Transmission of information in living organism occurred through different mechanisms amongst which electrical signaling is a widely conserved process in life kingdom. This transmission allow driving appropriate physiological processes in response to changing environmental conditions. We recently report that plant water status can be assessed with the use of a novel biosensor based on bioelectrical signal combined with supervised machine learning algorithms. This innovative electrophysiological sensor can be used in greenhouse production conditions, without a Faraday cage, enabling real-time electric signal measurements. Successful crop production requires that crop pests and diseases be managed so that their effects on the plants are minimized. In soilless tomato cultivation, Tetranychus urticae (spider mites) is one of the common pest that affect the culture. In this study, we utilize the electrophysiological sensors in order to detect the presence of spider mites. We show that bioelectrical activity is significantly modified in response to spider mites infestation. Furthermore, the automatic classification of plant status using supervised machine learning allows accurate detection of the presence of spider mites. To date, visual crop monitoring is the continually on-going surveillance to detect the presence of a pest at the very early stages of development of the pest population, before economic damage has occurred. Therefore, electrophysiological assessment represents an efficient alternative agronomic tool at the service of producers for decision support or for taking preventive measures before initial visual symptoms of plant stress appear.