AUTHOR=Steinert Lars , Putze Felix , Küster Dennis , Schultz Tanja TITLE=Predicting Activation Liking of People With Dementia JOURNAL=Frontiers in Computer Science VOLUME=3 YEAR=2022 URL=https://www.frontiersin.org/journals/computer-science/articles/10.3389/fcomp.2021.770492 DOI=10.3389/fcomp.2021.770492 ISSN=2624-9898 ABSTRACT=

Physical, social and cognitive activation is an important cornerstone in non-pharmacological therapy for People with Dementia (PwD). To support long-term motivation and well-being, activation contents first need to be perceived positively. Prompting for explicit feedback, however, is intrusive and interrupts the activation flow. Automated analyses of verbal and non-verbal signals could provide an unobtrusive means of recommending suitable contents based on implicit feedback. In this study, we investigate the correlation between engagement responses and self-reported activation ratings. Subsequently, we predict ratings of PwD based on verbal and non-verbal signals in an unconstrained care setting. Applying Long-Short-Term-Memory (LSTM) networks, we can show that our classifier outperforms chance level. We further investigate which features are the most promising indicators for the prediction of activation ratings of PwD.