“…Specifically, the methodology used, which consists of multimodal and discursive analyses, can fall within the field of Social Signal Processing ( Vinciarelli et al, 2011 ) and of Sentic Computing ( Susanto et al, 2021 ). This effort has been applied also within the field of automatic signal detection, which recently have crossed both linguistic levels, as in the case of Sentiment Multimodal Analysis ( Tiwari et al, 2020 ), and other body channel detection (e.g., facial or vocal expressions and body postures) ( Soleymani et al, 2017 ). More in general, the recent remarkable development of the Affective Computing and the introduction of deep learning increased the development of more sophisticated systems ( Wadawadagi and Pagi, 2020 ) aimed at predicting and automatically detecting emotional patterns starting from multimodal input ( Morency et al, 2011 ; Poria et al, 2016 ; Chaturvedi et al, 2019 ; Yadav and Vishwakarma, 2019 ), with a real-time output ( Cambria et al, 2013 ; Tran and Cambria, 2018 ).…”