Journal of the Korean Society of Clothing and Textiles (한국의류학회지)

The Korean Society of Clothing and Textiles (한국의류학회)
권호 표지
DOI QR코드

DOI QR Code

Development of Online Fashion Thesaurus and Taxonomy for Text Mining

텍스트마이닝을 위한 패션 속성 분류체계 및 말뭉치 웹사전 구축

  • Seyoon Jang (Research Institute of Human Ecology, Seoul National University) ;
  • Ha Youn Kim (Dept. of Clothing & Textiles, Kunsan National University) ;
  • Songmee Kim (Dept. of Textiles, Merchandising, and Fashion Design, Seoul National University) ;
  • Woojin Choi (Dept. of Textiles, Merchandising, and Fashion Design, Seoul National University) ;
  • Jin Jeong (Dept. of Textiles, Merchandising, and Fashion Design, Seoul National University) ;
  • Yuri Lee (Dept. of Textiles, Merchandising, and Fashion Design, Seoul National University/Research Institute of Human Ecology, Seoul National University)
  • 장세윤 (서울대학교 생활과학연구소) ;
  • 김하연 (군산대학교 의류학과) ;
  • 김송미 (서울대학교 의류학과) ;
  • 최우진 (서울대학교 의류학과) ;
  • 정진 (서울대학교 의류학과) ;
  • 이유리 (서울대학교 의류학과/서울대학교 생활과학연구소)
  • Received : 2022.09.29
  • Accepted : 2022.11.08
  • Published : 2022.12.31
Download PDF
⟨ Previous Next ⟩

Abstract

Text data plays a significant role in understanding and analyzing trends in consumer, business, and social sectors. For text analysis, there must be a corpus that reflects specific domain knowledge. However, in the field of fashion, the professional corpus is insufficient. This study aims to develop a taxonomy and thesaurus that considers the specialty of fashion products. To this end, about 100,000 fashion vocabulary terms were collected by crawling text data from WSGN, Pantone, and online platforms; text subsequently was extracted through preprocessing with Python. The taxonomy was composed of items, silhouettes, details, styles, colors, textiles, and patterns/prints, which are seven attributes of clothes. The corpus was completed through processing synonyms of terms from fashion books such as dictionaries. Finally, 10,294 vocabulary words, including 1,956 standard Korean words, were classified in the taxonomy. All data was then developed into a web dictionary system. Quantitative and qualitative performance tests of the results were conducted through expert reviews. The performance of the thesaurus also was verified by comparing the results of text mining analysis through the previously developed corpus. This study contributes to achieving a text data standard and enables meaningful results of text mining analysis in the fashion field.

Keywords

Acknowledgement

본 연구는 한국콘텐츠진흥원의 '소상공인의 패션디자인 향상을 위한 지능형 패션 수요 예측 및 판로 분석 기술 개발(R2020040102)' 사업의 연구비를 지원받아 수행되었음.

References

  1. Ahn, D. J. (2016). Textile science: Merchandiser에게 꼭 필요 한 섬유지식 (2판) [Textile science: Fiber knowledge essential to merchandiser (2nd ed.)]. Seoul: Hanol.
  2. Ajmani, S., Ghosh, H., Mallik, A., & Chaudhury, S. (2013). An ontology based personalized garment recommendation system. Proceedings of the 2013 IEEE/WIC/ACM International Joint Conferences on Web Intelligence (WI) and Intelligent Agent Technologies (IAT), USA, 03, 17-20. doi:10.1109/WI-IAT.2013.143
  3. Baek, J. H., & Bae, S. J. (2017). A study on the utilization characteristics of art print for strengthening visual identity of fashion brand. Journal of the Korean Society of Design Culture, 23(3), 401-419. doi:10.18208/ksdc.2017.23.3.401
  4. Bengfort, B., Bilbro, R., & Ojeda, T. (2018). Applied text analysis with Python: Enabling language-aware data products with machine learning. Sebastopol, CA: O'Reilly Media, Inc.
  5. Bollacker, K., Diaz-Rodriguez, N., & Li, X. (2016, January 1). Beyond clothing ontologies: Modeling fashion with subjective influence networks. Paper presented at the KDD Workshop on Machine Learning meets Fashion, San Francisco, CA.
  6. Cha, S. (2018). A study on the tone classification system of KS A 0011 in the perspective of chromatics. Journal of Korea Society of Color Studies, 32(2), 129-150. doi:10.17289/jkscs.32.2.201805.129
  7. Chakraborty, S., Hoque, S. M. A., & Kabir, S. M. F. (2020). Predicting fashion trend using runway images: application of logistic regression in trend forecasting. International Journal of Fashion Design, Technology and Education, 13(3), 376-386. doi:10.1080/17543266.2020.1829096
  8. Choi, J. I. (2014). 불한 웹사전의 신조어 수용 [A reflection on neologisms in the French-Korean dictionary on the web]. Etudes de Langues et Litterature Francaises, 100, 813-834.
  9. Choi, Y.-H., & Lee, K.-H. (2020). Ethical fashion research trend using text mining: Network analysis of the published literature 2009-2019. Fashion & Textile Research Journal, 22(2), 181-191. doi:10.5805/SFTI.2020.22.2.181
  10. Choo, S. (2001). Images of fashion fabric based on color and texture (Unpublished doctoral dissertation). Yonsei University, Seoul.
  11. Danescu-Niculescu-Mizil, C., & Lee, L. (2011). Chameleons in imagined conversations: A new approach to understanding coordination of linguistic style in dialogs. Proceedings of the 2nd Workshop on Cognitive Modeling and Computational Linguistics, USA, 76-87. doi:10.48550/arXiv.1106.3077
  12. DeLong, M. R. (1987). The way we look: A framework for visual analysis of dress. Ames, IA: Iowa State University Press.
  13. Fashionary. (2021). Fashionpedia: The visual dictionary of fashion design. Hong Kong: Fashionary International Limited.
  14. Gandomi, A., & Haider, M. (2015). Beyond the hype: Big data concepts, methods, and analytics. International Journal of Information Management, 35(2), 137-144. doi:10.1016/j.ijinfomgt.2014.10.007
  15. Garshol, L. M. (2004). Metadata? Thesauri? Taxonomies? Topic maps! Making sense of it all. Journal of Information Science, 30(4), 378-391. doi:10.1177/0165551504045856
  16. Gruber, T. R. (1995). Toward principles for the design of ontologies used for knowledge sharing? International Journal of Human-Computer Studies, 43(5-6), 907-928. doi:10.1006/ijhc.1995.1081
  17. Guan, C., Qin, S., Ling, W., & Long, Y. (2018). Enhancing apparel data based on fashion theory for developing a novel apparel style recommendation system. In A. Rocha, H. Adeli, L. P. Reis, & S. Costanzo (Eds.), Trends and advances in information systems and technologies: Vol. 3 (pp. 31-40). Cham: Springer. doi:10.1007/978-3-319-77700-9_4
  18. Guan, C., Qin, S., & Long, Y. (2019). Apparel-based deep learning system design for apparel style recommendation. International Journal of Clothing Science and Technology, 31(3), 376-389. doi:10.1108/IJCST-02-2018-0019
  19. Han, K. H. (2019). A study on the consumer's perception of HiSeoul fashion show using big data analysis. Journal of Fashion Business, 23(5), 81-95. doi:10.12940/jfb.2019.23.5.81
  20. Han, S.-Y., Cho, Y., & Lee, Y. (2016). The effect of the fashion product classification method in online shopping sites. Journal of the Korean Society of Clothing and Textiles, 40(2), 287-304. doi:10.5850/JKSCT.2016.40.2.287
  21. Heo, S. H., & Nah, K. (2019). Brand relationship of material and color identity according to color scheme. Journal of the Korean Society of Design Culture, 25(3), 523-534. doi:10.18208/ksdc.2019.25.3.523
  22. Hong, Y. J., Kim, R. R., Lim, S. E., & Kim, Y. I., (2014). The type and characteristics of the modern men's fashion images. Journal of the Korean Society of Costume, 64(5), 18-29. doi:10.7233/jksc.2014.64.5.018
  23. Horn, M. J., & Gurel, L. M. (1981). The second skin: An interdisciplinary study of clothing (3rd ed.). Boston, MA: Houghton Mifflin Company
  24. Jang, N., & Kim, M.-J. (2020). Material as a key element of fashion trend in 2010~2019 - Text mining analysis -. Fashion & Textile Research Journal, 22(5), 551-560. doi:10.5805/SFTI.2020.22.5.551
  25. Jang, S., Kim, H. Y., Lee, Y., Soel, J., Kim, S., & Lee, S.-g. (2022). Deep learning for classification of high-end fashion brand sensibility. Journal of the Korean Society of Clothing and Textiles, 46(1), 165-181. doi:10.5850/JKSCT.2022.46.1.165
  26. Kiapour, M. H., Yamaguchi, K., Berg, A. C., & Berg, T. L. (2014). Hipster wars: Discovering elements of fashion styles. In D. Fleet, T. Pajdla, B. Schiele, & T. Tuytelaars (Eds.), Computer vision -- ECCV 2014 13th European Conference, Zurich, Switzerland, September 6-12, 2014, Proceedings, Part I (pp. 472-488). Cham: Springer. doi:10.1007/978-3-319-10590-1_31
  27. Kim, C. E., & Lee, J. H. (2018). Trends of big data and artificial intelligence in the fashion industry. Journal of the Korean Society of Clothing and Textiles, 42(1), 148-158. doi:10.5850/JKSCT.2018.42.1.148
  28. Kim, H., & Lee, H. K. (2022). Changes in the perception of second-hand fashion consumption in the post-pandemic era. Fashion & Textile Research Journal, 24(1), 66-80. doi:10.5805/SFTI.2022.24.1.66
  29. Kim, J. Y., Oh, K. W., & Jung, H. J. (2015). Creating the idea of textile print pattern design using the visual expression of popular music. Fashion & Textile Research Journal, 17(4), 524-540. doi:10.5805/SFTI.2015.17.4.524
  30. Kim, S.-Y., & Yoon, S.-W. (2013). Fashion design development and type analysis of redesign using clothing details. Journal of the Korea Fashion & Costume Design Association, 15(1),191-206.
  31. Kim, Y.-K. (2008). Development of indicators for evaluating the web credibility by goodness-of-fit analysis. Journal of the Korean Society for Information Management, 25(4), 185-204. doi:10.3743/KOSIM.2008.25.4.185
  32. Korean Apparel Industry Association. (2009, October). 봉제용어 순화집 [Refined terminology of sewing] [PDF document]. The Korean Society of Clothing and Textiles. Retrieved from https://www.ksct.or.kr/up_file/dboard_dataroom%5B19%5D%5B0%5D
  33. Kotler, P., & Armstrong, G. (2015). Principles of marketing (16th ed.). Boston, MA: Pearson.
  34. Kwon, S., & Park, M. (2021). A study on the design characteristics of athleisure look in image-based SNS. Journal of the Korean Society of Clothing and Textiles, 45(1), 17-27. doi:10.5850/JKSCT.2021.45.1.17
  35. Lamb, J. M., & Kallal, M. J. (1992). A conceptual framework for apparel design. Clothing and Textiles Research Journal, 10(2), 42-47. doi:10.1177/0887302X9201000207
  36. Lee, H. G. (2015). The types of style (Unpublished doctoral dissertation). Seoul National University, Seoul.
  37. Lee, J.-J., & Park, E. K. (2006). Lifestyle & trend (Rev. ed.). Seoul: Yekyong Publishing Co.
  38. Lee, K.-H. (2009). Planning of systematic color coordinate system and manufacture of color paper for establishment of basic color education. Journal of the Korean Society for Clothing Industry, 11(5), 709-719.
  39. Lee, K. M. (2018). Artificial intelligence. Paju: Life & Power Press Co., Ltd.
  40. Littrell, M. A., & Miller, N. J. (2001) Marketing across cultures: Consumers' perceptions of product complexity, familiarity, and compatibility. Journal of Global Marketing, 15(1), 67-86. doi:10.1300/J042v15n01_05
  41. Liu, Z., Luo, P., Qiu, S., Wang, X., & Tang, X. (2016). DeepFashion: Powering robust clothes recognition and retrieval with rich annotations. Proceedings of 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), USA, 1096-1104. doi:10.1109/CVPR.2016.124
  42. Mallavarapu, T., Cranfill, L., Kim, E. H., Parizi, R. M., Morris, J., & Son, J. (2021). A federated approach for fine-grained classification of fashion apparel. Machine Learning with Applications, 6:100118. doi:10.1016/j.mlwa.2021.100118
  43. Ministry of Science and ICT. (2022, July 12). AI 학습용 데이터 190종 추가 개방…총 381종으로 늘어 [Additional 190 types of data for AI learning will be opened...a total of 381 types]. 대한민국 정책브리핑 [Korea Policy Briefing]. Retrieved from https://www.korea.kr/news/policyNewsView.do?newsId=148903465
  44. Mizoguchi, R. (2012). Ontology engineering (K.-S. Choi, & D.-S. Hwang, Trans.). Seoul: Dooyangsa. (Original work published 2005)
  45. Noy, N. F., & McGuinness, D. L. (2001, March). Ontology development 101: A guide to creating your first ontology [PDF document]. Stanford Knowledge Systems Laboratory Technical Report KSL-01-05 and Stanford Medical Informatics Technical Report SMI-2001-0880. Retrieved from https://protege.stanford.edu/publications/ontology_development/ontology101.pdf
  46. Park, J. H. (2012). 한국어 동사 의미망 구축 방법론 [Methodology for constructing the meaning network of Korean verbs]. Seoul: Chung Woon.
  47. Park, N., & Choi, Y. (2020a). A form attribute classification system for fashion items. International Journal of Fashion Design, Technology and Education, 13(1), 11-19. doi:10.1080/17543266.2019.1664641
  48. Park, N., & Choi, Y. (2020b). Color & texture attribute classification system of fashion item image for standardizing learning data in fashion AI. Journal of the Korean Society of Clothing and Textiles, 44(2), 354-368. doi:10.5850/JKSCT.2020.44.2.354
  49. Park, N., & Choi, Y. (2021). Classification system of fashion emotion for the standardization of data. Journal of the Korean Society of Clothing and Textiles, 45(6), 949-964. doi:10.5850/JKSCT.2021.45.6.949
  50. Ryu, H.-J. (2010). Pattern fashion. Seoul: Idambooks.
  51. Sadeh, G., Fritz, L., Shalev, G., & Oks, E. (2019, June 15). Joint visual-textual embedding for multimodal style search. Cornell University. Retrieved from https://arxiv.org/abs/1906.06620
  52. Seo, Y., & Kim, Y. (2019). Characteristics and network analysis of seasonal fashion trend color. Journal of Korea Society of Color Studies, 33(2), 17-28. doi:10.17289/jkscs.33.2.201905.17
  53. Seo, Y., & Shin, K.-s. (2019). Hierarchical convolutional neural networks for fashion image classification. Expert Systems with Applications, 116, 328-339. doi:10.1016/j.eswa.2018.09.022
  54. Shin, S.-Y., & Kim, Y.-I. (2013). The classification of fashion frame and fashion image of Korean women in their twenties and thirties. Journal of the Korean Society of Costume, 63(4), 118-131. doi:10.7233/jksc.2013.63.4.118
  55. Song, E.-y., & Lim, H.-s. (2021). Perceptions and trends of digital fashion technology - A big data analysis -. Fashion & Textile Research Journal, 23(3), 380-389. doi:10.5805/SFTI.2021.23.3.380
  56. Sung, K.-S. (2020). Social media big data analysis of Z-generation fashion. Journal of the Korea Fashion & Costume Design Association, 22(3), 49-61. doi:10.30751/kfcda.2020.22.3.49
  57. Takagi, M., Simo-Serra, E., Iizuka, S., & Ishikawa, H. (2017). What makes a style: Experimental analysis of fashion prediction. Proceedings of 2017 IEEE International Conference on Computer Vision Workshops (ICCVW), Italy, 2247-2253. doi:10.1109/ICCVW.2017.263
  58. TEXTOM. (n.d.) About TEXTOM. TEXTOM. Retrieved from https://www.textom.co.kr/home/sub/overview.php?pnm=1
  59. Tortora, P. G., & Keiser, S. J. (2014). The fairchild books dictionary of fashion. (4th ed.). New York, NY: Bloomsburg Publishing Inc.
  60. Uschold, M., King, M., Moralee, S., & Zorgios, Y. (1998). The enterprise ontology. The Knowledge Engineering Review, 13(1), 31-89. doi:10.1017/S0269888998001088
  61. Vogiatzis, D., Pierrakos, D., Paliouras, G., Jenkyn-Jones, S., & Possen, B. J. H. H. A. (2012). Expert and community based style advice. Expert Systems with Application, 39(12), 10647-10655. doi:10.1016/j.eswa.2012.02.178
  62. Wu, H., Gao, Y., Guo, X., Al-Halah, Z., Rennie, S., Grauman, K., & Feris, R. (2021). Fashion IQ: A new dataset towards retrieving images by natural language feedback. Proceedings of 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), USA, 11302-11312. doi:10.1109/ CVPR46437.2021.01115
  63. Xiao, H., Rasul, K., & Vollgraf, R. (2017, August 25). FashionMNIST: a novel image dataset for benchmarking machine learning algorithms. Cornell University. Retrieved from https://arxiv.org/abs/1708.07747
  64. Young, D. E. (2018). Swatch reference guide for fashion fabrics (4th ed.). New York, NY: Bloomsburg Publishing Inc.
  65. Zheng, S., Yang, F., Kiapour, M. H., & Piramuthu, R. (2018). ModaNet: A large-scale street fashion dataset with polygon annotations. Proceedings of the 26th ACM international conference on Multimedia, Korea, 1670-1678. doi:10.1145/32 40508.3240652
  66. Zou, X., Kong, X., Wong, W., Wang, C., Liu, Y., & Cao, Y. (2019). FashionAI: A hierarchical dataset for fashion understanding. Proceedings of the 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CV PRW), USA, 296-304. doi:10.1109/CVPRW.2019.00039