식 형태로 수집하여 단어빈도 분석과 단어 간 유사도분석에서 추출된 상위 50개 단어를 제시하고 선택하는 방식으로 이루어졌다. 전자상거래 사용자 상품평 유사도 분석결과 내용 중 클릭 키워드에 대한 장점으로 통증(.985), 디자인(.963)가 분석되었으며 단점은 가볍다(.952), 적응(.948)이었다. 서술식 빈도분석에서는 버티컬(123개), 통증(118개)이 가장 많이 선택 되었으며 장/단점 유사단어를 선택에 해당되는 장점에서는 버티컬(83개), 통증(75개) 선택 되었으며 단점에서는 적응(89개), 버튼(72개)이었다. 따라서 본 연구에서 적용한 방식을 상품기획 프로세스의 신상품 개발 및 기존 상품의 검토 전략으로 반영 시 중견기업, 중소기업의 의사결정자와 상품기획자는 의사결정에 중대한 자료로 활용 할 수 있을 것으로 기대된다.

Keywords

References

  1. Statistics Korea, Trend of online shopping[Internet] Seoul: Statistics Korea [cited 2024 August 14]. Available from: https://kostat.go.kr/portal/korea/kor_nw/1/1/index.board?bmode=read&aSeq=391169
  2. Q. Y. Hao, S. J. Lee & K. R. Lee. (2015). The Acceptance of Customer Reviews in Taobao. Journal of the Korea Convergence Society, 6(4), 205-212. DOI:10.15207/jkcs.2015.6.4.205
  3. D. J. Kim, D. in. Park & J. S. Park. (2018). Study on the Change of Marketing Strategy through Data Mining Technique. Korea Business Review, 22(2), 177-194. DOI:10.17287/kbr.2018.22.2.177
  4. D. Lee, J. C. Jo & H. S. Lim (2017). User Sentiment Analysis on Amazon Fashion Product Review Using Word Embedding. Journal of the Korea Convergence Society, 8(4), 1-8. DOI:10.15207/jkcs.2017.8.4.001
  5. S. Lim, H. Lee & Y. Yoon (2020). Prediction of New Drug-Side Effect Relation using Word2Vec Model-based Word Similarity. The Journal of Korean Institute of Information Technology, 18(11), 25-33. DOI:10.14801/jkiit.2020.18.11.25
  6. D. Y. Kim & Y. G. Lee. (2018). News based Stock Market Sentiment Lexicon Acquisition Using Word2Vec. The Korea Journal of BigData, 3(1), 13-20. DOI:10.36498/kbigdt.2018.3.1.13
  7. J. N. Yun, G. H. Kim. & D. K. Ryoo. (2018). A Study on Early Warning Model in the Dry Bulk Shipping Industry by Signal Approach. Journal of Navigation and Port Research, 42(1), 57-66. https://doi.org/10.5394/KINPR.2018.42.1.57
  8. J. E. Ahn, Y. J. Kim, H. S. Kim, W. J. Kim, & Lee, Y. (2017). A study on medical herb recommendation system using word2vec. In Proceedings of the Korean Society of Computer Information Conference. 83-85
  9. H. Kang. & J. Yang (2019). Optimization of Word2vec Models for Korean Word Embeddings. Journal of Digital Contents Society, 20(4), 825-833. DOI:10.9728/dcs.2019.20.4.825
  10. T. Mikolov, K. Chen, G. Corrado & Dean, J. (2013). Efficient estimation of word representations in vector space. arXiv preprint arXiv:1301.3781.
  11. K. Heo, J. Yang, D. Kim, K. Bok & J. Yoo. (2019). Design and Implementation of Minutes Summary System Based on Word Frequency and Similarity Analysis. The Journal of the Korea Contents Association, 19(10), 620-629.
  12. Y. H. Ahn & K. R. Park. (2021). Product Planning using Similarity Analysis Technique Based on Word2Vec Model. In Proceedings of the Korean Society of Computer Information Conference 11-12.
  13. J. C. Yun. H. C. Kim, J. J. Kim. & S. D. Youn. (2010). A Study on the CBR Pattern using Similarity and the Euclidean Calculation Pattern. The Journal of the Korean Institute of Information and Communication Engineering, 14(4), 875-885. DOI:10.6109/jkiice.2010.14.4.875
  14. Y. S. Jeon (2020). Management for Reducing Emissions in the Seoul Metropolitan Area during Heat Wave Episodes using CMAQ. Master's dissertation. KonKuk University, Seoul.
  15. J. W. Choi & D.-K. An (2016). A Study on the Data Analysis of the Written Comments in Lecture Evaluation. Journal of Digital Convergence, 14(11), 101-106. DOI:10.14400/jdc.2016.14.11.101
  16. L. H. Chen, W. C. Ko. & F. T. Yeh. (2017). Approach based on fuzzy goal programing and quality function deployment for new product planning. European Journal of Operational Research, 259(2), 654-663. https://doi.org/10.1016/j.ejor.2016.10.028