Annotation and Analysis of the PoliModal Corpus of Political Interviews

In this paper, we present the first available corpus of Italian political interviews with multimodal annotation, consisting of 56 face-to-face interviews taken from a political talk show. We detail the annotation scheme and we present a number of statistical analyses to understand the relation between these multimodal traits and language complexity. We also exploit the corpus to test the validity of existing studies on political orientation and language use, showing that results on our data are not as clear-cut as on English ones.