Decoding the Perceived Difficulty of Communicated Contents by Older People: Toward Conversational Robot-Assistive Elderly Care

In this study, we propose a semi-supervised learning model for decoding of the perceived difficulty of communicated content by older people. Our model is based on mapping of the older people's prefrontal cortex (PFC) activity during their verbal communication onto fine-grained cluster spaces of a working memory (WM) task that induces loads on human's PFC through modulation of its difficulty level. This allows for differential quantification of the observed changes in pattern of PFC activation during verbal communication with respect to the difficulty level of the WM task. We show that such a quantification establishes a reliable basis for categorization and subsequently learning of the PFC responses to more naturalistic contents, such as story comprehension. Our contribution is to present evidence on effectiveness of our method for estimation of the older people's perceived difficulty of the communicated contents during an online storytelling scenario.