Automatic tool to annotate smile intensities in conversational face-to-face interactions

Abstract This study presents an automatic tool that allows to trace smile intensities along a video record of conversational face-to-face interactions. The processed output proposes sequence adjusted time intervals labeled following the Smiling Intensity Scale ( Gironzetti, Attardo, and Pickering, 2016 ), 5 levels scale varying from neutral facial expression laughing smile. underlying statistical model this is trained on manually annotated corpus conversations featuring spontaneous expressions. will be detailed in study. can used with benefits for annotating results are twofold. First, evaluation reveals observed agreement 68% between manual annotations. Second, correcting labels interval boundaries outputs reduces by factor 10 annotation as compared spent without pretreatment. Our engine makes use state-of-the-art toolbox OpenFace tracking face measuring Action Units interest all video. documentation scripts our tool, SMAD software, available download at HMAD open source project URL page https://github.com/srauzy/HMAD (last access 31 July 2023).