*Artificial Intelligence for Sensory Acceptability Prediction DOI: http://dx.doi.org/10.5772/intechopen.105162*

stabilizers, and vinegar were not critical for the algorithms. Conversely, the oil content (%) showed a weak relationship with the acceptability (�0.25) but it represented an important input for the models. The high influence of this parameter could be related to its role in the product because it contributes to the viscosity, mouthfeel, appearance, and flavor of the product [23]. Regarding the correlations among acceptability and the two sensory attributes (taste and texture) found herein, it agrees with that reported in Caracciolo et al. [24], regarding the willingness to consume (comparable with acceptability) of microgreens (leafy vegetables). Among different features such as aroma, astringency, bitterness, texture, sourness, appearance, and flavor, the authors observed that flavor and texture were the features with more relationship with the willingness to consume [24].
