Abstract

In this letter, we extend our recent results on prediction of the older people's perceived difficulty of verbal communication during a humanoid-mediated storytelling experiment to the case of a longitudinal conversation that was conducted over a four-week period and included a battery of conversational topics. For this purpose, we used our model that estimates the older people's perceived difficulty by mapping their prefrontal cortex (PFC) activity during the 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 enables us to differentially quantify the observed changes in PFC activity during the conversation based on the difficulty level of the WM task. We show that such a quantification forms a reliable basis for learning the PFC activation patterns in response to conversational contents. Our results indicate the ability of our model to predict the older people's perceived difficulty of a wide range of humanoid-mediated tele-conversations, regardless of their type, topic, and duration.

Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call