Emotional design engineering for packaging of olive oil using machine learning techniques
Consumer behaviour, and therefore purchase intentions, are affected by the visual elements of packaging. This is particularly important for products in the agri-food sector, especially for olive oil. In this work, the perception of different packaging options by olive oil users is analysed. For this...
| Autores: | , , , |
|---|---|
| Tipo de recurso: | artículo |
| Estado: | Versión publicada |
| Fecha de publicación: | 2025 |
| País: | España |
| Institución: | Universidad de Sevilla (US) |
| Repositorio: | idUS. Depósito de Investigación de la Universidad de Sevilla |
| OAI Identifier: | oai:idus.us.es:11441/176996 |
| Acceso en línea: | https://hdl.handle.net/11441/176996 https://doi.org/10.1080/23311916.2025.2555340 |
| Access Level: | acceso abierto |
| Palabra clave: | Kansei engineering Machine learning Sustainable design Engineering design Olive oil packaging |
| Sumario: | Consumer behaviour, and therefore purchase intentions, are affected by the visual elements of packaging. This is particularly important for products in the agri-food sector, especially for olive oil. In this work, the perception of different packaging options by olive oil users is analysed. For this, machine learning tools are employed in the synthesis phase of the Kansei Engineering (KE) methodology. On the one hand, four properties (material, colour, price, capacity) were considered for the definition of the property space. Subsequently, for the determination of the semantic space, a literature search was first performed, and an affinity analysis was then carried out, followed by a pilot survey to reduce the number of Kanseis. The semantic space consisted of 17 and 6 Kanseis, respectively. The final survey was given to a sample of 100 Andalusian citizens. Machine learning techniques (linear regression, ridge regression SVR) were employed for the synthesis phase. The results show that KE can be used as a tool to optimise the design of olive oil packaging by using machine learning tools in the synthesis phase. This study can provide the basis for other studies of other agri-food products and for the use of other artificial intelligence tools. |
|---|