Robot chefs on the menu: decoding emotions and intentions with PLS-ANN-fsQCA

Purpose Drawing from affect theory and the uncanny valley theory, this study aims to investigate the psychological factors influencing consumers’ ongoing willingness to use robotic chefs. It considers the dual emotional effects of curiosity and trust against feelings of ostracism and eeriness, exploring both straightforward and complex pathways to maintaining engagement. Design/methodology/approach Using a multi-method approach, the authors combined partial least squares structural equation modelling (PLS-SEM), artificial neural networks (ANN) and fuzzy set qualitative comparative analysis (fsQCA) to analyse data collected from a survey of 336 consumers with experience using robot chefs. Findings PLS-SEM identifies trust as a critical positive driver and mediator, whereas ostracism and eeriness adversely affect continuous consumption intention (CCI). Curiosity by itself does not have a direct impact on CCI. ANN supports the nonlinear significance of these predictors. FsQCA uncovers five different pathways to achieving high CCI, highlighting causal asymmetry. Trust remains a fundamental condition, but high CCI can also result from curiosity, even when eeriness is present. Practical implications Restaurants should focus on establishing trust by being transparent and dependable. To avoid the uncanny valley effect, robotic designs should emphasise functional looks rather than trying to closely mimic humans. After the initial experience, marketing should shift from highlighting novelty to emphasising trust. Originality/value This study provides a detailed framework for adopting robotic chefs, going beyond simple linear models. It highlights how emotions play a conditional role and showcases the effectiveness of combining PLS-SEM, ANN and fsQCA methods to understand the complex nature of consumer behaviour in human−robot interactions.