As a guest user you are not logged in or recognized by your IP address. You have
access to the Front Matter, Abstracts, Author Index, Subject Index and the full
text of Open Access publications.
Detecting early signs of dementia in everyday situations becomes more and more important in a rapidly aging society. Language dysfunctions are recognized as the prominent signs of dementia. Previous computational studies characterized these language dysfunctions by using acoustic and linguistic features for detecting dementia. However, they mainly investigated language dysfunctions collected from patients during neuropsychological tests. Language dysfunctions observed during regular conversations in everyday situations received little attention. One of the dysfunctions associated with dementia which is frequently observed in regular conversations is the repetition of a topic on different days. In this study, we propose a feature to characterize topic repetition in conversations on different days. We used conversational data obtained from a daily monitoring service of eight elderly people, two of whom had dementia. Through the analysis of topic extraction with latent Dirichlet allocation, we found that the frequency of topic repetition was significantly higher in people with dementia than in the control group. The results suggest that our proposed feature for identifying topic repetition in regular conversations on different days might be used for detecting dementia.
This website uses cookies
We use cookies to provide you with the best possible experience. They also allow us to analyze user behavior in order to constantly improve the website for you. Info about the privacy policy of IOS Press.
This website uses cookies
We use cookies to provide you with the best possible experience. They also allow us to analyze user behavior in order to constantly improve the website for you. Info about the privacy policy of IOS Press.