Interpretability of Gradual Semantics in Abstract Argumentation

rgumentation, in the field of Artificial Intelligence, is a for-malism allowing to reason with contradictory information as well as tomodel an exchange of arguments between one or several agents. For thispurpose, many semantics have been defined with, amongst them, grad-ual semantics aiming to assign an acceptability degree to each argument.Although the number of these semantics continues to increase, there iscurrently no method allowing to explain the results returned by thesesemantics. In this paper, we study the interpretability of these seman-tics by measuring, for each argument, the impact of the other argumentson its acceptability degree. We define a new property and show that thescore of an argument returned by a gradual semantics which satisfies thisproperty can also be computed by aggregating the impact of the otherarguments on it. This result allows to provide, for each argument in anargumentation framework, a ranking between arguments from the most to the least impacting ones w.r.t a given gradual semantics