Determining Packaging Design Concepts Using K-Means Cluster Genetic Algorithm Methods Through a Kansei Engineering Approach

DOI

10.2991/978-94-6239-687-6_21How to use a DOI?

Keywords

Clustering; Kansei Engineering; K-Means GA; Design Concept; TFIDF

Abstract

Indonesia was the fourth-largest cocoa producer in 2023. However, locally produced specialty chocolate bars have not been able to compete optimally with imported products. One main contributing factor is the lack of appealing and consumer-preferred packaging design. A packaging development approach based on Kansei Engineering (KE) is considered appropriate, as it enables the identification of consumers’ emotional responses to create products aligned with their preferences. The packaging design concept plays a crucial role in the development process. Therefore, this study aims to determine the most optimal packaging design concept using the K-Means method. The Term Frequency–Inverse Document Frequency (TF-IDF) technique was employed to extract consumer emotional responses (Kansei words), while K-Means, K-Medoids, and K-Means Genetic Algorithm methods were applied to cluster the packaging design concepts. The TF-IDF results showed that the Kansei term “chocolate design” had the highest weight (0.5334). All three clustering methods produced three clusters; however, the K-Means Genetic Algorithm demonstrated the best performance, achieving the silhouette score (0.5264), Davies-Bouldin Index of (0.3844), and a Calinski-Harabasz Index of (23.726). Based on the K-Means Genetic Algorithm clustering, the selected design concept is “Usable.” This concept will serve as a reference in determining the packaging design elements.

Copyright

© 2026 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Fahri Fadhillah
AU  - Novi Purnama Sari
AU  - Wiwi Prastiwinarti
AU  - Adita Evalina Fitria Utami
PY  - 2026
DA  - 2026/05/24
TI  - Determining Packaging Design Concepts Using K-Means Cluster Genetic Algorithm Methods Through a Kansei Engineering Approach
BT  - Proceedings of the 8th Mechanical and Industrial Engineering Symposium (MIE 2025)
PB  - Atlantis Press
SP  - 286
EP  - 304
SN  - 2589-4943
UR  - https://doi.org/10.2991/978-94-6239-687-6_21
DO  - 10.2991/978-94-6239-687-6_21
ID  - Fadhillah2026
ER  -