«up_agr» = unimodal pragmatic consensus, The previous article on the list in the example of discussion texts is quite famous. The list of discussion texts will be beneficial if it is reinforced by the example of the dialogue on convergence and disagreement. Some keywords in «accept and disagree,» which are often used, have been published to express consent and rejection. The expression of consent and disagreement is closely linked to the text of the debate, as it studies a subject from different angles. These types of texts are considered advantages and disadvantages. What the advantages and disadvantages are is explained in the next contribution. Accepting and contradicting are not in a simple binary relationship: there can be several nuances, the degree of this behavior (in whole or in part), indecision about which opinion to follow or defend it (uncertainty) or even a total lack (indifference). Recognition of these variants of the agreement/objection is a key factor for mediating a successful conversation: incompetence or misinterpretation of convergence events can even lead to the total failure of the given interaction. Although languages generally have a number of lexical and syntactic means to express this behavior, it can still be misleading to rely exclusively on the linguistic form. For example, if actor B agrees with actor A, he could say yes; However, the same «yes» can also be used to suggest exactly the opposite, i.e. signify differences of opinion, depending on how the «yes» is pronounced. Alternatively, one can agree or contradict by not even saying a word, but simply by remaining silent: here too, it is the non-verbal behavior that contributes to the understanding of the context, effectively to the pragmatic interpretation of the event.
In doing so, we go beyond simply looking for simple temporal orientations for certain events, but we try to identify behaviors that consist of events that occurred over a longer observation period. It is indeed a cognitive process in which the patterns thus identified are compared to stereotypical patterns of behavior that we already know (either as innate or as acquired), and the pragmatic function of the best concordance is attributed to the given pattern found during the observation period, in our case that related to consent/disagreement. This paper has focused on discovering multimodal compliance/dissent patterns based on data from the HuComTech Corpus. It advocates for a multimodal approach to human interaction by highlighting the interdependence of text, language, and gestures in communication, and shows how important it is to implement human behaviors in more user-to-use human-computer interaction systems. . . .